Welcome to Smart Agriculture 中文

Top Read Articles

    Published in last 1 year |  In last 2 years |  In last 3 years |  All
    Please wait a minute...
    For Selected: Toggle Thumbnails
    Vegetable Crop Growth Modeling in Digital Twin Platform Based on Large Language Model Inference
    ZHAO Chunjiang, LI Jingchen, WU Huarui, YANG Yusen
    Smart Agriculture    2024, 6 (6): 63-71.   DOI: 10.12133/j.smartag.SA202410008
    Abstract4381)   HTML267)    PDF(pc) (1460KB)(1842)       Save

    [Objective] In the era of digital agriculture, real-time monitoring and predictive modeling of crop growth are paramount, especially in autonomous farming systems. Traditional crop growth models, often constrained by their reliance on static, rule-based methods, fail to capture the dynamic and multifactorial nature of vegetable crop growth. This research tried to address these challenges by leveraging the advanced reasoning capabilities of pre-trained large language models (LLMs) to simulate and predict vegetable crop growth with accuracy and reliability. Modeling the growth of vegetable crops within these platforms has historically been hindered by the complex interactions among biotic and abiotic factors. [Methods] The methodology was structured in several distinct phases. Initially, a comprehensive dataset was curated to include extensive information on vegetable crop growth cycles, environmental conditions, and management practices. This dataset incorporates continuous data streams such as soil moisture, nutrient levels, climate variables, pest occurrence, and historical growth records. By combining these data sources, the study ensured that the model was well-equipped to understand and infer the complex interdependencies inherent in crop growth processes. Then, advanced techniques was emploied for pre-training and fine-tuning LLMs to adapt them to the domain-specific requirements of vegetable crop modeling. A staged intelligent agent ensemble was designed to work within the digital twin platform, consisting of a central managerial agent and multiple stage-specific agents. The managerial agent was responsible for identifying transitions between distinct growth stages of the crops, while the stage-specific agents were tailored to handle the unique characteristics of each growth phase. This modular architecture enhanced the model's adaptability and precision, ensuring that each phase of growth received specialized attention and analysis. [Results and Discussions] The experimental validation of this method was conducted in a controlled agricultural setting at the Xiaotangshan Modern Agricultural Demonstration Park in Beijing. Cabbage (Zhonggan 21) was selected as the test crop due to its significance in agricultural production and the availability of comprehensive historical growth data. Over five years, the dataset collected included 4 300 detailed records, documenting parameters such as plant height, leaf count, soil conditions, irrigation schedules, fertilization practices, and pest management interventions. This dataset was used to train the LLM-based system and evaluate its performance using ten-fold cross-validation. The results of the experiments demonstrating the efficacy of the proposed system in addressing the complexities of vegetable crop growth modeling. The LLM-based model achieved 98% accuracy in predicting crop growth degrees and a 99.7% accuracy in identifying growth stages. These metrics significantly outperform traditional machine learning approaches, including long short-term memory (LSTM), XGBoost, and LightGBM models. The superior performance of the LLM-based system highlights its ability to reason over heterogeneous data inputs and make precise predictions, setting a new benchmark for crop modeling technologies. Beyond accuracy, the LLM-powered system also excels in its ability to simulate growth trajectories over extended periods, enabling farmers and agricultural managers to anticipate potential challenges and make proactive decisions. For example, by integrating real-time sensor data with historical patterns, the system can predict how changes in irrigation or fertilization practices will impact crop health and yield. This predictive capability is invaluable for optimizing resource allocation and mitigating risks associated with climate variability and pest outbreaks. [Conclusions] The study emphasizes the importance of high-quality data in achieving reliable and generalizable models. The comprehensive dataset used in this research not only captures the nuances of cabbage growth but also provides a blueprint for extending the model to other crops. In conclusion, this research demonstrates the transformative potential of combining large language models with digital twin technology for vegetable crop growth modeling. By addressing the limitations of traditional modeling approaches and harnessing the advanced reasoning capabilities of LLMs, the proposed system sets a new standard for precision agriculture. Several avenues also are proposed for future work, including expanding the dataset, refining the model architecture, and developing multi-crop and multi-region capabilities.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Research Status and Prospects of Key Technologies for Rice Smart Unmanned Farms
    YU Fenghua, XU Tongyu, GUO Zhonghui, BAI Juchi, XIANG Shuang, GUO Sien, JIN Zhongyu, LI Shilong, WANG Shikuan, LIU Meihan, HUI Yinxuan
    Smart Agriculture    2024, 6 (6): 1-22.   DOI: 10.12133/j.smartag.SA202410018
    Abstract4282)   HTML245)    PDF(pc) (3047KB)(2891)       Save

    [Significance] Rice smart unmanned farm is the core component of smart agriculture, and it is a key path to realize the modernization of rice production and promote the high-quality development of agriculture. Leveraging advanced information technologies such as the Internet of Things (IoT) and artificial intelligence (AI), these farms enable deep integration of data-driven decision making and intelligent machines. This integration creates an unmanned production system that covers the entire process from planting and managing rice crops to harvesting, greatly improving the efficiency and precision of rice cultivation. [Progress] This paper systematically sorted out the key technologies of rice smart unmanned farms in the three main links of pre-production, production and post-production, and the key technologies of pre-production mainly include the construction of high-standard farmland, unmanned nursery, land leveling, and soil nutrient testing. The construction of high-standard farmland is the foundation of the physical environment of the smart unmanned farms of rice, which provides perfect operating environment for the operation of modernized smart farm machinery through the reasonable layout of the field roads, good drainage and irrigation systems, and the scientific planting structure. Agricultural machine operation provides a perfect operating environment. The technical level of unmanned nursery directly determines the quality of rice cultivation and harvesting in the later stage, and a variety of rice seeding machines and nursery plate setting machines have been put into use. Land leveling technology can improve the growing environment of rice and increase the land utilization rate, and the current land leveling technology through digital sensing and path planning technology, which improves the operational efficiency and reduces the production cost at the same time. Soil nutrient detection technology is mainly detected by electrochemical analysis and spectral analysis, but both methods have their advantages and disadvantages, how to integrate the two methods to achieve an all-round detection of soil nutrient content is the main direction of future research. The key technologies in production mainly include rice dry direct seeding, automated transplanting, precise variable fertilization, intelligent irrigation, field weed management, and disease diagnosis. Among them, the rice dry direct seeding technology requires the planter to have high precision and stability to ensure reasonable seeding depth and density. Automated rice transplanting technology mainly includes three ways: root washing seedling machine transplanting, blanket seedling machine transplanting, and potting blanket seedling machine transplanting; at present, the incidence of problems in the automated transplanting process should be further reduced, and the quality and efficiency of rice machine transplanting should be improved. Precision variable fertilization technology is mainly composed of three key technologies: information perception, prescription decision-making and precise operation, but there are still fewer cases of unmanned farms combining the three technologies, and in the future, the main research should be on the method of constructing the whole process operation system of variable fertilization. The smart irrigation system is based on the water demand of the whole life cycle of rice to realize adaptive irrigation control, and the current smart irrigation technology can automatically adjust the irrigation strategy through real-time monitoring of soil, climate and crop growth conditions to further improve irrigation efficiency and agricultural production benefits. The field weed management and disease diagnosis technology mainly recognizes rice weeds as well as diseases through deep learning and other methods, and combines them with precision application technology for prevention and intervention. Post-production key technologies mainly include rice yield estimation, unmanned harvesting, rice storage and processing quality testing. Rice yield estimation technology is mainly used to predict yield by combining multi-source data and algorithms, but there are still problems such as the difficulty of integrating multi-source data, which requires further research. In terms of unmanned aircraft harvesting technology, China's rice combine harvester market has tended to stabilize, and the safety of the harvester's autopilot should be further improved in the future. Rice storage and processing quality detection technology mainly utilizes spectral technology and machine vision technology to detect spectra and images, and future research can combine deep learning and multimodal fusion technology to improve the machine vision system's ability and adaptability to recognize the appearance characteristics of rice. [Conclusions and Prospects] This paper reviews the researches of the construction of intelligent unmanned rice farms at home and abroad in recent years, summarizes the main difficulties faced by the key technologies of unmanned farms in practical applications, analyzes the challenges encountered in the construction of smart unmanned farms, summarizes the roles and responsibilities of the government, enterprises, scientific research institutions, cooperatives and other subjects in promoting the construction of intelligent unmanned rice farms, and puts forward relevant suggestions. It provides certain support and development ideas for the construction of intelligent unmanned rice farms in China.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Key Technologies and Prospects of Laser Weeding Robots
    YU Zhongyi, WANG Hongyu, HE Xiongkui, ZHAO Lei, WANG Yuanyuan, SUN Hai
    Smart Agriculture    2025, 7 (2): 132-145.   DOI: 10.12133/j.smartag.SA202410031
    Abstract3993)   HTML105)    PDF(pc) (6774KB)(1294)       Save

    [Significance] Grass damage in farmland seriously restricts the quality and yield of crop planting and production, and promotes the occurrence of pests and diseases. Weed control is a necessary measure for high yield and high quality of crops. Currently, there are five main weed control methods: Manual, biological, thermal, mechanical, and chemical weed control. Traditional chemical weed control methods are gradually limited due to soil pollution and ecological balance disruption. Intelligent laser weeding technology, with the characteristics of environmental protection, high efficiency, flexibility, and automation, as an emerging and promising ecological and environmental protection new object control method for field weeds, has become the core direction to replace chemical weeding in recent years. The laser weeding robot is the carrier of laser weeding technology, an important manifestation of the development of modern agriculture towards intelligence and precision, and has great application and promotion value. [Progress] Laser weeding is currently a research hotspot to develop and study key technologies and equipment for smart agriculture, and has achieved a series of significant results, greatly promoting the promotion and application of intelligent laser weeding robots in the field. Laser weed control technology achieves precise weed control through thermal, photochemical, and photodynamic effects. In this article, the research background of laser weeding was introduced, its key technologies, operation system and equipment were discussed in details, covering aspects such as operating principles, system architecture, seedling, weed recognition and localization, robot navigation and path planning, as well as actuator control technologies. Then, based on the current research status of laser weeding robots, the existing problems and development trends of intelligent laser weeding robots were prospected. [Conclusion and Prospect] Based on the different field grass conditions in different regions, a large number of indoor and outdoor experiments on laser weed control should be carried out in the future to further verify the technical effectiveness and feasibility of laser field weed control, providing support for the research and application of laser weed control equipment technology. Despite facing challenges such as high costs and poor environmental adaptability, with the integration of technologies such as artificial intelligence and the Internet of Things, as well as policy support, laser weeding is expected to become an important support for sustainable agricultural development.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    CSD-YOLOv8s: Dense Sheep Small Target Detection Model Based on UAV Images
    WENG Zhi, LIU Haixin, ZHENG Zhiqiang
    Smart Agriculture    2024, 6 (4): 42-52.   DOI: 10.12133/j.smartag.SA202401004
    Abstract3832)   HTML143)    PDF(pc) (1772KB)(1457)       Save

    [Objective] The monitoring of livestock grazing in natural pastures is a key aspect of the transformation and upgrading of large-scale breeding farms. In order to meet the demand for large-scale farms to achieve accurate real-time detection of a large number of sheep, a high-precision and easy-to-deploy small-target detection model: CSD-YOLOv8s was proposed to realize the real-time detection of small-targeted individual sheep under the high-altitude view of the unmanned aerial vehicle (UAV). [Methods] Firstly, a UAV was used to acquire video data of sheep in natural grassland pastures with different backgrounds and lighting conditions, and together with some public datasets downloaded formed the original image data. The sheep detection dataset was generated through data cleaning and labeling. Secondly, in order to solve the difficult problem of sheep detection caused by dense flocks and mutual occlusion, the SPPFCSPC module was constructed with cross-stage local connection based on the you only look once (YOLO)v8 model, which combined the original features with the output features of the fast spatial pyramid pooling network, fully retained the feature information at different stages of the model, and effectively solved the problem of small targets and serious occlusion of the sheep, and improved the detection performance of the model for small sheep targets. In the Neck part of the model, the convolutional block attention module (CBAM) convolutional attention module was introduced to enhance the feature information capture based on both spatial and channel aspects, suppressing the background information spatially and focusing on the sheep target in the channel, enhancing the network's anti-jamming ability from both channel and spatial dimensions, and improving the model's detection performance of multi-scale sheep under complex backgrounds and different illumination conditions. Finally, in order to improve the real-time and deploy ability of the model, the standard convolution of the Neck network was changed to a lightweight convolutional C2f_DS module with a changeable kernel, which was able to adaptively select the corresponding convolutional kernel for feature extraction according to the input features, and solved the problem of input scale change in the process of sheep detection in a more flexible way, and at the same time, the number of parameters of the model was reduced and the speed of the model was improved. [Results and Discussions] The improved CSD-YOLOv8s model exhibited excellent performance in the sheep detection task. Compared with YOLO, Faster R-CNN and other classical network models, the improved CSD-YOLOv8s model had higher detection accuracy and frames per second (FPS) of 87 f/s in the flock detection task with comparable detection speed and model size. Compared with the YOLOv8s model, Precision was improved from 93.0% to 95.2%, mAP was improved from 91.2% to 93.1%, and it had strong robustness to sheep targets with different degree of occlusion and different scales, which effectively solved the serious problems of missed and misdetection of sheep in the grassland pasture UAV-on-ground sheep detection task due to the small sheep targets, large background noise, and high degree of densification. misdetection serious problems. Validated by the PASCAL VOC 2007 open dataset, the CSD-YOLOv8s model proposed in this study improved the detection accuracy of 20 different objects, including transportation vehicles, animals, etc., especially in sheep detection, the detection accuracy was improved by 9.7%. [Conclusions] This study establishes a sheep dataset based on drone images and proposes a model called CSD-YOLOv8s for detecting grazing sheep in natural grasslands. The model addresses the serious issues of missed detections and false alarms in sheep detection under complex backgrounds and lighting conditions, enabling more accurate detection of grazing livestock in drone images. It achieves precise detection of targets with varying degrees of clustering and occlusion and possesses good real-time performance. This model provides an effective detection method for detecting sheep herds from the perspective of drones in natural pastures and offers technical support for large-scale livestock detection in breeding farms, with wide-ranging potential applications.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Artificial Intelligence-Driven High-Quality Development of New-Quality Productivity in Animal Husbandry: Restraining Factors, Generation Logic and Promotion Paths
    LIU Jifang, ZHOU Xiangyang, LI Min, HAN Shuqing, GUO Leifeng, CHI Liang, YANG Lu, WU Jianzhai
    Smart Agriculture    2025, 7 (1): 165-177.   DOI: 10.12133/j.smartag.SA202407010
    Abstract3828)   HTML95)    PDF(pc) (1692KB)(898)       Save

    [Significance] Developing new-quality productivity is of great significance for promoting high-quality development of animal husbandry. However, there is currently limited research on new-quality productivity in animal husbandry, and there is a lack of in-depth analysis on its connotation, characteristics, constraints, and promotion path. [Progress] This article conducts a systematic study on the high-quality development of animal husbandry productivity driven by artificial intelligence. The new-quality productivity of animal husbandry is led by cutting-edge technological innovations such as biotechnology, information technology, and green technology, with digitalization, greening, and ecologicalization as the direction of industrial upgrading. Its basic connotation is manifested as higher quality workers, more advanced labor materials, and a wider range of labor objects. Compared with traditional productivity, the new-quality productivity of animal husbandry is an advanced productivity guided by technological innovation, new development concepts, and centered on the improvement of total factor productivity. It has significant characteristics of high production efficiency, good industrial benefits, and strong sustainable development capabilities. China's new-quality productivity in animal husbandry has a good foundation for development, but it also faces constraints such as insufficient innovation in animal husbandry breeding technology, weak core competitiveness, low mechanization rate of animal husbandry, weak independent research and development capabilities of intelligent equipment, urgent demand for "machine replacement", shortcomings in the quantity and quality of animal husbandry talents, low degree of scale of animal husbandry, and limited level of intelligent management. Artificial intelligence in animal husbandry can be widely used in environmental control, precision feeding, health monitoring and disease prevention and control, supply chain optimization and other fields. Artificial intelligence, through revolutionary breakthroughs in animal husbandry technology represented by digital technology, innovative allocation of productivity factors in animal husbandry linked by data elements, and innovative allocation of productivity factors in animal husbandry adapted to the digital economy, has given birth to new-quality productivity in animal husbandry and empowered the high-quality development of animal husbandry. [Conclusions and Prospects] This article proposes a path to promote the development of new-quality productivity in animal husbandry by improving the institutional mechanism of artificial intelligence to promote the development of modern animal husbandry industry, strengthening the application of artificial intelligence in animal husbandry technology innovation and promotion, and improving the management level of artificial intelligence in the entire industry chain of animal husbandry.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    The Path of Smart Agricultural Technology Innovation Leading Development of Agricultural New Quality Productivity
    CAO Bingxue, LI Hongfei, ZHAO Chunjiang, LI Jin
    Smart Agriculture    2024, 6 (4): 116-127.   DOI: 10.12133/j.smartag.SA202405004
    Abstract3721)   HTML274)    PDF(pc) (1102KB)(2688)       Save

    [Significance] Building the agricultural new quality productivity is of great significance. It is the advanced quality productivity which realizes the transformation, upgrading, and deep integration of substantive, penetrating, operational, and media factors, and has outstanding characteristics such as intelligence, greenness, integration, and organization. As a new technology revolution in the field of agriculture, smart agricultural technology transforms agricultural production mode by integrating agricultural biotechnology, agricultural information technology, and smart agricultural machinery and equipment, with information and knowledge as important core elements. The inherent characteristics of "high-tech, high-efficiency, high-quality, and sustainable" in agricultural new quality productivity are fully reflected in the practice of smart agricultural technology innovation. And it has become an important core and engine for promoting the agricultural new quality productivity. [Progress] Through literature review and theoretical analysis, this article conducts a systematic study on the practical foundation, internal logic, and problem challenges of smart agricultural technology innovation leading the development of agricultural new quality productivity. The conclusions show that: (1) At present, the global innovation capability of smart agriculture technology is constantly enhancing, and significant technology breakthroughs have been made in fields such as smart breeding, agricultural information perception, agricultural big data and artificial intelligence, smart agricultural machinery and equipment, providing practical foundation support for leading the development of agricultural new quality productivity. Among them, the smart breeding of 'Phenotype+Genotype+Environmental type' has entered the fast lane, the technology system for sensing agricultural sky, air, and land information is gradually maturing, the research and exploration on agricultural big data and intelligent decision-making technology continue to advance, and the creation of smart agricultural machinery and equipment for different fields has achieved fruitful results; (2) Smart agricultural technology innovation provides basic resources for the development of agricultural new quality productivity through empowering agricultural factor innovation, provides sustainable driving force for the development of agricultural new quality productivity through empowering agricultural technology innovation, provides practical paradigms for the development of agricultural new quality productivity through empowering agricultural scenario innovation, provides intellectual support for the development of agricultural new quality productivity through empowering agricultural entity innovation, and provides important guidelines for the development of agricultural new quality productivity through empowering agricultural value innovation; (3) Compared to the development requirements of agricultural new quality productivity in China and the advanced level of international smart agriculture technology, China's smart agriculture technology innovation is generally in the initial stage of multi-point breakthroughs, system integration, and commercial application. It still faces major challenges such as an incomplete policy system for technology innovation, key technologies with bottlenecks, blockages and breakpoints, difficulties in the transformation and implementation of technology achievements, and incomplete support systems for technology innovation. [Conclusions and Prospects] Regarding the issue of technology innovation in smart agriculture, this article proposes the 'Four Highs' path of smart agriculture technology innovation to fill the gaps in smart agriculture technology innovation and accelerate the formation of agricultural new quality productivity in China. The "Four Highs" path specifically includes the construction of high-energy smart agricultural technology innovation platforms, the breakthroughs in high-precision and cutting-edge smart agricultural technology products, the creation of high-level smart agricultural application scenarios, and the cultivation of high-level smart agricultural innovation talents. Finally, this article proposes four strategic suggestions such as deepening the understanding of smart agriculture technology innovation and agricultural new quality productivity, optimizing the supply of smart agriculture technology innovation policies, building a national smart agriculture innovation development pilot zone, and improving the smart agriculture technology innovation ecosystem.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Orchard-Wide Visual Perception and Autonomous Operation of Fruit Picking Robots: A Review
    CHEN Mingyou, LUO Lufeng, LIU Wei, WEI Huiling, WANG Jinhai, LU Qinghua, LUO Shaoming
    Smart Agriculture    2024, 6 (5): 20-39.   DOI: 10.12133/j.smartag.SA202405022
    Abstract3706)   HTML299)    PDF(pc) (4030KB)(6884)       Save

    [Significance] Fruit-picking robot stands as a crucial solution for achieving intelligent fruit harvesting. Significant progress has been made in developing foundational methods for picking robots, such as fruit recognition, orchard navigation, path planning for picking, and robotic arm control, the practical implementation of a seamless picking system that integrates sensing, movement, and picking capabilities still encounters substantial technical hurdles. In contrast to current picking systems, the next generation of fruit-picking robots aims to replicate the autonomous skills exhibited by human fruit pickers. This involves effectively performing ongoing tasks of perception, movement, and picking without human intervention. To tackle this challenge, this review delves into the latest research methodologies and real-world applications in this field, critically assesses the strengths and limitations of existing methods and categorizes the essential components of continuous operation into three sub-modules: local target recognition, global mapping, and operation planning. [Progress] Initially, the review explores methods for recognizing nearby fruit and obstacle targets. These methods encompass four main approaches: low-level feature fusion, high-level feature learning, RGB-D information fusion, and multi-view information fusion, respectively. Each of these approaches incorporates advanced algorithms and sensor technologies for cluttered orchard environments. For example, low-level feature fusion utilizes basic attributes such as color, shapes and texture to distinguish fruits from backgrounds, while high-level feature learning employs more complex models like convolutional neural networks to interpret the contextual relationships within the data. RGB-D information fusion brings depth perception into the mix, allowing robots to gauge the distance to each fruit accurately. Multi-view information fusion tackles the issue of occlusions by combining data from multiple cameras and sensors around the robot, providing a more comprehensive view of the environment and enabling more reliable sensing. Subsequently, the review shifts focus to orchard mapping and scene comprehension on a broader scale. It points out that current mapping methods, while effective, still struggle with dynamic changes in the orchard, such as variations of fruits and light conditions. Improved adaptation techniques, possibly through machine learning models that can learn and adjust to different environmental conditions, are suggested as a way forward. Building upon the foundation of local and global perception, the review investigates strategies for planning and controlling autonomous behaviors. This includes not only the latest advancements in devising movement paths for robot mobility but also adaptive strategies that allow robots to react to unexpected obstacles or changes within the whole environment. Enhanced strategies for effective fruit picking using the Eye-in-Hand system involve the development of more dexterous robotic hands and improved algorithms for precisely predicting the optimal picking point of each fruit. The review also identifies a crucial need for further advancements in the dynamic behavior and autonomy of these technologies, emphasizing the importance of continuous learning and adaptive control systems to improve operational efficiency in diverse orchard environments. [Conclusions and Prospects] The review underscores the critical importance of coordinating perception, movement, and picking modules to facilitate the transition from a basic functional prototype to a practical machine. Moreover, it emphasizes the necessity of enhancing the robustness and stability of core algorithms governing perception, planning, and control, while ensuring their seamless coordination which is a central challenge that emerges. Additionally, the review raises unresolved questions regarding the application of picking robots and outlines future trends, include deeper integration of stereo vision and deep learning, enhanced global vision sampling, and the establishment of standardized evaluation criteria for overall operational performance. The paper can provide references for the eventual development of robust, autonomous, and commercially viable picking robots in the future.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Smart Supply Chains for Agricultural Products: Key Technologies, Research Progress and Future Direction
    HAN Jiawei, YANG Xinting
    Smart Agriculture    2025, 7 (3): 1-16.   DOI: 10.12133/j.smartag.SA202501006
    Abstract3619)   HTML179)    PDF(pc) (1373KB)(1199)       Save

    [Significance] The smart transformation of agricultural product supply chains is an essential solution to the challenges faced by traditional supply chains, such as information asymmetry, high logistics costs, and difficulties in quality traceability. This transformation also serves as a vital pathway to modernize agriculture and enhance industrial competitiveness. By integrating technologies such as the Internet of Things (IoT), big data, and artificial intelligence (AI), smart supply chains facilitate precise production and processing, efficient logistics distribution, and transparent quality supervision. As a result, they improve circulation efficiency, ensure product safety, increase farmers' incomes, and promote sustainable agricultural development. Furthermore, in light of global shifts in agricultural trade, this transformation bolsters the international competitiveness of China's agricultural products and propels the agricultural industrial chain toward higher value-added segments. This paper systematically examines the conceptual framework, technological applications, and future trends of smart supply chains, aiming to provide a theoretical foundation for industry practices and insights for policymaking and technological innovation. [Progress] In the production phase, IoT and remote sensing technologies enable real-time monitoring of crop growth conditions, including soil moisture, temperature, and pest infestation, facilitating precision irrigation, fertilization, and pest management. Big data analysis, coupled with AI algorithms, helps in predicting crop yields, optimizing resource allocation, and minimizing waste. Additionally, AI-driven smart pest control systems can dynamically adjust pesticide application, reducing chemical usage and environmental impact. The processing stage leverages advanced technologies for efficient sorting, grading, cleaning, and packaging. Computer vision and hyperspectral imaging technologies enhance the sorting efficiency and quality inspection of agricultural products, ensuring only high-quality products proceed to the next stage. Novel cleaning techniques, such as ultrasonic and nanobubble cleaning, effectively remove surface contaminants and reduce microbial loads without compromising product quality. Moreover, AI-integrated systems optimize processing lines, reduce downtime and enhance overall throughput. Warehousing employs IoT sensors to monitor environmental conditions like temperature, humidity, and gas concentrations, ensure optimal storage conditions for diverse agricultural products. AI algorithms predict inventory demand, optimize stock levels to minimize waste and maximize freshness. Robotics and automation in warehouses improve picking, packing, and palletizing efficiency, reduce labor costs and enhance accuracy. The transportation sector focuses on cold chain innovations to maintain product quality during transit. IoT-enabled temperature-controlled containers and AI-driven scheduling systems ensure timely and efficient delivery. Additionally, the integration of blockchain technology provides immutable records of product handling and conditions, enhances transparency and trust. The adoption of new energy vehicles, such as electric and hydrogen-powered trucks, further reduces carbon footprints and operating costs. In the distribution and sales stages, big data analytics optimize delivery routes, reducing transportation time and costs. AI-powered demand forecasting enables precise inventory management, minimizes stockouts and excess inventories. Moreover, AI and machine learning algorithms personalize marketing efforts, improve customer engagement and satisfaction. Blockchain technology ensures product authenticity and traceability, enhances consumer trust. [Conclusions and Prospects] As technological advancements and societal demands continue to evolve, the smart transformation of agricultural product supply chains has become increasingly urgent. Future development should prioritize unmanned operations to alleviate labor shortages and enhance product quality and safety. Establishing information-sharing platforms and implementing refined management practices are crucial for optimizing resource allocation, improving operational efficiency, and enhancing international competitiveness. Additionally, aligning with the "dual-carbon" strategy by promoting clean energy adoption, optimizing transportation methods, and advocating for sustainable packaging will drive the supply chain toward greater sustainability. However, the application of emerging technologies in agricultural supply chains faces challenges such as data governance, technical adaptability, and standardization. Addressing these issues requires policy guidance, technological innovation, and cross-disciplinary collaboration. By overcoming these challenges, the comprehensive intelligent upgrade of agricultural product supply chains can be achieved, ultimately contribute to the modernization and sustainable development of the agricultural sector.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Research Progress on Remote Sensing Monitoring and Intelligent Decision-Making Algorithms for Rice Production
    ZHAO Bingting, HUA Chuanhai, YE Chenyang, XIONG Yuchun, QIAN Tao, CHENG Tao, YAO Xia, ZHENG Hengbiao, ZHU Yan, CAO Weixing, JIANG Chongya
    Smart Agriculture    2025, 7 (2): 57-72.   DOI: 10.12133/j.smartag.SA202501002
    Abstract3615)   HTML73)    PDF(pc) (1365KB)(540)       Save

    [Significance] Rice is a staple food crop worldwide, and ccurate monitoring of its growth is crucial for global food security. Remote sensing serves as a powerful tool in modern agriculture. By integrating remote sensing with intelligent decision-making algorithms, farmers can achieve more precise and sustainable rice cultivation. To provide actionable insights and guidance for researchers in this field, this review examines the latest advancements in remote sensing and smart algorithms for rice farming, while addressing current challenges and future trends. [Progress] Currently, remote sensing-based monitoring systems for rice production have been comprehensively implemented across the entire production cycle. For planting distribution identification, optical remote sensing and synthetic aperture radar (SAR) technologies complement each other to enhance accuracy through data fusion. Regarding growth period monitoring, a robust technical framework has been established, incorporating the empirical threshold method, shape model approach, and machine learning classification techniques. Dynamic evaluation of growth status is enabled by constructing correlation models between remote sensing features and biophysical parameters. Disaster monitoring systems provide rapid responses to various natural disasters. Yield and quality predictions integrate crop models, remote sensing data, and machine learning algorithms. Intelligent decision-making algorithms are deeply embedded in all stages of rice production. For instance, during planting planning, the integration of geographic information systems (GIS) and multi-criteria evaluation methods facilitates regional suitability assessments and farm-level quantitative designs. In topdressing management, nitrogen-based intelligent algorithms have significantly improved fertilization precision. Irrigation optimization achieves water conservation and emission reduction by synthesizing soil moisture and meteorological data. Finally, precise pesticide application prescriptions are generated using remote sensing and unmanned aerial vehicle (UAV) technologies. [Conclusions and Prospects] Despite significant progress, current research faces persistent challenges, including difficulties in multi-source data fusion, complexities in acquiring prior knowledge, insufficient model standardization, and barriers to large-scale technology implementation. Future efforts should prioritize the following six directions: (1) Technological innovation: Advance collaborative analysis of multi-source remote sensing data, design optimized data fusion algorithms, and construct an integrated air-space-ground monitoring network; (2) Intelligent algorithms: Explore cutting-edge techniques such as generative adversarial networks (GANs) and federated learning to enhance model adaptability across diverse environments; (3) Research scale: Establish a global rice growth monitoring system and develop multi-factor coupling models to assess climate change impacts; (4) Technology dissemination: Strengthen demonstration projects, reduce equipment costs, and cultivate interdisciplinary professionals; (5) Standards and protocols: Promote internationally unified standards for monitoring and decision - making frameworks; (6) System integration: Leverage technologies such as digital twins and blockchain to develop smart agriculture platforms for end-to-end intelligent management. Through multi-dimensional innovation, these advancements will significantly elevate the intelligence of rice production, offering robust support for global food security and sustainable agricultural development.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Research Progress and Prospects of Key Navigation Technologies for Facility Agricultural Robots
    HE Yong, HUANG Zhenyu, YANG Ningyuan, LI Xiyao, WANG Yuwei, FENG Xuping
    Smart Agriculture    2024, 6 (5): 1-19.   DOI: 10.12133/j.smartag.SA202404006
    Abstract3597)   HTML392)    PDF(pc) (2130KB)(8058)       Save

    [Significance] With the rapid development of robotics technology and the persistently rise of labor costs, the application of robots in facility agriculture is becoming increasingly widespread. These robots can enhance operational efficiency, reduce labor costs, and minimize human errors. However, the complexity and diversity of facility environments, including varying crop layouts and lighting conditions, impose higher demands on robot navigation. Therefore, achieving stable, accurate, and rapid navigation for robots has become a key issue. Advanced sensor technologies and algorithms have been proposed to enhance robots' adaptability and decision-making capabilities in dynamic environments. This not only elevates the automation level of agricultural production but also contributes to more intelligent agricultural management. [Progress] This paper reviews the key technologies of automatic navigation for facility agricultural robots. It details beacon localization, inertial positioning, simultaneous localization and mapping (SLAM) techniques, and sensor fusion methods used in autonomous localization and mapping. Depending on the type of sensors employed, SLAM technology could be subdivided into vision-based, laser-based and fusion systems. Fusion localization is further categorized into data-level, feature-level, and decision-level based on the types and stages of the fused information. The application of SLAM technology and fusion localization in facility agriculture has been increasingly common. Global path planning plays a crucial role in enhancing the operational efficiency and safety of facility aricultural robots. This paper discusses global path planning, classifying it into point-to-point local path planning and global traversal path planning. Furthermore, based on the number of optimization objectives, it was divided into single-objective path planning and multi-objective path planning. In regard to automatic obstacle avoidance technology for robots, the paper discusses sevelral commonly used obstacle avoidance control algorithms commonly used in facility agriculture, including artificial potential field, dynamic window approach and deep learning method. Among them, deep learning methods are often employed for perception and decision-making in obstacle avoidance scenarios. [Conclusions and Prospects] Currently, the challenges for facility agricultural robot navigation include complex scenarios with significant occlusions, cost constraints, low operational efficiency and the lack of standardized platforms and public datasets. These issues not only affect the practical application effectiveness of robots but also constrain the further advancement of the industry. To address these challenges, future research can focus on developing multi-sensor fusion technologies, applying and optimizing advanced algorithms, investigating and implementing multi-robot collaborative operations and establishing standardized and shared data platforms.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    A Regional Farming Pig Counting System Based on Improved Instance Segmentation Algorithm
    ZHANG Yanqi, ZHOU Shuo, ZHANG Ning, CHAI Xiujuan, SUN Tan
    Smart Agriculture    2024, 6 (4): 53-63.   DOI: 10.12133/j.smartag.SA202310001
    Abstract3584)   HTML96)    PDF(pc) (2077KB)(784)       Save

    [Objective] Currently, pig farming facilities mainly rely on manual counting for tracking slaughtered and stored pigs. This is not only time-consuming and labor-intensive, but also prone to counting errors due to pig movement and potential cheating. As breeding operations expand, the periodic live asset inventories put significant strain on human, material and financial resources. Although methods based on electronic ear tags can assist in pig counting, these ear tags are easy to break and fall off in group housing environments. Most of the existing methods for counting pigs based on computer vision require capturing images from a top-down perspective, necessitating the installation of cameras above each hogpen or even the use of drones, resulting in high installation and maintenance costs. To address the above challenges faced in the group pig counting task, a high-efficiency and low-cost pig counting method was proposed based on improved instance segmentation algorithm and WeChat public platform. [Methods] Firstly, a smartphone was used to collect pig image data in the area from a human view perspective, and each pig's outline in the image was annotated to establish a pig count dataset. The training set contains 606 images and the test set contains 65 images. Secondly, an efficient global attention module was proposed by improving convolutional block attention module (CBAM). The efficient global attention module first performed a dimension permutation operation on the input feature map to obtain the interaction between its channels and spatial dimensions. The permuted features were aggregated using global average pooling (GAP). One-dimensional convolution replaced the fully connected operation in CBAM, eliminating dimensionality reduction and significantly reducing the model's parameter number. This module was integrated into the YOLOv8 single-stage instance segmentation network to build the pig counting model YOLOv8x-Ours. By adding an efficient global attention module into each C2f layer of the YOLOv8 backbone network, the dimensional dependencies and feature information in the image could be extracted more effectively, thereby achieving high-accuracy pig counting. Lastly, with a focus on user experience and outreach, a pig counting WeChat mini program was developed based on the WeChat public platform and Django Web framework. The counting model was deployed to count pigs using images captured by smartphones. [Results and Discussions] Compared with existing methods of Mask R-CNN, YOLACT(Real-time Instance Segmentation), PolarMask, SOLO and YOLOv5x, the proposed pig counting model YOLOv8x-Ours exhibited superior performance in terms of accuracy and stability. Notably, YOLOv8x-Ours achieved the highest accuracy in counting, with errors of less than 2 and 3 pigs on the test set. Specifically, 93.8% of the total test images had counting errors of less than 3 pigs. Compared with the two-stage instance segmentation algorithm Mask R-CNN and the YOLOv8x model that applies the CBAM attention mechanism, YOLOv8x-Ours showed performance improvements of 7.6% and 3%, respectively. And due to the single-stage design and anchor-free architecture of the YOLOv8 model, the processing speed of a single image was only 64 ms, 1/8 of Mask R-CNN. By embedding the model into the WeChat mini program platform, pig counting was conducted using smartphone images. In cases where the model incorrectly detected pigs, users were given the option to click on the erroneous location in the result image to adjust the statistical outcomes, thereby enhancing the accuracy of pig counting. [Conclusions] The feasibility of deep learning technology in the task of pig counting was demonstrated. The proposed method eliminates the need for installing hardware equipment in the breeding area of the pig farm, enabling pig counting to be carried out effortlessly using just a smartphone. Users can promptly spot any errors in the counting results through image segmentation visualization and easily rectify any inaccuracies. This collaborative human-machine model not only reduces the need for extensive manpower but also guarantees the precision and user-friendliness of the counting outcomes.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Automatic Measurement Method of Beef Cattle Body Size Based on Multimodal Image Information and Improved Instance Segmentation Network
    WENG Zhi, FAN Qi, ZHENG Zhiqiang
    Smart Agriculture    2024, 6 (4): 64-75.   DOI: 10.12133/j.smartag.SA202310007
    Abstract3545)   HTML82)    PDF(pc) (3345KB)(1928)       Save

    [Objective] The body size parameter of cattle is a key indicator reflecting the physical development of cattle, and is also a key factor in the cattle selection and breeding process. In order to solve the demand of measuring body size of beef cattle in the complex environment of large-scale beef cattle ranch, an image acquisition device and an automatic measurement algorithm of body size were designed. [Methods] Firstly, the walking channel of the beef cattle was established, and when the beef cattle entered the restraining device through the channel, the RGB and depth maps of the image on the right side of the beef cattle were acquired using the Inter RealSense D455 camera. Secondly, in order to avoid the influence of the complex environmental background, an improved instance segmentation network based on Mask2former was proposed, adding CBAM module and CA module, respectively, to improve the model's ability to extract key features from different perspectives, extracting the foreground contour from the 2D image of the cattle, partitioning the contour, and comparing it with other segmentation algorithms, and using curvature calculation and other mathematical methods to find the required body size measurement points. Thirdly, in the processing of 3D data, in order to solve the problem that the pixel point to be measured in the 2D RGB image was null when it was projected to the corresponding pixel coordinates in the depth-valued image, resulting in the inability to calculate the 3D coordinates of the point, a series of processing was performed on the point cloud data, and a suitable point cloud filtering and point cloud segmentation algorithm was selected to effectively retain the point cloud data of the region of the cattle's body to be measured, and then the depth map was 16. Then the depth map was filled with nulls in the field to retain the integrity of the point cloud in the cattle body region, so that the required measurement points could be found and the 2D data could be returned. Finally, an extraction algorithm was designed to combine 2D and 3D data to project the extracted 2D pixel points into a 3D point cloud, and the camera parameters were used to calculate the world coordinates of the projected points, thus automatically calculating the body measurements of the beef cattle. [Results and Discussions] Firstly, in the part of instance segmentation, compared with the classical Mask R-CNN and the recent instance segmentation networks PointRend and Queryinst, the improved network could extract higher precision and smoother foreground images of cattles in terms of segmentation accuracy and segmentation effect, no matter it was for the case of occlusion or for the case of multiple cattles. Secondly, in three-dimensional data processing, the method proposed in the study could effectively extract the three-dimensional data of the target area. Thirdly, the measurement error of body size was analysed, among the four body size measurement parameters, the smallest average relative error was the height of the cross section, which was due to the more prominent position of the cross section, and the different standing positions of the cattle have less influence on the position of the cross section, and the largest average relative error was the pipe circumference, which was due to the influence of the greater overlap of the two front legs, and the higher requirements for the standing position. Finally, automatic body measurements were carried out on 137 beef cattle in the ranch, and the automatic measurements of the four body measurements parameters were compared with the manual measurements, and the results showed that the average relative errors of body height, cross section height, body slant length, and tube girth were 4.32%, 3.71%, 5.58% and 6.25%, respectively, which met the needs of the ranch. The shortcomings were that fewer body-size parameters were measured, and the error of measuring circumference-type body-size parameters was relatively large. Later studies could use a multi-view approach to increase the number of body rule parameters to be measured and improve the accuracy of the parameters in the circumference category. [Conclusions] The article designed an automatic measurement method based on two-dimensional and three-dimensional contactless body measurements of beef cattle. Moreover, the innovatively proposed method of measuring tube girth has higher accuracy and better implementation compared with the current research on body measurements in beef cattle. The relative average errors of the four body tape parameters meet the needs of pasture measurements and provide theoretical and practical guidance for the automatic measurement of body tape in beef cattle.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Tomato Growth Height Prediction Method by Phenotypic Feature Extraction Using Multi-modal Data
    GONG Yu, WANG Ling, ZHAO Rongqiang, YOU Haibo, ZHOU Mo, LIU Jie
    Smart Agriculture    2025, 7 (1): 97-110.   DOI: 10.12133/j.smartag.SA202410032
    Abstract3454)   HTML99)    PDF(pc) (1307KB)(314)       Save

    [Objective] Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming. However, current prediction methods predominantly rely on empirical, mechanistic, or learning-based models that utilize either images data or environmental data. These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively. [Methods] To address this limitation, a two-stage phenotypic feature extraction (PFE) model based on deep learning algorithm of recurrent neural network (RNN) and long short-term memory (LSTM) was developed. The model integrated environment and plant information to provide a holistic understanding of the growth process, emploied phenotypic and temporal feature extractors to comprehensively capture both types of features, enabled a deeper understanding of the interaction between tomato plants and their environment, ultimately leading to highly accurate predictions of growth height. [Results and Discussions] The experimental results showed the model's effectiveness: When predicting the next two days based on the past five days, the PFE-based RNN and LSTM models achieved mean absolute percentage error (MAPE) of 0.81% and 0.40%, respectively, which were significantly lower than the 8.00% MAPE of the large language model (LLM) and 6.72% MAPE of the Transformer-based model. In longer-term predictions, the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead, the PFE-RNN model continued to outperform the other two baseline models, with MAPE of 2.66% and 14.05%, respectively. [Conclusions] The proposed method, which leverages phenotypic-temporal collaboration, shows great potential for intelligent, data-driven management of tomato cultivation, making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Agri-QA Net: Multimodal Fusion Large Language Model Architecture for Crop Knowledge Question-Answering System
    WU Huarui, ZHAO Chunjiang, LI Jingchen
    Smart Agriculture    2025, 7 (1): 1-10.   DOI: 10.12133/j.smartag.SA202411005
    Abstract3396)   HTML274)    PDF(pc) (1010KB)(1990)       Save

    [Objective] As agriculture increasingly relies on technological innovations to boost productivity and ensure sustainability, farmers need efficient and accurate tools to aid their decision-making processes. A key challenge in this context is the retrieval of specialized agricultural knowledge, which can be complex and diverse in nature. Traditional agricultural knowledge retrieval systems have often been limited by the modalities they utilize (e.g., text or images alone), which restricts their effectiveness in addressing the wide range of queries farmers face. To address this challenge, a specialized multimodal question-answering system tailored for cabbage cultivation was proposed. The system, named Agri-QA Net, integrates multimodal data to enhance the accuracy and applicability of agricultural knowledge retrieval. By incorporating diverse data modalities, Agri-QA Net aims to provide a holistic approach to agricultural knowledge retrieval, enabling farmers to interact with the system using multiple types of input, ranging from spoken queries to images of crop conditions. By doing so, it helps address the complexity of real-world agricultural environments and improves the accessibility of relevant information. [Methods] The architecture of Agri-QA Net was built upon the integration of multiple data modalities, including textual, auditory, and visual data. This multifaceted approach enables the system to develop a comprehensive understanding of agricultural knowledge, allowed the system to learn from a wide array of sources, enhancing its robustness and generalizability. The system incorporated state-of-the-art deep learning models, each designed to handle one specific type of data. Bidirectional Encoder Representations from Transformers (BERT)'s bidirectional attention mechanism allowed the model to understand the context of each word in a given sentence, significantly improving its ability to comprehend complex agricultural terminology and specialized concepts. The system also incorporated acoustic models for processing audio inputs. These models analyzed the spoken queries from farmers, allowing the system to understand natural language inputs even in noisy, non-ideal environments, which was a common challenge in real-world agricultural settings. Additionally, convolutional neural networks (CNNs) were employed to process images from various stages of cabbage growth. CNNs were highly effective in capturing spatial hierarchies in images, making them well-suited for tasks such as identifying pests, diseases, or growth abnormalities in cabbage crops. These features were subsequently fused in a Transformer-based fusion layer, which served as the core of the Agri-QA Net architecture. The fusion process ensured that each modality—text, audio, and image—contributes effectively to the final model's understanding of a given query. This allowed the system to provide more nuanced answers to complex agricultural questions, such as identifying specific crop diseases or determining the optimal irrigation schedules for cabbage crops. In addition to the fusion layer, cross-modal attention mechanisms and domain-adaptive techniques were incorporated to refine the model's ability to understand and apply specialized agricultural knowledge. The cross-modal attention mechanism facilitated dynamic interactions between the text, audio, and image data, ensuring that the model paid attention to the most relevant features from each modality. Domain-adaptive techniques further enhanced the system's performance by tailoring it to specific agricultural contexts, such as cabbage farming, pest control, or irrigation management. [Results and Discussions] The experimental evaluations demonstrated that Agri-QA Net outperforms traditional single-modal or simple multimodal models in agricultural knowledge tasks. With the support of multimodal inputs, the system achieved an accuracy rate of 89.5%, a precision rate of 87.9%, a recall rate of 91.3%, and an F1-Score of 89.6%, all of which are significantly higher than those of single-modality models. The integration of multimodal data significantly enhanced the system's capacity to understand complex agricultural queries, providing more precise and context-aware answers. The addition of cross-modal attention mechanisms enabled for more nuanced and dynamic interaction between the text, audio, and image data, which in turn improved the model's understanding of ambiguous or context-dependent queries, such as disease diagnosis or crop management. Furthermore, the domain-adaptive technique enabled the system to focus on specific agricultural terminology and concepts, thereby enhancing its performance in specialized tasks like cabbage cultivation and pest control. The case studies presented further validated the system's ability to assist farmers by providing actionable, domain-specific answers to questions, demonstrating its practical application in real-world agricultural scenarios. [Conclusions] The proposed Agri-QA Net framework is an effective solution for addressing agricultural knowledge questions, especially in the domain of cabbage cultivation. By integrating multimodal data and leveraging advanced deep learning techniques, the system demonstrates a high level of accuracy and adaptability. This study not only highlights the potential of multimodal fusion in agriculture but also paves the way for future developments in intelligent systems designed to support precision farming. Further work will focus on enhancing the model's performance by expanding the dataset to include more diverse agricultural scenarios, refining the handling of dialectical variations in audio inputs, and improving the system's ability to detect rare crop diseases. The ultimate goal is to contribute to the modernization of agricultural practices, offering farmers more reliable and effective tools to solve the challenges in crop management.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    A Lightweight Model for Detecting Small Targets of Litchi Pests Based on Improved YOLOv10n
    LI Zusheng, TANG Jishen, KUANG Yingchun
    Smart Agriculture    2025, 7 (2): 146-159.   DOI: 10.12133/j.smartag.SA202412003
    Abstract3384)   HTML150)    PDF(pc) (2262KB)(3976)       Save

    [Objective] The accuracy of identifying litchi pests is crucial for implementing effective control strategies and promoting sustainable agricultural development. However, the current detection of litchi pests is characterized by a high percentage of small targets, which makes target detection models challenging in terms of accuracy and parameter count, thus limiting their application in real-world production environments. To improve the identification efficiency of litchi pests, a lightweight target detection model YOLO-LP (YOLO-Litchi Pests) based on YOLOv10n was proposed. The model aimed to enhance the detection accuracy of small litchi pest targets in multiple scenarios by optimizing the network structure and loss function, while also reducing the number of parameters and computational costs. [Methods] Two classes of litchi insect pests (Cocoon and Gall) images were collected as datasets for modeling in natural scenarios (sunny, cloudy, post-rain) and laboratory environments. The original data were expanded through random scaling, random panning, random brightness adjustments, random contrast variations, and Gaussian blurring to balance the category samples and enhance the robustness of the model, generating a richer dataset named the CG dataset (Cocoon and Gall dataset). The YOLO-LP model was constructed after the following three improvements. Specifically, the C2f module of the backbone network (Backbone) in YOLOv10n was optimized and the C2f_GLSA module was constructed using the global-to-local spatial aggregation (GLSA) module to focus on small targets and enhance the differentiation between the targets and the backgrounds, while simultaneously reducing the number of parameters and computation. A frequency-aware feature fusion module (FreqFusion) was introduced into the neck network (Neck) of YOLOv10n and a frequency-aware path aggregation network (FreqPANet) was designed to reduce the complexity of the model and address the problem of fuzzy and shifted target boundaries. The SCYLLA-IoU (SIoU) loss function replaced the Complete-IoU (CIoU) loss function from the baseline model to optimize the target localization accuracy and accelerate the convergence of the training process. [Results and Discussions] YOLO-LP achieved 90.9%, 62.2%, and 59.5% for AP50, AP50:95, and AP-Small50:95 in the CG dataset, respectively, and 1.9%, 1.0%, and 1.2% higher than the baseline model. The number of parameters and the computational costs were reduced by 13% and 17%, respectively. These results suggested that YOLO-LP had a high accuracy and lightweight design. Comparison experiments with different attention mechanisms validated the effectiveness of the GLSA module. After the GLSA module was added to the baseline model, AP50, AP50:95, and AP-Small50:95 achieved the highest performance in the CG dataset, reaching 90.4%, 62.0%, and 59.5%, respectively. Experiment results comparing different loss functions showed that the SIoU loss function provided better fitting and convergence speed in the CG dataset. Ablation test results revealed that the validity of each model improvement and the detection performance of any combination of the three improvements was significantly better than the baseline model in the YOLO-LP model. The performance of the models was optimal when all three improvements were applied simultaneously. Compared to several mainstream models, YOLO-LP exhibited the best overall performance, with a model size of only 5.1 MB, 1.97 million parameters (Params), and a computational volume of 5.4 GFLOPs. Compared to the baseline model, the detection of the YOLO-LP performance was significantly improved across four multiple scenarios. In the sunny day scenario, AP50, AP50:95, and AP-Small50:95 increased by 1.9%, 1.0 %, and 2.0 %, respectively. In the cloudy day scenario, AP50, AP50:95, and AP-Small50:95 increased by 2.5%, 1.3%, and 1.3%, respectively. In the post-rain scenario, AP50, AP50:95, and AP-Small50:95 increased by 2.0%, 2.4%, and 2.4%, respectively. In the laboratory scenario, only AP50 increased by 0.7% over the baseline model. These findings indicated that YOLO-LP achieved higher accuracy and robustness in multi-scenario small target detection of litchi pests. [Conclusions] The proposed YOLO-LP model could improve detection accuracy and effectively reduce the number of parameters and computational costs. It performed well in small target detection of litchi pests and demonstrated strong robustness across different scenarios. These improvements made the model more suitable for deployment on resource-constrained mobile and edge devices. The model provided a valuable technical reference for small target detection of litchi pests in various scenarios.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Automatic Measurement of Mongolian Horse Body Based on Improved YOLOv8n-pose and 3D Point Cloud Analysis
    LI Minghuang, SU Lide, ZHANG Yong, ZONG Zheying, ZHANG Shun
    Smart Agriculture    2024, 6 (4): 91-102.   DOI: 10.12133/j.smartag.SA202312027
    Abstract3248)   HTML73)    PDF(pc) (2477KB)(3159)       Save

    [Objective] There exist a high genetic correlation among various morphological characteristics of Mongolian horses. Utilizing advanced technology to obtain body structure parameters related to athletic performance could provide data support for breeding institutions to develop scientific breeding plans and establish the groundwork for further improvement of Mongolian horse breeds. However, traditional manual measurement methods are time-consuming, labor-intensive, and may cause certain stress responses in horses. Therefore, ensuring precise and effective measurement of Mongolian horse body dimensions is crucial for formulating early breeding plans. [Method] Video images of 50 adult Mongolian horses in the suitable breeding stage at the Inner Mongolia Agricultural University Horse Breeding Technical Center was first collected. Fifty images per horse were captured to construct the training and validation sets, resulting in a total of 2 500 high-definition RGB images of Mongolian horses, with an equal ratio of images depicting horses in motion and at rest. To ensure the model's robustness and considering issues such as angles, lighting, and image blurring during actual image capture, a series of enhancement algorithms were applied to the original dataset, expanding the Mongolian horse image dataset to 4 000 images. The YOLOv8n-pose was employed as the foundational keypoint detection model. Through the design of the C2f_DCN module, deformable convolution (DCNV2) was integrated into the C2f module of the Backbone network to enhance the model's adaptability to different horse poses in real-world scenes. Besides, an SA attention module was added to the Neck network to improve the model's focus on critical features. The original loss function was replaced with SCYLLA-IoU (SIoU) to prioritize major image regions, and a cosine annealing method was employed to dynamically adjust the learning rate during model training. The improved model was named DSS-YOLO (DCNv2-SA-SIoU-YOLO) network model. Additionally, a test set comprising 30 RGB-D images of mature Mongolian horses was selected for constructing body dimension measurement tasks. DSS-YOLO was used for keypoint detection of body dimensions. The 2D keypoint coordinates from RGB images were fused with corresponding depth values from depth images to obtain 3D keypoint coordinates, and Mongolian horse's point cloud information was transformed. Point cloud processing and analysis were performed using pass-through filtering, random sample consensus (RANSAC) shape fitting, statistical outlier filtering, and principal component analysis (PCA) coordinate system correction. Finally, body height, body oblique length, croup height, chest circumference, and croup circumference were automatically computed based on keypoint spatial coordinates. [Results and Discussion] The proposed DSS-YOLO model exhibited parameter and computational costs of 3.48 M and 9.1 G, respectively, with an average accuracy mAP0.5:0.95 reaching 92.5%, and a dDSS of 7.2 pixels. Compared to Hourglass, HRNet, and SimCC, mAP0.5:0.95 increased by 3.6%, 2.8%, and 1.6%, respectively. By relying on keypoint coordinates for automatic calculation of body dimensions and suggesting the use of a mobile least squares curve fitting method to complete the horse's hip point cloud, experiments involving 30 Mongolian horses showed a mean average error (MAE) of 3.77 cm and mean relative error (MRE) of 2.29% in automatic measurements. [Conclusions] The results of this study showed that DSS-YOLO model combined with three-dimensional point cloud processing methods can achieve automatic measurement of Mongolian horse body dimensions with high accuracy. The proposed measurement method can also be extended to different breeds of horses, providing technical support for horse breeding plans and possessing practical application value.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Pig Back Transformer: Automatic 3D Pig Body Measurement Model
    WANG Yuxiao, SHI Yuanyuan, CHEN Zhaoda, WU Zhenfang, CAI Gengyuan, ZHANG Sumin, YIN Ling
    Smart Agriculture    2024, 6 (4): 76-90.   DOI: 10.12133/j.smartag.SA202401023
    Abstract3165)   HTML83)    PDF(pc) (2776KB)(2117)       Save

    [Objective] Nowadays most no contact body size measurement studies are based on point cloud segmentation method, they use a trained point cloud segmentation neural network to segment point cloud of pigs, then locate measurement points based on them. But point cloud segmentation neural network always need a larger graphics processing unit (GPU) memory, moreover, the result of the measurement key point still has room of improvement. This study aims to design a key point generating neural network to extract measurement key points from pig's point cloud. Reducing the GPU memory usage and improve the result of measurement points at the same time, improve both the efficiency and accuracy of the body size measurement. [Methods] A neural network model was proposed using improved Transformer attention mechanic called Pig Back Transformer for generating key points and back orientation points which were related to pig body dimensions. In the first part of the network, it was introduced an embedding structure for initial feature extraction and a Transformer encoder structure with edge attention which was a self-attention mechanic improved from Transformer's encoder. The embedding structure using two shared multilayer perceptron (MLP) and a distance embedding algorithm, it takes a set of points from the edge of pig back's point cloud as input and then extract information from the edge points set. In the encoder part, information about the offset distances between edge points and mass point which were their feature that extracted by the embedding structure mentioned before incorporated. Additionally, an extraction algorithm for back edge point was designed for extracting edge points to generate the input of the neural network model. In the second part of the network, it was proposed a Transformer encoder with improved self-attention called back attention. In the design of back attention, it also had an embedding structure before the encoder structure, this embedding structure extracted features from offset values, these offset values were calculated by the points which are none-edge and down sampled by farthest point sampling (FPS) to both the relative centroid point and model generated global key point from the first part that introduced before. Then these offset values were processed with max pooling with attention generated by the extracted features of the points' axis to extract more information that the original Transformer encoder couldn't extract with the same number of parameters. The output part of the model was designed to generate a set of offsets of the key points and points for back direction fitting, than add the set offset to the global key point to get points for pig body measurements. At last, it was introduced the methods for calculating body dimensions which were length, height, shoulder width, abdomen width, hip width, chest circumference and abdomen circumference using key points and back direction fitting points. [Results and Discussions] In the task of generating key points and points for back direction fitting, the improved Pig Back Transformer performed the best in the accuracy wise in the models tested with the same size of parameters, and the back orientation points generated by the model were evenly distributed which was a good preparation for a better body length calculation. A melting test for edge detection part with two attention mechanic and edge trim method both introduced above had being done, when the edge detection and the attention mechanic got cut off, the result had been highly impact, it made the model couldn't perform as well as before, when the edge trim method of preprocessing part had been cut off, there's a moderate impact on the trained model, but it made the loss of the model more inconsistence while training than before. When comparing the body measurement algorithm with human handy results, the relative error in length was 0.63%, which was an improvement compared to other models. On the other hand, the relative error of shoulder width, abdomen width and hip width had edged other models a little but there was no significant improvement so the performance of these measurement accuracy could be considered negligible, the relative error of chest circumference and abdomen circumference were a little bit behind by the other methods existed, it's because the calculate method of circumferences were not complicated enough to cover the edge case in the dataset which were those point cloud that have big holes in the bottom of abdomen and chest, it impacted the result a lot. [Conclusions] The improved Pig Back Transformer demonstrates higher accuracy in generating key points and is more resource-efficient, enabling the calculation of more accurate pig body measurements. And provides a new perspective for non-contact livestock body size measurements.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Lightweight Cattle Facial Recognition Method Based on Improved YOLOv11
    HAN Yu, QI Kangkang, ZHENG Jiye, LI Jinai, JIANG Fugui, ZHANG Xianglun, YOU Wei, ZHANG Xia
    Smart Agriculture    2025, 7 (3): 173-184.   DOI: 10.12133/j.smartag.SA202502010
    Abstract3066)   HTML85)    PDF(pc) (2163KB)(170)       Save

    [Objective] Beef cattle breeding constitutes a pivotal component of modern animal husbandry, where accurate individual identification serves as the cornerstone for advancing automated technologies, including intelligent weight measurement, body condition scoring, body conformation assessment, and behavior monitoring. However, practical breeding environments are riddled with challenges: soiled conditions, cluttered backgrounds, and constant animal movement collectively result in high variability in cattle facial data features. Furthermore, inconsistent lighting and diverse shooting angles often obscure key features, increasing the risk of misjudgment during detection. To tackle these issues, this study introduces an improved model, YOLO-PCW, which enhances detection performance while maintaining a lightweight structure, effectively addressing the complexities of precise cattle face recognition in challenging breeding settings. [Methods] The research leveraged the Cow Fusion dataset (CFD), a comprehensive collection of real-world cattle face images captured under variable lighting conditions, from multiple angles, and against complex backgrounds, for model training and validation. Concurrently, a Custom Cow Monitor Dataset (CMD) was created from video footage obtained through the a breeding farm's monitoring system, providing a robust basis for evaluating the model's generalization capabilities. The YOLOv11 architecture served as the foundational framework for implementing the following performance improvements. The partial convolution (PConv) was seamlessly integrated into the C3K2 module within the YOLOv11 head network. Utilizing the sparse convolutional properties of PConv on the feature maps, the convolutional structure was meticulously optimized, reducing computational redundancy and memory access while preserving the model's accuracy, rendering it highly suitable for real-time applications. Additionally, the convolutional block attention module (CBAM) was incorporated to enhance feature map processing through adaptive channel-wise and spatial attentions. This refinement enabled precise extraction of target regions by mitigating background interference, allowing the model to focus on critical anatomical features such as the eyes, mouth, and nose. Furthermore, the weighted intersection over union (WIoU) loss function was adopted to replace the CIoU, optimizing the weighted strategy for bounding box regression errors. This innovation reduced the adverse effects of large or outlier gradients in extreme samples, enabling the model to prioritize average-quality samples for refinement. The resulting improvement in key region localization accuracy bolstered the model's generalization capability and overall performance, establishing a state-of-the-art cattle face recognition framework. [Results and Discussion] The YOLO-PCW model achieved a remarkable accuracy rate (P) of 96.4%, recall rate (R) of 96.7%, and mean average precision (mAP) of 98.7%. With 2.3 million parameters and a computational load of 5.6 GFLOPs, it not only improved accuracy, recall, and mAP by 3.6, 5, and 4.4 percentage point respectively, but also achieved a significant reduction in floating-point computational load and parameter size, down to 88.9% and 88.5% of the original model's, respectively. Ablation studies revealed that the CBAM module enhanced precision from 92.8% to 95.2%. The WIoU loss function optimized target positioning accuracy, achieving a precision of 93.8%. The PConv module substantially reduced computational load from 6.3 GFLOPs to 5.5 GFLOPs, thereby lightening the model's computational burden significantly. The synergistic collaboration of these components provided robust support for enhancing the performance of the cattle face recognition model. Comparative experiments demonstrated that under identical conditions, the YOLO-PCW model outperformed algorithms such as Faster-RCNN, SSD, YOLOv5, YOLOv7-tiny, and YOLOv8 under identical conditions, exhibiting the most outstanding performance. It effectively balanced recognition accuracy with computational efficiency, achieving optimal utilization of computational resources. [Conclusions] The improved YOLO-PCW model, featuring a lightweight architecture and optimized attention mechanism, could successfully improve detection accuracy while simplifies deployment. It can achieve precise cattle face recognition in real-world breeding environments, providing an efficient and practical solution for individual identification in applications such as animal welfare breeding, intelligent ranch management, smart ranch construction, and animal health monitoring.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Current Status and Trends of Application Scenarios and Industrial Development in the Agricultural Low-Altitude Economy
    HE Yong, DAI Fushuang, ZHU Jiangpeng, HE Liwen, WANG Yueying
    Smart Agriculture    2025, 7 (6): 1-17.   DOI: 10.12133/j.smartag.SA202507014
    Abstract2988)   HTML131)    PDF(pc) (2623KB)(838)       Save

    [Significance] The agricultural low-altitude economy has rapidly emerged as a transformative force in rural modernization, catalyzed by advancements in intelligent technologies and gradual improvements in low-altitude airspace governance. It encompasses a wide array of applications where aerial platforms—particularly unmanned aerial vehicles (UAVs)—play a pivotal role in reshaping agricultural production, environmental monitoring, and rural management systems. Systematically analyzing the development trajectory and implementation pathways of agricultural low-altitude economy holds considerable significance for promoting cross-sector integration, accelerating policy and technological innovation, and enabling the widespread adoption of intelligent solutions across agriculture-related industries. [Progress] This review draws upon an extensive body of literature and applies keyword clustering analysis to systematically explore the development of the agricultural low-altitude economy. Based on 13 570 peer-reviewed articles retrieved from the Web of Science database between 2000 and 2024, the study reveals a rapid growth trajectory, particularly since 2011, driven by technological breakthroughs in UAVs, sensors, and intelligent analytics. Five representative application domains were identified: smart farming, animal husbandry, forestry, fisheries, and rural governance. Through the integration of bibliometric tools and structured keyword combinations, the study captures both the evolution of research focus and the expansion of technical capabilities. The results demonstrate that agricultural low-altitude economy has progressed from early-stage feasibility validation toward large-scale, multi-functional applications. At the same time, it has catalyzed the development of an emerging industrial framework encompassing equipment manufacturing, aerial service provision, operational support systems, and talent development. These trends highlight the growing maturity and strategic relevance of agricultural low-altitude economy as a technological enabler for modern agriculture. In the context of smart farming, low-altitude technologies are extensively utilized for precision sowing, variable-rate fertilization, real-time crop health monitoring, and pest and disease detection. UAV-based remote sensing facilitates the creation of high-resolution field maps and spatially explicit data layers that support data-driven and site-specific decision-making in modern agricultural management. In smart livestock systems, drones are employed for livestock monitoring, early disease detection, and fence-line inspections, particularly in large, remote pasture areas with limited ground accessibility. Smart forestry applications include forest fire early warning, forest inventory updates, and dynamic monitoring of ecological changes, enabled by low-altitude hyperspectral, LiDAR, and thermal imaging technologies. For smart fisheries, UAVs and amphibious drones support water quality sensing, pond surveillance, and feeding behavior analysis, thereby enhancing aquaculture productivity, animal welfare, and environmental sustainability. In the broader context of smart rural governance, agricultural low-altitude economy technologies assist with infrastructure inspections, land use monitoring, rural logistics coordination, and even public security surveillance, contributing to comprehensive, intelligent rural revitalization. Alongside scenario-based applications, this paper also summarizes the current structure of the agricultural low-altitude economy industry chain, which is preliminarily composed of four key components: manufacturing, flight operations, supporting services, and integrated service platforms. In the manufacturing segment, the development and production of specialized agricultural UAVs, multi-rotor drones, and fixed-wing VTOL aircraft are advancing rapidly, enabling adaptation to various terrains and crop types. The flight operations segment is expanding with increasing market participation, offering aerial spraying, broadcasting, surveying, and inspection services with improved timeliness and precision. Supporting services include airspace coordination, meteorological forecasting, equipment maintenance, and safety supervision. Additionally, comprehensive service systems have emerged, integrating digital platform management, third-party evaluation, data analysis, and agricultural technical advisory services. Talent development and training form a crucial pillar of agricultural low-altitude economy's development. A growing number of vocational institutions and drone enterprises are providing structured training programs for agricultural drone pilots, technicians, and system operators. These programs aim to enhance operational capabilities, ensure safety compliance, and foster human capital that can support the sustainable growth of agricultural low-altitude economy applications across rural regions. [Conclusions and Prospects] Agricultural low-altitude economy is transitioning from isolated, technology-specific applications to an integrated, platform-oriented ecosystem that blends equipment, data, services, and governance. To fully realize its potential, several strategic directions should be pursued. First, there is a pressing need to refine regulatory frameworks to accommodate the unique operational characteristics of rural low-altitude airspace, including dynamic zoning policies, UAV registration standards, and risk management protocols. Second, sustained investment in core technologies, such as autonomous flight control, multi-modal sensing, and AI-based analytics, are essential for overcoming current technical limitations and unlocking new capabilities. Third, agricultural low-altitude economy's infrastructure backbone should be reinforced through the deployment of distributed drone ports, mobile ground control stations, and secure data networks, particularly in underserved regions. Additionally, establishing a national-scale training and certification framework is critical for ensuring an adequate supply of skilled professionals, while innovative funding models such as public-private partnerships and scenario-based insurance can enhance accessibility and scalability. Pilot projects and demonstration zones should also be expanded to validate and refine agricultural low-altitude economy systems under diverse agroecological and socio-economic conditions. In summary, agricultural low-altitude economy offers strategic leverage for advancing China's goals in smart agriculture, green development, and rural revitalization. With cross-sector collaboration and proactive policy support, agricultural low-altitude economy can evolve into a resilient and inclusive ecosystem that fosters agricultural transformation, boosts productivity, and enhances environmental sustainability.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Lightweight Apple Leaf Disease Detection Algorithm Based on Improved YOLOv8
    LUO Youlu, PAN Yonghao, XIA Shunxing, TAO Youzhi
    Smart Agriculture    2024, 6 (5): 128-138.   DOI: 10.12133/j.smartag.SA202406012
    Abstract2987)   HTML122)    PDF(pc) (1702KB)(2337)       Save

    [Objective] As one of China's most important agricultural products, apples hold a significant position in cultivation area and yield. However, during the growth process, apples are prone to various diseases that not only affect the quality of the fruit but also significantly reduce the yield, impacting farmers' economic benefits and the stability of market supply. To reduce the incidence of apple diseases and increase fruit yield, developing efficient and fast apple leaf disease detection technology is of great significance. An improved YOLOv8 algorithm was proposed to identify the leaf diseases that occurred during the growth of apples. [Methods] YOLOv8n model was selected to detect various leaf diseases such as brown rot, rust, apple scab, and sooty blotch that apples might encounter during growth. SPD-Conv was introduced to replace the original convolutional layers to retain fine-grained information and reduce model parameters and computational costs, thereby improving the accuracy of disease detection. The multi-scale dilated attention (MSDA) attention mechanism was added at appropriate positions in the Neck layer to enhance the model's feature representation capability, which allowed the model to learn the receptive field dynamically and adaptively focus on the most representative regions and features in the image, thereby enhancing the ability to extract disease-related features. Finally, inspired by the RepVGG architecture, the original detection head was optimized to achieve a separation of detection and inference architecture, which not only accelerated the model's inference speed but also enhanced feature learning capability. Additionally, a dataset of apple leaf diseases containing the aforementioned diseases was constructed, and experiments were conducted. [Results and Discussions] Compared to the original model, the improved model showed significant improvements in various performance metrics. The mAP50 and mAP50:95 achieved 88.2% and 37.0% respectively, which were 2.7% and 1.3% higher than the original model. In terms of precision and recall, the improved model increased to 83.1% and 80.2%, respectively, representing an improvement of 0.9% and 1.1% over the original model. Additionally, the size of the improved model was only 7.8 MB, and the computational cost was reduced by 0.1 G FLOPs. The impact of the MSDA placement on model performance was analyzed by adding it at different positions in the Neck layer, and relevant experiments were designed to verify this. The experimental results showed that adding MSDA at the small target layer in the Neck layer achieved the best effect, not only improving model performance but also maintaining low computational cost and model size, providing important references for the optimization of the MSDA mechanism. To further verify the effectiveness of the improved model, various mainstream models such as YOLOv7-tiny, YOLOv9-c, RetinaNet, and Faster-RCNN were compared with the propoed model. The experimental results showed that the improved model outperformed these models by 1.4%, 1.3%, 7.8%, and 11.6% in mAP50, 2.8%, 0.2%, 3.4%, and 5.6% in mAP50:95. Moreover, the improved model showed significant advantages in terms of floating-point operations, model size, and parameter count, with a parameter count of only 3.7 MB, making it more suitable for deployment on hardware-constrained devices such as drones. In addition, to assess the model's generalization ability, a stratified sampling method was used, selecting 20% of the images from the dataset as the test set. The results showed that the improved model could maintain a high detection accuracy in complex and variable scenes, with mAP50 and mAP50:95 increasing by 1.7% and 1.2%, respectively, compared to the original model. Considering the differences in the number of samples for each disease in the dataset, a class balance experiment was also designed. Synthetic samples were generated using oversampling techniques to increase the number of minority-class samples. The experimental results showed that the class-balanced dataset significantly improved the model's detection performance, with overall accuracy increasing from 83.1% to 85.8%, recall from 80.2% to 83.6%, mAP50 from 88.2% to 88.9%, and mAP50:95 from 37.0% to 39.4%. The class-balanced dataset significantly enhanced the model's performance in detecting minority diseases, thereby improving the overall performance of the model. [Conclusions] The improved model demonstrated significant advantages in apple leaf disease detection. By introducing SPD-Conv and MSDA attention mechanisms, the model achieved noticeable improvements in both precision and recall while effectively reducing computational costs, leading to more efficient detection capabilities. The improved model could provide continuous health monitoring throughout the apple growth process and offer robust data support for farmers' scientific decision-making before fruit harvesting.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Spectral Technology in Vegetable Production Detection: Research Progress, Challenges and Suggestions
    BAI Juekun, CHEN Huaimeng, DONG Daming, LIU Yachao, YUE Xiaolong, DU Xiuke
    Smart Agriculture    2025, 7 (4): 1-17.   DOI: 10.12133/j.smartag.SA202504027
    Abstract2900)   HTML67)    PDF(pc) (1474KB)(162)       Save

    [Significance] Vegetables are indispensable to global food security and human nutrition, yet approximately 33% of the annual 1.2 billion-ton harvest is lost or wasted, largely because of undetected biotic and abiotic stresses, poor post-harvest management, and chemical safety hazards. Conventional analytical workflows, based on wet chemistry and chromatography, are destructive, labour-intensive, and difficult to scale, creating an urgent need for rapid, non-invasive sensing tools that can operate across the full production-to-consumption continuum. Optical spectroscopy, spanning near-infrared (NIR), Raman, fluorescence, laser-induced breakdown spectroscopy (LIBS), and UV-Vis modalities, offers label-free, multiplexed, and second-scale measurements directly on living plants or minimally processed products. Existing reviews have concentrated on isolated techniques or single application niches, leaving critical knowledge gaps regarding hardware robustness under open-field conditions, algorithmic generalisability across cultivars and climates, data interoperability, and cost-driven adoption barriers for smallholders. [Progress] This paper presents a holistic, chain-wide appraisal of spectroscopic sensing in vegetable production. It shows that hardware evolution has been dominated by miniaturisation and functional integration. Hand-held NIR units (e.g., Neospectra MEMS, NirVana AG410) now weigh <300 g and achieve R2 > 0.95 for soluble solids and moisture in tomato, zucchini, and pepper. Palm-top Raman systems (9 × 7 × 4 cm) equipped with 1 064 nm lasers and InGaAs detectors suppress fluorescence sufficiently to quantify lycopene (RMSE = 1.14 mg/100 g) and classify ripeness stages with 100% accuracy. Battery-powered fluorescence sensors coupled with smartphones wirelessly stream data to cloud-based convolutional neural networks (CNNs), delivering 93%~100% correct cultivar identification for spinach, onion, and tomato seeds within 5 s per sample. Methodological advances combine advanced chemometrics and deep learning. Transfer learning enables a model trained on greenhouse tomatoes to predict field-grown cherry tomatoes with only 10% recalibration samples, cutting data acquisition costs by 70%. SERS substrates, fabricated as flexible "place-and-play" nano-mesh films, boost Raman signals by 106~108, pushing limits of detection for carbaryl, imidacloprid, and thiamethoxam below 1 mg/kg on pak-choi and lettuce. Multi-modal fusion (LIBS-NIR) simultaneously quantifies macro-elements (Ca, K, Mg) and micro-elements (Fe, Mn) with relative errors <5%. Chain-wide demonstrations span five critical stages: (i) breeding—NIR screens seed viability via starch and moisture signatures; (ii) cultivation—portable Raman "leaf-clip" sensors detect nitrate deficiency (1 045 cm-1 peak) and early pathogen attack (LsoA vs. LsoB, 80% accuracy) in lettuce and tomato before visible symptoms emerge; (iii) harvest—non-invasive lycopene monitoring in tomato and carotenoid profiling in chilli guides optimal picking time and reduces post-harvest losses by 15%; (iv) storage—chlorophyll fluorescence tracks water loss and senescence in black radish and carrot over six-month cold storage, enabling dynamic shelf-life prediction; (v) market entry—LIBS inspects incoming crates for Pb and Cd in seconds, while fluorescence-SVM pipelines simultaneously verify pesticide residues, ensuring compliance with EU and Chinese MRLs. Data governance initiatives are emerging but remain fragmented. Several consortia have released open spectral libraries (e.g., VegSpec-1.0 with 50 000 annotated spectra from 30 vegetable species), yet differences in acquisition parameters, preprocessing pipelines, and metadata schemas hinder cross-study reuse. [Conclusions and Prospects] Spectroscopic sensing has matured from laboratory proof-of-concept to robust field prototypes capable of guiding real-time decisions across the entire vegetable value chain. Nevertheless, four priority areas must be addressed to unlock global adoption: Model generalisation—curate large-scale, multi-environment, multi-cultivar spectral repositories and embed meta-learning algorithms that continuously adapt to new genotypes and climates with minimal retraining. Hardware resilience—develop self-calibrating sensors with adaptive optics and real-time environmental compensation (temperature, humidity, ambient light) to maintain laboratory-grade SNR in dusty, humid, or high-irradiance field settings. Standardisation and interoperability—establish ISO-grade protocols for hardware interfaces, data formats, calibration transfer, and privacy-preserving data sharing, enabling seamless integration of devices, clouds, and decision-support platforms. Cost-effective commercialisation—pursue modular, open-hardware designs leveraging printed optics and economies of scale to reduce unit costs below USD 500, and introduce service-based models (leasing, pay-per-scan) tailored to smallholder economics. If these challenges are met, spectroscopy-based digital twins of vegetable production systems could become a reality, delivering safer food, reduced waste, and climate-smart agriculture within the next decade.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Lightweight Tomato Leaf Disease and Pest Detection Method Based on Improved YOLOv10n
    WU Liuai, XU Xueke
    Smart Agriculture    2025, 7 (1): 146-155.   DOI: 10.12133/j.smartag.SA202410023
    Abstract2891)   HTML122)    PDF(pc) (1834KB)(986)       Save

    [Objective] To address the challenges in detecting tomato leaf diseases and pests, such as complex environments, small goals, low precision, redundant parameters, and high computational complexity, a novel lightweight, high-precision, real-time detection model was proposed called YOLOv10n-YS. This model aims to accurately identify diseases and pests, thereby providing a solid scientific basis for their prevention and management strategies. Methods] The dataset was collected using mobile phones to capture images from multiple angles under natural conditions, ensuring complete and clear leaf images. It included various weather conditions and covered nine types: Early blight, leaf mold, mosaic virus, septoria, spider mites damage, yellow leaf curl virus, late blight, leaf miner disease, and healthy leaves, with all images having a resolution of 640×640 pixels. In the proposed YOLOv10n-YS model, firstly, the C2f in the backbone network was replaced with C2f_RepViTBlock, thereby reducing the computational load and parameter volume and achieving a lightweight design. Secondly, through the introduction of a sliced operation SimAM attention mechanism, the Conv_SWS module was formed, which enhanced the extraction of small target features. Additionally, the DySample lightweight dynamic up sampling module was used to replace the up sampling module in the neck network, concentrating sampling points on target areas and ignoring backgrounds, thereby effectively identifying defects. Finally, the efficient channel attention (ECA) was improved by performing average pooling and max pooling on the input layer to aggregate features and then adding them together, which further enhanced global perspective information and features of different scales. The improved module, known as efficient channel attention with cross-channel interaction (EMCA) attention, was introduced, and the pyramid spatial attention (PSA) in the backbone network was replaced with the EMCA attention mechanism, thereby enhancing the feature extraction capability of the backbone network. [Results and Discussions] After introducing the C2f_RepViTBlock, the model's parameter volume and computational load were reduced by 12.3% and 9.7%, respectively, with mAP@0.5 and F1-Score each increased by 0.2% and 0.3%. Following the addition of the Conv_SWS and the replacement of the original convolution, mAP@0.5 and F1-Score were increased by 1.2% and 2%, respectively, indicating that the Conv_SWS module significantly enhanced the model's ability to extract small target features. After the introduction of DySample, mAP@0.5 and F1-Score were increased by 1.8% and 2.6%, respectively, but with a slight increase in parameter volume and computational load. Finally, the addition of the EMCA attention mechanism further enhanced the feature extraction capability of the backbone network. Through these four improvements, the YOLOv10n-YS model was formed. Compared with the YOLOv10n algorithm, YOLOv10n-YS reduced parameter volume and computational load by 13.8% and 8.5%, respectively, with both mAP@0.5 and F1-Score increased. These improvements not only reduced algorithm complexity but also enhanced detection accuracy, making it more suitable for industrial real-time detection. The detection accuracy of tomato diseases and pests using the YOLOv10n-YS algorithm was significantly better than that of comparative algorithms, and it had the lowest model parameter volume and computational load. The visualization results of detection by different models showed that the YOLOv10n-YS network could provide technical support for the detection and identification of tomato leaf diseases and pests. To verify the performance and robustness of the YOLOv10n-YS algorithm, comparative experiments were conducted on the public Plant-Village-9 dataset with different algorithms. The results showed that the average detection accuracy of YOLOv10n-YS on the Plant-Village dataset reached 91.1%, significantly higher than other algorithms. [Conclusions] The YOLOv10n-YS algorithm is not only characterized by occupying a small amount of space but also by possessing high recognition accuracy. On the tomato leaf dataset, excellent performance was demonstrated by this algorithm, thereby verifying its broad applicability and showcasing its potential to play an important role in large-scale crop pest and disease detection applications. Deploying the model on drone platforms and utilizing multispectral imaging technology can achieve real-time detection and precise localization of pests and diseases in complex field environments.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Agricultural Large Language Model Based on Precise Knowledge Retrieval and Knowledge Collaborative Generation
    JIANG Jingchi, YAN Lian, LIU Jie
    Smart Agriculture    2025, 7 (1): 20-32.   DOI: 10.12133/j.smartag.SA202410025
    Abstract2864)   HTML89)    PDF(pc) (2081KB)(1045)       Save

    [Objective] The rapid advancement of large language models (LLMs) has positioned them as a promising novel research paradigm in smart agriculture, leveraging their robust cognitive understanding and content generative capabilities. However, due to the lack of domain-specific agricultural knowledge, general LLMs often exhibit factual errors or incomplete information when addressing specialized queries, which is particularly prominent in agricultural applications. Therefore, enhancing the adaptability and response quality of LLMs in agricultural applications has become an important research direction. [Methods] To improve the adaptability and precision of LLMs in the agricultural applications, an innovative approach named the knowledge graph-guided agricultural LLM (KGLLM) was proposed. This method integrated information entropy for effective knowledge filtering and applied explicit constraints on content generation during the decoding phase by utilizing semantic information derived from an agricultural knowledge graph. The process began by identifying and linking key entities from input questions to the agricultural knowledge graph, which facilitated the formation of knowledge inference paths and the development of question-answering rationales. A critical aspect of this approach was ensuring the validity and reliability of the external knowledge incorporated into the model. This was achieved by evaluating the entropy difference in the model's outputs before and after the introduction of each piece of knowledge. Knowledge that didn't enhance the certainty of the answers was systematically filtered out. The knowledge paths that pass this entropy evaluation were used to adjust the token prediction probabilities, prioritizing outputs that were closely aligned with the structured knowledge. This allowed the knowledge graph to exert explicit guidance over the LLM's outputs, ensuring higher accuracy and relevance in agricultural applications. [Results and Discussions] The proposed knowledge graph-guided technique was implemented on five mainstream general-purpose LLMs, including open-source models such as Baichuan, ChatGLM, and Qwen. These models were compared with state-of-the-art knowledge graph-augmented generation methods to evaluate the effectiveness of the proposed approach. The results demonstrate that the proposed knowledge graph-guided approach significantly improved several key performance metrics of fluency, accuracy, factual correctness, and domain relevance. Compared to GPT-4o, the proposed method achieved notable improvements by an average of 2.592 3 in Mean BLEU, 2.815 1 in ROUGE, and 9.84% in BertScore. These improvements collectively signify that the proposed approach effectively leverages agricultural domain knowledge to refine the outputs of general-purpose LLMs, making them more suitable for agricultural applications. Ablation experiments further validated that the knowledge-guided agricultural LLM not only filtered out redundant knowledge but also effectively adjusts token prediction distributions during the decoding phase. This enhanced the adaptability of general-purpose LLMs in agriculture contexts and significantly improves the interpretability of their responses. The knowledge filtering and knowledge graph-guided model decoding method proposed in this study, which was based on information entropy, effectively identifies and selects knowledge that carried more informational content through the comparison of information entropy.Compared to existing technologies in the agricultural field, this method significantly reduced the likelihood of "hallucination" phenomena during the generation process. Furthermore, the guidance of the knowledge graph ensured that the model's generated responses were closely related to professional agricultural knowledge, thereby avoiding vague and inaccurate responses generated from general knowledge. For instance, in the application of pest and disease control, the model could accurately identify the types of crop diseases and corresponding control measures based on the guided knowledge path, thereby providing more reliable decision support. [Conclusions] This study provides a valuable reference for the construction of future agricultural large language models, indicating that the knowledge graphs guided mehtod has the potential to enhance the domain adaptability and answer quality of models. Future research can further explore the application of similar knowledge-guided strategies in other vertical fields to enhance the adaptability and practicality of LLMs across various professional domains.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Research Progress and Prospect of Multi-robot Collaborative SLAM in Complex Agricultural Scenarios
    MA Nan, CAO Shanshan, BAI Tao, KONG Fantao, SUN Wei
    Smart Agriculture    2024, 6 (6): 23-43.   DOI: 10.12133/j.smartag.SA202406005
    Abstract2810)   HTML138)    PDF(pc) (2300KB)(9017)       Save

    [Significance] The rapid development of artificial intelligence and automation has greatly expanded the scope of agricultural automation, with applications such as precision farming using unmanned machinery, robotic grazing in outdoor environments, and automated harvesting by orchard-picking robots. Collaborative operations among multiple agricultural robots enhance production efficiency and reduce labor costs, driving the development of smart agriculture. Multi-robot simultaneous localization and mapping (SLAM) plays a pivotal role by ensuring accurate mapping and localization, which are essential for the effective management of unmanned farms. Compared to single-robot SLAM, multi-robot systems offer several advantages, including higher localization accuracy, larger sensing ranges, faster response times, and improved real-time performance. These capabilities are particularly valuable for completing complex tasks efficiently. However, deploying multi-robot SLAM in agricultural settings presents significant challenges. Dynamic environmental factors, such as crop growth, changing weather patterns, and livestock movement, increase system uncertainty. Additionally, agricultural terrains vary from open fields to irregular greenhouses, requiring robots to adjust their localization and path-planning strategies based on environmental conditions. Communication constraints, such as unstable signals or limited transmission range, further complicate coordination between robots. These combined challenges make it difficult to implement multi-robot SLAM effectively in agricultural environments. To unlock the full potential of multi-robot SLAM in agriculture, it is essential to develop optimized solutions that address the specific technical demands of these scenarios. [Progress] Existing review studies on multi-robot SLAM mainly focus on a general technological perspective, summarizing trends in the development of multi-robot SLAM, the advantages and limitations of algorithms, universally applicable conditions, and core issues of key technologies. However, there is a lack of analysis specifically addressing multi-robot SLAM under the characteristics of complex agricultural scenarios. This study focuses on the main features and applications of multi-robot SLAM in complex agricultural scenarios. The study analyzes the advantages and limitations of multi-robot SLAM, as well as its applicability and application scenarios in agriculture, focusing on four key components: multi-sensor data fusion, collaborative localization, collaborative map building, and loopback detection. From the perspective of collaborative operations in multi-robot SLAM, the study outlines the classification of SLAM frameworks, including three main collaborative types: centralized, distributed, and hybrid. Based on this, the study summarizes the advantages and limitations of mainstream multi-robot SLAM frameworks, along with typical scenarios in robotic agricultural operations where they are applicable. Additionally, it discusses key issues faced by multi-robot SLAM in complex agricultural scenarios, such as low accuracy in mapping and localization during multi-sensor fusion, restricted communication environments during multi-robot collaborative operations, and low accuracy in relative pose estimation between robots. [Conclusions and Prospects] To enhance the applicability and efficiency of multi-robot SLAM in complex agricultural scenarios, future research needs to focus on solving these critical technological issues. Firstly, the development of enhanced data fusion algorithms will facilitate improved integration of sensor information, leading to greater accuracy and robustness of the system. Secondly, the combination of deep learning and reinforcement learning techniques is expected to empower robots to better interpret environmental patterns, adapt to dynamic changes, and make more effective real-time decisions. Thirdly, large language models will enhance human-robot interaction by enabling natural language commands, improving collaborative operations. Finally, the integration of digital twin technology will support more intelligent path planning and decision-making processes, especially in unmanned farms and livestock management systems. The convergence of digital twin technology with SLAM is projected to yield innovative solutions for intelligent perception and is likely to play a transformative role in the realm of agricultural automation. This synergy is anticipated to revolutionize the approach to agricultural tasks, enhancing their efficiency and reducing the reliance on labor.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Chinese Kiwifruit Text Named Entity Recognition Method Based on Dual-Dimensional Information and Pruning
    QI Zijun, NIU Dangdang, WU Huarui, ZHANG Lilin, WANG Lunfeng, ZHANG Hongming
    Smart Agriculture    2025, 7 (1): 44-56.   DOI: 10.12133/j.smartag.SA202410022
    Abstract2801)   HTML19)    PDF(pc) (1225KB)(645)       Save

    [Objective] Chinese kiwifruit texts exhibit unique dual-dimensional characteristics. The cross-paragraph dependency is complex semantic structure, whitch makes it challenging to capture the full contextual relationships of entities within a single paragraph, necessitating models capable of robust cross-paragraph semantic extraction to comprehend entity linkages at a global level. However, most existing models rely heavily on local contextual information and struggle to process long-distance dependencies, thereby reducing recognition accuracy. Furthermore, Chinese kiwifruit texts often contain highly nested entities. This nesting and combination increase the complexity of grammatical and semantic relationships, making entity recognition more difficult. To address these challenges, a novel named entity recognition (NER) method, KIWI-Coord-Prune(kiwifruit-CoordKIWINER-PruneBi-LSTM) was proposed in this research, which incorporated dual-dimensional information processing and pruning techniques to improve recognition accuracy. [Methods] The proposed KIWI-Coord-Prune model consisted of a character embedding layer, a CoordKIWINER layer, a PruneBi-LSTM layer, a self-attention mechanism, and a CRF decoding layer, enabling effective entity recognition after processing input character vectors. The CoordKIWINER and PruneBi-LSTM modules were specifically designed to handle the dual-dimensional features in Chinese kiwifruit texts. The CoordKIWINER module applied adaptive average pooling in two directions on the input feature maps and utilized convolution operations to separate the extracted features into vertical and horizontal branches. The horizontal and vertical features were then independently extracted using the Criss-Cross Attention (CCNet) mechanism and Coordinate Attention (CoordAtt) mechanism, respectively. This module significantly enhanced the model's ability to capture cross-paragraph relationships and nested entity structures, thereby generating enriched character vectors containing more contextual information, which improved the overall representation capability and robustness of the model. The PruneBi-LSTM module was built upon the enhanced dual-dimensional vector representations and introduced a pruning strategy into Bi-LSTM to effectively reduce redundant parameters associated with background descriptions and irrelevant terms. This pruning mechanism not only enhanced computational efficiency while maintaining the dynamic sequence modeling capability of Bi-LSTM but also improved inference speed. Additionally, a dynamic feature extraction strategy was employed to reduce the computational complexity of vector sequences and further strengthen the learning capacity for key features, leading to improved recognition of complex entities in kiwifruit texts. Furthermore, the pruned weight matrices become sparser, significantly reducing memory consumption. This made the model more efficient in handling large-scale agricultural text-processing tasks, minimizing redundant information while achieving higher inference and training efficiency with fewer computational resources. [Results and Discussions] Experiments were conducted on the self-built KIWIPRO dataset and four public datasets: People's Daily, ClueNER, Boson, and ResumeNER. The proposed model was compared with five advanced NER models: LSTM, Bi-LSTM, LR-CNN, Softlexicon-LSTM, and KIWINER. The experimental results showed that KIWI-Coord-Prune achieved F1-Scores of 89.55%, 91.02%, 83.50%, 83.49%, and 95.81%, respectively, outperforming all baseline models. Furthermore, controlled variable experiments were conducted to compare and ablate the CoordKIWINER and PruneBi-LSTM modules across the five datasets, confirming their effectiveness and necessity. Additionally, the impact of different design choices was explored for the CoordKIWINER module, including direct fusion, optimized attention mechanism fusion, and network structure adjustment residual optimization. The experimental results demonstrated that the optimized attention mechanism fusion method yielded the best performance, which was ultimately adopted in the final model. These findings highlight the significance of properly designing attention mechanisms to extract dual-dimensional features for NER tasks. Compared to existing methods, the KIWI-Coord-Prune model effectively addressed the issue of underutilized dual-dimensional information in Chinese kiwifruit texts. It significantly improved entity recognition performance for both overall text structures and individual entity categories. Furthermore, the model exhibited a degree of generalization capability, making it applicable to downstream tasks such as knowledge graph construction and question-answering systems. [Conclusions] This study presents an novel NER approach for Chinese kiwifruit texts, which integrating dual-dimensional information extraction and pruning techniques to overcome challenges related to cross-paragraph dependencies and nested entity structures. The findings offer valuable insights for researchers working on domain-specific NER and contribute to the advancement of agriculture-focused natural language processing applications. However, two key limitations remain: 1) The balance between domain-specific optimization and cross-domain generalization requires further investigation, as the model's adaptability to non-agricultural texts has yet to be empirically validated; 2) the multilingual applicability of the model is currently limited, necessitating further expansion to accommodate multilingual scenarios. Future research should focus on two key directions: 1) Enhancing domain robustness and cross-lingual adaptability by incorporating diverse textual datasets and leveraging pre-trained multilingual models to improve generalization, and 2) Validating the model's performance in multilingual environments through transfer learning while refining linguistic adaptation strategies to further optimize recognition accuracy.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Research Advances and Prospect of Intelligent Monitoring Systems for the Physiological Indicators of Beef Cattle
    ZHANG Fan, ZHOU Mengting, XIONG Benhai, YANG Zhengang, LIU Minze, FENG Wenxiao, TANG Xiangfang
    Smart Agriculture    2024, 6 (4): 1-17.   DOI: 10.12133/j.smartag.SA202312001
    Abstract2789)   HTML133)    PDF(pc) (1471KB)(1809)       Save

    [Significance] The beef cattle industry plays a pivotal role in the development of China's agricultural economy and the enhancement of people's dietary structure. However, there exists a substantial disparity in feeding management practices and economic efficiency of beef cattle industry compared to developed countries. While the beef cattle industry in China is progressing towards intensive, modern, and large-scale development, it encounters challenges such as labor shortage and rising labor costs that seriously affect its healthy development. The determination of animal physiological indicators plays an important role in monitoring animal welfare and health status. Therefore, leveraging data collected from various sensors as well as technologies like machine learning, data mining, and modeling analysis enables automatic acquisition of meaningful information on beef cattle physiological indicators for intelligent management of beef cattle. In this paper, the intelligent monitoring technology of physiological indicators in beef cattle breeding process and its application value are systematically summarized, and the existing challenges and future prospects of intelligent beef cattle breeding process in China are prospected. [Progress] The methods of obtaining information on beef cattle physiological indicators include contact sensors worn on the body and non-contact sensors based on various image acquisitions. Monitoring the exercise behavior of beef cattle plays a crucial role in disease prevention, reproduction monitoring, and status assessment. The three-axis accelerometer sensor, which tracks the amount of time that beef cattle spend on lying, walking, and standing, is a widely used technique for tracking the movement behavior of beef cattle. Through machine vision analysis, individual recognition of beef cattle and identification of standing, lying down, and straddling movements can also be achieved, with the characteristics of non-contact, stress-free, low cost, and generating high data volume. Body temperature in beef cattle is associated with estrus, calving, and overall health. Sensors for monitoring body temperature include rumen temperature sensors and rectal temperature sensors, but there are issues with their inconvenience. Infrared temperature measurement technology can be utilized to detect beef cattle with abnormal temperatures by monitoring eye and ear root temperatures, although the accuracy of the results may be influenced by environmental temperature and monitoring distance, necessitating calibration. Heart rate and respiratory rate in beef cattle are linked to animal diseases, stress, and pest attacks. Monitoring heart rate can be accomplished through photoelectric volume pulse wave measurement and monitoring changes in arterial blood flow using infrared emitters and receivers. Respiratory rate monitoring can be achieved by identifying different nostril temperatures during inhalation and exhalation using thermal infrared imaging technology. The ruminating behavior of beef cattle is associated with health and feed nutrition. Currently, the primary tools used to detect rumination behavior are pressure sensors and three-axis accelerometer sensors positioned at various head positions. Rumen acidosis is a major disease in the rapid fattening process of beef cattle, however, due to limitations in battery life and electrode usage, real-time pH monitoring sensors placed in the rumen are still not widely utilized. Changes in animal physiology, growth, and health can result in alterations in specific components within body fluids. Therefore, monitoring body fluids or surrounding gases through biosensors can be employed to monitor the physiological status of beef cattle. By processing and analyzing the physiological information of beef cattle, indicators such as estrus, calving, feeding, drinking, health conditions, and stress levels can be monitored. This will contribute to the intelligent development of the beef cattle industry and enhance management efficiency. While there has been some progress made in developing technology for monitoring physiological indicators of beef cattle, there are still some challenges that need to be addressed. Contact sensors consume more energy which affects their lifespan. Various sensors are susceptible to environmental interference which affects measurement accuracy. Additionally, due to a wide variety of beef cattle breeds, it is difficult to establish a model database for monitoring physiological indicators under different feeding conditions, breeding stages, and breeds. Furthermore, the installation cost of various intelligent monitoring devices is relatively high, which also limits its utilization coverage. [Conclusion and Prospects] The application of intelligent monitoring technology for beef cattle physiological indicators is highly significance in enhancing the management level of beef cattle feeding. Intelligent monitoring systems and devices are utilized to acquire physiological behavior data, which are then analyzed using corresponding data models or classified through deep learning techniques to promptly monitor subtle changes in physiological indicators. This enables timely detection of sick, estrus, and calving cattle, facilitating prompt measures by production managers, reducing personnel workload, and improving efficiency. The future development of physiological indicators monitoring technologies in beef cattle primarily focuses on the following three aspects: (1) Enhancing the lifespan of contact sensors by reducing energy consumption, decreasing data transmission frequency, and improving battery life. (2) Integrating and analyzing various monitoring data from multiple perspectives to enhance the accuracy and utility value. (3) Strengthening research on non-contact, high-precision and automated analysis technologies to promote the precise and intelligent development within the beef cattle industry.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Grading Asparagus officinalis L. Using Improved YOLOv11
    YANG Qilang, YU Lu, LIANG Jiaping
    Smart Agriculture    2025, 7 (4): 84-94.   DOI: 10.12133/j.smartag.SA202501024
    Abstract2780)   HTML88)    PDF(pc) (1922KB)(198)       Save

    [Objective] Asparagus officinalis L. is a perennial plant with a long harvesting cycle and fast growth rate. The harvesting period of tender stems is relatively concentrated, and the shelf life of tender stems is very short. Therefore, the harvested asparagus needs to be classified according to the specifications of asparagus in a short time and then packaged and sold. However, at this stage, the classification of asparagus specifications basically depends on manual work, and it is difficult for asparagus of different specifications to rely on sensory grading, which requires a lot of money and labor. To save labor costs, an algorithm based on asparagus stem diameter classification was developed using deep learning and computer vision technology. YOLOv11 was selected as the baseline model and several improvements were made to propose a lightweight model for accurate grading of post-harvest asparagus. [Methods] Dataset was obtained by cell phone photography of post-harvest asparagus using fixed camera positions. In order to improve the generalization ability of the model, the training set was augmented with data by increasing contrast, mirroring, and adjusting brightness. The data-enhanced training set included a total of 2 160 images for training the model, and the test set and validation set included 90 and 540 images respectively for inference and validation of the model. In order to enhance the performance of the improved model, the following four improvements were made to the baseline model, respectively. First, the efficient channel attention (ECA) module was added to the twelfth layer of the YOLOv11 backbone network. The ECA enhanced asparagus stem diameter feature extraction by dynamically adjusting channel weights in the convolutional neural network and improved the recognition accuracy of the improved model. Second, the bi-directional feature pyramid network (BiFPN) module was integrated into the neck network. This module modified the original feature fusion method to automatically emphasize key asparagus features and improved the grading accuracy through multi-scale feature fusion. What's more, BiFPN dynamically adjusted the importance of each layer to reduce redundant computations. Next, the slim-neck module was applied to optimize the neck network. The slim-neck module consisted of GSConv and VoVGSCSP. The GSConv module replaced the traditional convolutional. And the VoVGSCSP module replaced the C2k3 module. This optimization reduced computational costs and model size while improving the recognition accuracy. Finally, the original YOLOv11 detection head was replaced with an EfficientDet Head. EfficientDet Head had the advantages of light weight and high accuracy. This head co-training with BiFPN to enhance the effect of multi-scale fusion and improve the performance of the model. [Results and Discussions] In order to verify the validity of the individual modules introduced in the improved YOLOv11 model and the superiority of the performance of the improved model, ablation experiments and comparison experiments were conducted respectively. The results of the comparison test between different attentional mechanisms added to the baseline model showed that the ECA module had better performance than other attentional mechanisms in the post-harvest asparagus grading task. The YOLOv11-ECA had higher recognition accuracy and smaller model size, so the selection of the ECA module had a certain degree of reliability. Ablation experiments demonstrated that the improved YOLOv11 achieved 96.8% precision (P), 96.9% recall (R), and 92.5% mean average precision (mAP), with 4.6 GFLOPs, 1.67 × 10⁶ parameters, and a 3.6 MB model size. The results of the asparagus grading test indicated that the localization frames of the improved model were more accurate and had a higher confidence level. Compared with the original YOLOv11 model, the improved YOLOv11 model increased the precision, recall, and mAP by 2.6, 1.4, and 2.2 percentage points, respectively. And the floating-point operation, parameter quantity, and model size were reduced by 1.7 G, 9.1 × 105, and 1.6 MB, respectively. Moreover, various improvements to the model could increase the accuracy of the model while ensuring that the model was light weight. In addition, the results of the comparative tests showed that the performance of the improved YOLOv11 model was better than those of SSD, YOLOv5s, YOLOv8n, YOLOv11, and YOLOv12. Overall, the improved YOLOv11 had the best overall performance, but still had some shortcomings. In terms of the real-time performance of the model, the inference speed of the improved model was not optimal, and the inference speed of the improved YOLOv11 was inferior to that of YOLOv5s and YOLOv8n. The inference speed of improved YOLOv11 and YOLOv11 evaluate using the aggregate test. The results of the Wilcoxon signed-rank test showed that the improved YOLOv11 had a significant improvement in inference speed compared to the original YOLOv11 model. [Conclusions] The improved YOLOv11 model demonstrated better recognition, lower parameters and floating-point operations, and smaller model size in the asparagus grading task. The improved YOLOv11 could provide a theoretical foundation for intelligent post-harvest asparagus grading. Deploying the improved YOLOv11 model on asparagus grading equipment enables fast and accurate grading of post-harvest asparagus.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Intelligent Decision-Making Method for Personalized Vegetable Crop Water and Fertilizer Management Based on Large Language Models
    WU Huarui, LI Jingchen, YANG Yusen
    Smart Agriculture    2025, 7 (1): 11-19.   DOI: 10.12133/j.smartag.SA202410007
    Abstract2775)   HTML148)    PDF(pc) (1181KB)(672)       Save

    [Objective] The current crop management faces the challenges of difficulty in capturing personalized needs and the lack of flexibility in the decision-making process. To address the limitations of conventional precision agriculture systems, optimize key aspects of agricultural production, including crop yield, labor efficiency, and water and fertilizer use, while ensure sustainability and adaptability to diverse farming conditions, in this research, an intelligent decision-making method was presents for personalized vegetable crop water and fertilizer management using large language model (LLM) by integrating user-specific preferences into decision-making processes through natural language interactions. [Methods] The method employed artificial intelligence techniques, combining natural language processing (NLP) and reinforcement learning (RL). Initially, LLM engaged users through structured dialogues to identify their unique preferences related to crop production goals, such as maximizing yield, reducing resource consumption, or balancing multiple objectives. These preferences were then modeled as quantifiable parameters and incorporated into a multi-objective optimization framework. To realize this framework, proximal policy optimization (PPO) was applied within a reinforcement learning environment to develop dynamic water and fertilizer management strategies. Training was conducted in the gym-DSSAT simulation platform, a system designed for agricultural decision support. The RL model iteratively learned optimal strategies by interacting with the simulation environment, adjusting to diverse conditions and balancing conflicting objectives effectively. To refine the estimation of user preferences, the study introduced a two-phase process comprising prompt engineering to guide user responses and adversarial fine-tuning for enhanced accuracy. These refinements ensured that user inputs were reliably transformed into structured decision-making criteria. Customized reward functions were developed for RL training to address specific agricultural goals. The reward functions account for crop yield, resource efficiency, and labor optimization, aligning with the identified user priorities. Through iterative training and simulation, the system dynamically adapted its decision-making strategies to varying environmental and operational conditions. [Results and Discussions] The experimental evaluation highlighted the system's capability to effectively personalize crop management strategies. Using simulations, the method demonstrated significant improvements over traditional approaches. The LLM-based model accurately captured user-specific preferences through structured natural language interactions, achieving reliable preference modeling and integration into the decision-making process. The system's adaptability was evident in its ability to respond dynamically to changes in user priorities and environmental conditions. For example, in scenarios emphasizing resource conservation, water and fertilizer use were significantly reduced without compromising crop health. Conversely, when users prioritized yield, the system optimized irrigation and fertilization schedules to enhance productivity. These results showcased the method's flexibility and its potential to balance competing objectives in complex agricultural settings. Additionally, the integration of user preferences into RL-based strategy development enabled the generation of tailored management plans. These plans aligned with diverse user goals, including maximizing productivity, minimizing resource consumption, and achieving sustainable farming practices. The system's multi-objective optimization capabilities allowed it to navigate trade-offs effectively, providing actionable insights for decision-making. The experimental validation also demonstrated the robustness of the PPO algorithm in training the RL model. The system's strategies were refined iteratively, resulting in consistent performance improvements across various scenarios. By leveraging LLM to capture nuanced user preferences and combining them with RL for adaptive decision-making, the method bridges the gap between generic precision agriculture solutions and personalized farming needs. [Conclusions] This study established a novel framework for intelligent decision-making in agriculture, integrating LLM with reinforcement learning to address personalized crop management challenges. By accurately capturing user-specific preferences and dynamically adapting to environmental and operational variables, the method offers a transformative approach to optimizing agricultural productivity and sustainability. Future work will focus on expanding the system's applicability to a wider range of crops and environmental contexts, enhancing the interpretability of its decision-making processes, and facilitating integration with real-world agricultural systems. These advancements aim to further refine the precision and impact of intelligent agricultural decision-making systems, supporting sustainable and efficient farming practices globally.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Real-Time Monitoring Method for Cow Rumination Behavior Based on Edge Computing and Improved MobileNet v3
    ZHANG Yu, LI Xiangting, SUN Yalin, XUE Aidi, ZHANG Yi, JIANG Hailong, SHEN Weizheng
    Smart Agriculture    2024, 6 (4): 29-41.   DOI: 10.12133/j.smartag.SA202405023
    Abstract2767)   HTML61)    PDF(pc) (1694KB)(526)       Save

    [Objective] Real-time monitoring of cow ruminant behavior is of paramount importance for promptly obtaining relevant information about cow health and predicting cow diseases. Currently, various strategies have been proposed for monitoring cow ruminant behavior, including video surveillance, sound recognition, and sensor monitoring methods. However, the application of edge device gives rise to the issue of inadequate real-time performance. To reduce the volume of data transmission and cloud computing workload while achieving real-time monitoring of dairy cow rumination behavior, a real-time monitoring method was proposed for cow ruminant behavior based on edge computing. [Methods] Autonomously designed edge devices were utilized to collect and process six-axis acceleration signals from cows in real-time. Based on these six-axis data, two distinct strategies, federated edge intelligence and split edge intelligence, were investigated for the real-time recognition of cow ruminant behavior. Focused on the real-time recognition method for cow ruminant behavior leveraging federated edge intelligence, the CA-MobileNet v3 network was proposed by enhancing the MobileNet v3 network with a collaborative attention mechanism. Additionally, a federated edge intelligence model was designed utilizing the CA-MobileNet v3 network and the FedAvg federated aggregation algorithm. In the study on split edge intelligence, a split edge intelligence model named MobileNet-LSTM was designed by integrating the MobileNet v3 network with a fusion collaborative attention mechanism and the Bi-LSTM network. [Results and Discussions] Through comparative experiments with MobileNet v3 and MobileNet-LSTM, the federated edge intelligence model based on CA-MobileNet v3 achieved an average Precision rate, Recall rate, F1-Score, Specificity, and Accuracy of 97.1%, 97.9%, 97.5%, 98.3%, and 98.2%, respectively, yielding the best recognition performance. [Conclusions] It is provided a real-time and effective method for monitoring cow ruminant behavior, and the proposed federated edge intelligence model can be applied in practical settings.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Agricultural Market Monitoring and Early Warning: An Integrated Forecasting Approach Based on Deep Learning
    XU Shiwei, LI Qianchuan, LUAN Rupeng, ZHUANG Jiayu, LIU Jiajia, XIONG Lu
    Smart Agriculture    2025, 7 (1): 57-69.   DOI: 10.12133/j.smartag.SA202411004
    Abstract2742)   HTML44)    PDF(pc) (1936KB)(1029)       Save

    [Significance] The fluctuations in the supply, consumption, and prices of agricultural products directly affect market monitoring and early warning systems. With the ongoing transformation of China's agricultural production methods and market system, advancements in data acquisition technologies have led to an explosive growth in agricultural data. However, the complexity of the data, the narrow applicability of existing models, and their limited adaptability still present significant challenges in monitoring and forecasting the interlinked dynamics of multiple agricultural products. The efficient and accurate forecasting of agricultural market trends is critical for timely policy interventions and disaster management, particularly in a country with a rapidly changing agricultural landscape like China. Consequently, there is a pressing need to develop deep learning models that are tailored to the unique characteristics of Chinese agricultural data. These models should enhance the monitoring and early warning capabilities of agricultural markets, thus enabling precise decision-making and effective emergency responses. [Methods] An integrated forecasting methodology was proposed based on deep learning techniques, leveraging multi-dimensional agricultural data resources from China. The research introduced several models tailored to different aspects of agricultural market forecasting. For production prediction, a generative adversarial network and residual network collaborative model (GAN-ResNet) was employed. For consumption forecasting, a variational autoencoder and ridge regression (VAE-Ridge) model was used, while price prediction was handled by an Adaptive-Transformer model. A key feature of the study was the adoption of an "offline computing and visualization separation" strategy within the Chinese agricultural monitoring and early warning system (CAMES). This strategy ensures that model training and inference are performed offline, with the results transmitted to the front-end system for visualization using lightweight tools such as ECharts. This approach balances computational complexity with the need for real-time early warnings, allowing for more efficient resource allocation and faster response times. The corn, tomato, and live pig market data used in this study covered production, consumption and price data from 1980 to 2023, providing comprehensive data support for model training. [Results and Discussions] The deep learning models proposed in this study significantly enhanced the forecasting accuracy for various agricultural products. For instance, the GAN-ResNet model, when used to predict maize yield at the county level, achieved a mean absolute percentage error (MAPE) of 6.58%. The VAE-Ridge model, applied to pig consumption forecasting, achieved a MAPE of 6.28%, while the Adaptive-Transformer model, used for tomato price prediction, results in a MAPE of 2.25%. These results highlighted the effectiveness of deep learning models in handling complex, nonlinear relationships inherent in agricultural data. Additionally, the models demonstrate notable robustness and adaptability when confronted with challenges such as sparse data, seasonal market fluctuations, and heterogeneous data sources. The GAN-ResNet model excels in capturing the nonlinear fluctuations in production data, particularly in response to external factors such as climate conditions. Its capacity to integrate data from diverse sources—including weather data and historical yield data—made it highly effective for production forecasting, especially in regions with varying climatic conditions. The VAE-Ridge model addressed the issue of data sparsity, particularly in the context of consumption data, and provided valuable insights into the underlying relationships between market demand, macroeconomic factors, and seasonal fluctuations. Finally, the Adaptive-Transformer model stand out in price prediction, with its ability to capture both short-term price fluctuations and long-term price trends, even under extreme market conditions. [Conclusions] This study presents a comprehensive deep learning-based forecasting approach for agricultural market monitoring and early warning. The integration of multiple models for production, consumption, and price prediction provides a systematic, effective, and scalable tool for supporting agricultural decision-making. The proposed models demonstrate excellent performance in handling the nonlinearities and seasonal fluctuations characteristic of agricultural markets. Furthermore, the models' ability to process and integrate heterogeneous data sources enhances their predictive power and makes them highly suitable for application in real-world agricultural monitoring systems. Future research will focus on optimizing model parameters, enhancing model adaptability, and expanding the system to incorporate additional agricultural products and more complex market conditions. These improvements will help increase the stability and practical applicability of the system, thus further enhancing its potential for real-time market monitoring and early warning capabilities.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Seedling Stage Corn Line Detection Method Based on Improved YOLOv8
    LI Hongbo, TIAN Xin, RUAN Zhiwen, LIU Shaowen, REN Weiqi, SU Zhongbin, GAO Rui, KONG Qingming
    Smart Agriculture    2024, 6 (6): 72-84.   DOI: 10.12133/j.smartag.SA202408008
    Abstract2730)   HTML119)    PDF(pc) (3458KB)(367)       Save

    [Objective] Crop line extraction is critical for improving the efficiency of autonomous agricultural machines in the field. However, traditional detection methods struggle to maintain high accuracy and efficiency under challenging conditions, such as strong light exposure and weed interference. The aims are to develop an effective crop line extraction method by combining YOLOv8-G, Affinity Propagation, and the Least Squares method to enhance detection accuracy and performance in complex field environments. [Methods] The proposed method employs machine vision techniques to address common field challenges. YOLOv8-G, an improved object detection algorithm that combines YOLOv8 and GhostNetV2 for lightweight, high-speed performance, was used to detect the central points of crops. These points were then clustered using the Affinity Propagation algorithm, followed by the application of the Least Squares method to extract the crop lines. Comparative tests were conducted to evaluate multiple backbone networks within the YOLOv8 framework, and ablation studies were performed to validate the enhancements made in YOLOv8-G. [Results and Discussions] The performance of the proposed method was compared with classical object detection and clustering algorithms. The YOLOv8-G algorithm achieved average precision (AP) values of 98.22%, 98.15%, and 97.32% for corn detection at 7, 14, and 21 days after emergence, respectively. Additionally, the crop line extraction accuracy across all stages was 96.52%. These results demonstrate the model's ability to maintain high detection accuracy despite challenging conditions in the field. [Conclusions] The proposed crop line extraction method effectively addresses field challenges such as lighting and weed interference, enabling rapid and accurate crop identification. This approach supports the automatic navigation of agricultural machinery, offering significant improvements in the precision and efficiency of field operations.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Graph Neural Networks for Knowledge Graph Construction: Research Progress, Agricultural Development Potential, and Future Directions
    YUAN Huan, FAN Beilei, YANG Chenxue, LI Xian
    Smart Agriculture    2025, 7 (2): 41-56.   DOI: 10.12133/j.smartag.SA202501007
    Abstract2722)   HTML69)    PDF(pc) (3048KB)(707)       Save

    [Significance] Graph neural networks (GNN) have emerged as a powerful tool in the realm of data analysis, particularly in knowledge graph construction. By capitalizing on the interaction and message passing among nodes in a graph, GNN can capture intricate relationships, making them widely applicable in various tasks, including knowledge representation, extraction, fusion, and inference. In the context of agricultural knowledge graph (AKG) development and knowledge service application, however, the agricultural domain presents unique challenges. These challenges encompass data with high multi-source heterogeneity, dynamic spatio-temporal changes in knowledge, complex relationships, and stringent requirements for interpretability. Given its strengths in graph structure data modeling, GNNs hold great promise in addressing these difficulties. For instance, in agricultural data, information from weather sensors, soil monitoring devices, and historical crop yield records varies significantly in format and type, and the ability of GNNs to handle such heterogeneity becomes crucial. [Progress] Firstly, this paper provides a comprehensive overview of the representation methods and fundamental concepts of GNNs was presented. The main structures, basic principles, characteristics, and application directions of five typical GNN models were discussed, including recursive graph neural networks (RGNN), convolutional graph neural networks (CGNN), graph auto-encoder networks (GAE), graph attention networks (GAT), and spatio-temporal graph neural networks(STGNN). Each of these models has distinct advantages in graph feature extraction, which are leveraged for tasks such as dynamic updates, knowledge completion, and complex relationship modeling in knowledge graphs. For example, STGNNs are particularly adept at handling the time-series and spatial data prevalent in agriculture, enabling more accurate prediction of crop growth patterns. Secondly, how GNN utilize graph structure information and message passing mechanisms to address issues in knowledge extraction related to multi-source heterogeneous data fusion and knowledge representation was elucidated. It can enhance the capabilities of entity recognition disambiguation and multi-modal data entity recognition. For example, when dealing with both textual descriptions of agricultural pests and corresponding image data, GNNs can effectively integrate these different modalities to accurately identify the pests. It also addresses the tasks of modeling complex dependencies and long-distance relationships or multi-modal relation extraction, achieving precise extraction of complex, missing information, or multi-modal events. Furthermore, GNNs possess unique characteristics, such as incorporating node or subgraph topology information, learning deep hidden associations between entities and relationships, generating low-dimensional representations encoding structure and semantics, and learning or fusing iterative non-linear neighborhood feature relationships on the graph structure, make it highly suitable for tasks like entity prediction, relation prediction, denoising, and anomaly information inference. These applications significantly enhance the construction quality of knowledge graphs. In an agricultural setting, this means more reliable predictions of disease outbreaks based on the relationships between environmental factors and crop health. Finally, in-depth analyses of typical cases of intelligent applications based on GNNs in agricultural knowledge question answering, recommendation systems, yield prediction, and pest monitoring and early warning are conducted. The potential of GNNs for constructing temporal agricultural knowledge models is explored, and its ability to adapt to the changing nature of agricultural data over time is highlighted. [Conclusions and Prospects] Research on constructing AKGs using GNNs is in its early stages. Future work should focus on key technologies like deep multi-source heterogeneous data fusion, knowledge graph evolution, scenario-based complex reasoning, and improving interpretability and generalization. GNN-based AKGs are expected to take on professional roles such as virtual field doctors and agricultural experts. Applications in pest control and planting decisions will be more precise, and intelligent tools like smart agricultural inputs and encyclopedia retrieval systems will be more comprehensive. By representing and predicting entities and relationships in agriculture, GNN-based AKGs can offer efficient knowledge services and intelligent solutions for sustainable agricultural development.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Defogging Remote Sensing Images Method Based on a Hybrid Attention-Based Generative Adversarial Network
    MA Liu, MAO Kebiao, GUO Zhonghua
    Smart Agriculture    2025, 7 (2): 172-182.   DOI: 10.12133/j.smartag.SA202410011
    Abstract2675)   HTML42)    PDF(pc) (1999KB)(327)       Save

    [Objective] Remote sensing images have become an important data source in fields such as surface observation, environmental monitoring, and natural disaster prediction. However, the acquisition of remote sensing images is often affected by weather phenomena such as fog and clouds, which reduces the image quality and poses challenges to subsequent analysis and processing tasks. In recent years, the introduction of attention mechanisms has enabled models to better capture and utilize important features in images, thereby significantly improving defogging performance. However, traditional channel attention mechanisms usually rely on global average pooling to summarize feature information. Although this method simplifies the complexity of calculations, it is not satisfactory when dealing with images with significant local changes and sensitivity to outliers. In addition, remote sensing images usually cover a wide area, and the diverse terrain makes the fog pattern more complex. Therefore, to address this issue, a hybrid attention-based generative adversarial network hybrid attention-based generative adversarial network (HAB-GAN) was proposed in this research, which integrates an efficient channel attention (ECA) module and a spatial attention block (SAB). [Method] By merging feature extraction from both channel and spatial dimensions, the model effectively enhanced its ability to identify and recover hazy areas in remote sensing images. In HAB-GAN, the ECA module captured local cross-channel interactions, addressing the shortcomings of traditional global averaged pooling in terms of insufficient sensitivity to local detail information. The ECA module used a global average pooling strategy without dimensionality reduction, automatically adapting to the characteristics of each channel without introducing extra parameters, thereby enhancing the inter-channel dependencies. ECA emploied a one-dimensional convolution operation, which used a learnable kernel size to adaptively determine the range of channel interactions. This design effectively avoided the over-smoothing of global features common in traditional pooling layers, allowing the model to more precisely extract local detailed while maintaining low computational complexity. The SAB module introduced a weighted mechanism on the spatial dimension by constructing a spatial attention map to enhance the model's ability to identify hazy areas in the image. This module extracted feature maps through convolution operations and applies attention weighting in both horizontal and vertical directions, highlighting regions with severe haze, allowing the model to better capture spatial information in the image, thereby enhancing dehazing performance. The generator of HAB-GAN combined residual network structures with hybrid attention modules. It first extracted initial features from input images through convolutional layers and then passed these features through several residual blocks. The residual blocks effectively mitigated the vanishing gradient problem in deep neural networks and maintain feature consistency and continuity by passing input features directly to deeper network layers through skip connections. Each residual block incorporated ECA and SAB modules, enabling precise feature learning through weighted processing in both channel and spatial dimensions. After extracting effective features, the generator generated dehazed images through convolution operations. The discriminator adopted a standard convolutional neural network architecture, focusing on extracting local detail features from the images generated by the generator. It consisted of multiple convolutional layers, batch normalization layers, and Leaky ReLU activation functions. By extracting local features layer by layer and down-sampling, the discriminator progressively reduced the spatial resolution of the images, evaluating their realism at both global and local levels. The generator and discriminator were jointly optimized through adversarial training, where the generator aimed to produce increasingly realistic dehazed images, and the discriminator continually improved its ability to distinguish between real and generated images, thereby enhancing the learning effectiveness and image quality of the generator. [Results and Discussions] To validate the effectiveness of HAB-GAN, experiments were conducted on the remote sensing image scene classification 45 (RESISC45) dataset. The experimental results demonstrated that compared to existing dehazing models, HAB-GAN excels in key evaluation metrics such as peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). Specifically, compared to SpA GAN, HAB-GAN improved PSNR by 2.642 5 dB and SSIM by 0.012 2; Compared to HyA-GAN, PSNR improved by 1.138 dB and SSIM by 0.001 9. Additionally, to assess the generalization capability of HAB-GAN, further experiments were conducted on the RICE2 dataset to verify its performance in cloud removal tasks. The results showed that HAB-GAN also performs exceptionally well in cloud removal tasks, with PSNR improving by 3.593 2 dB and SSIM improving by 0.040 2. Compared to HyA-GAN, PSNR and SSIM increased by 1.854 dB and 0.012 4, respectively. To further explored the impact of different modules on the model's performance, ablation experiments were designed, gradually removing the ECA module, the SAB module, and the entire hybrid attention module. The experimental results showed that removing the ECA module reduced PSNR by 2.642 5 dB and SSIM by 0.012 2; Removing the SAB module reduced PSNR by 2.955 dB and SSIM by 0.008 7, and removing the entire hybrid attention module reduced PSNR and SSIM by 3.866 1 dB and 0.033 4, respectively. [Conclusions] The proposed HAB-GAN model not only performs excellently in dehazing and beclouding tasks but also significantly enhances the clarity and detail recovery of dehazed images through the synergistic effect of the ECA module and the SAB module. Additionally, its strong performance across different remote sensing datasets further validates its effectiveness and generalization ability, showcasing broad application potential particularly in fields such as agriculture, environmental monitoring, and disaster prediction, where high-quality remote sensing data is crucial. HAB-GAN is poised to become a valuable tool for improving data reliability and supporting more accurate decision-making and analysis.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Grain Production Big Data Platform: Progress and Prospects
    YANG Guijun, ZHAO Chunjiang, YANG Xiaodong, YANG Hao, HU Haitang, LONG Huiling, QIU Zhengjun, LI Xian, JIANG Chongya, SUN Liang, CHEN Lei, ZHOU Qingbo, HAO Xingyao, GUO Wei, WANG Pei, GAO Meiling
    Smart Agriculture    2025, 7 (2): 1-12.   DOI: 10.12133/j.smartag.SA202409014
    Abstract2674)   HTML229)    PDF(pc) (1811KB)(2390)       Save

    [Significance] The explosive development of agricultural big data has accelerated agricultural production into a new era of digitalization and intelligentialize. Agricultural big data is the core element to promote agricultural modernization and the foundation of intelligent agriculture. As a new productive forces, big data enhances the comprehensive intelligent management decision-making during the whole process of grain production. But it faces the problems such as the indistinct management mechanism of grain production big data resources, the lack of the full-chain decision-making algorithm system and big data platform for the whole process and full elements of grain production. [Progress] Grain production big data platform is a comprehensive service platform that uses modern information technologies such as big data, Internet of Things (IoT), remote sensing and cloud computing to provide intelligent decision-making support for the whole process of grain production based on intelligent algorithms for data collection, processing, analysis and monitoring related to grain production. In this paper, the progress and challenges in grain production big data, monitoring and decision-making algorithms are reviewed, as well as big data platforms in China and worldwide. With the development of the IoT and high-resolution multi-modal remote sensing technology, the massive agricultural big data generated by the "Space-Air-Ground" Integrated Agricultural Monitoring System, has laid an important foundation for smart agriculture and promoted the shift of smart agriculture from model-driven to data-driven. However, there are still some issues in field management decision-making, such as the requirements for high spatio-temporal resolution and timeliness of the information are difficult to meet, and the algorithm migration and localization methods based on big data need to be studied. In addition, the agricultural machinery operation and spatio-temporal scheduling algorithm based on remote sensing and IoT monitoring information to determine the appropriate operation time window and operation prescription, needs to be further developed, especially the cross-regional scheduling algorithm of agricultural machinery for summer harvest in China. Aiming to address the issues of non-bi-connected monitoring and decision-making algorithms in grain production, as well as the insufficient integration of agricultural machinery and information perception, a framework for the grain production big data intelligent platform based on digital twins is proposed. The platform leverages multi-source heterogeneous grain production big data and integrates a full-chain suit of standardized algorithms, including data acquisition, information extraction, knowledge map construction, intelligent decision-making, full-chain collaboration of agricultural machinery operations. It covers the typical application scenarios such as irrigation, fertilization, pests and disease management, emergency response to drought and flood disaster, all enabled by digital twins technology. [Conclusions and Prospects] The suggestions and trends for development of grain production big data platform are summarized in three aspects: (1) Creating an open, symbiotic grain production big data platform, with core characteristics such as open interface for crop and environmental sensors, maturity grading and a cloud-native packaging mechanism for core algorithms, highly efficient response to data and decision services; (2) Focusing on the typical application scenarios of grain production, take the exploration of technology integration and bi-directional connectivity as the base, and the intelligent service as the soul of the development path for the big data platform research; (3) The data-algorithm-service self-organizing regulation mechanism, the integration of decision-making information with the intelligent equipment operation, and the standardized, compatible and open service capabilities, can form the new quality productivity to ensure food safety, and green efficiency grain production.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Low-Altitude Technology Empowering Smart Agriculture: Technical System, Application Scenarios, and Challenge Recommendations
    LAN Yubin, WANG Chaofeng, SUN Heguang, CHEN Shengde, WANG Guobin, DENG Xiaoling, WANG Yuanjie
    Smart Agriculture    2025, 7 (6): 18-34.   DOI: 10.12133/j.smartag.SA202506025
    Abstract2654)   HTML121)    PDF(pc) (2746KB)(225)       Save

    [Significance] Agricultural low altitude agricultural technology, with unmanned aerial vehicles (UAVs) as its primary platform, integrates 5G communication, artificial intelligence, and the Internet of Things to support data acquisition, analysis, and decision making throughout agricultural production. These advances are driving a transition from traditional experience based management toward a model in which data serve as the primary basis for decisions. As low altitude technology continues to advance in communication capacity, payload performance, and onboard processing, agricultural operations are undergoing profound changes. UAVs once used mainly for crop protection spraying have gradually evolved into multifunctional platforms capable of data collection, crop growth monitoring, image interpretation, precise input application, and operational assistance. Supported by a three dimensional integrated framework, which includes vertical integration, horizontal expansion, and spatio-temporal coordination, low altitude systems are reshaping field management structures, operational modes, and decision making processes. This transformation is accelerating the digitalization, networking, and intelligent upgrading of agriculture. The aim is to provide theoretical guidance and technical pathways for the broader application of low altitude technology in agriculture and to support the exploration of sustainable development models and industrial layouts for the low altitude agricultural economy. [Progress] The core contribution of low altitude technology to smart agriculture lies in establishing a complete sensing, decision, execution, and feedback cycle and implementing a four level structure comprising infrastructure, core technologies, application support, and scenario deployment. The infrastructure layer relies on 4G/5G networks, RTK high precision positioning, and ground based sensor systems. Multi source data are acquired through UAV mounted multi-spectral and thermal sensors working in coordination with ground monitoring devices to capture information on crop conditions and field environments. The core technology layer utilizes edge computing, cloud platforms, and analytical models to support growth assessment, pest and disease warnings, and other forms of analysis. At the application layer, UAVs operate in collaboration with ground equipment to implement precise crop protection, seeding, and irrigation, while also extending to field monitoring and agricultural logistics. This paper focuses on agricultural low altitude agricultural technology, summarizes its mechanisms and systematically reviews the associated technical system from the perspectives of operational equipment, low altitude remote sensing and recognition, data processing and analysis, and precision operation and supervision. It further examines key functions enabling agricultural intelligence. Drawing on recent research and representative cases, the paper discusses practical applications in depth. In smart orchards, for example, the South China Agricultural University Smart Patrol system combined with the Lichi Jun model can deliver early pest and disease warnings two to three weeks before outbreak and support yield estimation. In ecological unmanned farms, integrated sky, air, and ground monitoring enables autonomous operation across plowing, planting, management, and harvesting. In production operations, agricultural UAVs have accumulated over 7.5 billion mu (500 million hectare) times of service area globally, covering nearly one third of China's cultivated land area, saving approximately 210 million tons of water, and reducing carbon emissions by approximately 25.72 million tons. In logistics scenarios, transport assisted by UAVs in mountainous orchards improves efficiency more than tenfold while keeping damage rates below three percent. [Conclusions and Prospects] Sensors remain fundamental tools for capturing agricultural information and reflecting crop growth conditions. Developing highly generalizable technical modules helps lower application barriers and improve operational efficiency, while fusing multi scale data partially compensates for the limitations of single source information. Despite rapid progress, the low altitude agricultural economy still faces challenges including technological maturity, application cost, standardization, industrial integration, and workforce development. Based on an analysis of these challenges, this paper proposes building a three dimensional integrated technology framework featuring vertical integration, horizontal expansion, and spatio-temporal coordination; promoting the improvement and unification of technical standards; constructing an integrated industry ecosystem spanning research, manufacturing, application, and service; and strengthening policy support, industry norms, and talent training systems. These measures are expected to accelerate the emergence of new drivers of growth in the low altitude agricultural economy.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Automatic Navigation and Spraying Robot in Sheep Farm
    FAN Mingshuo, ZHOU Ping, LI Miao, LI Hualong, LIU Xianwang, MA Zhirun
    Smart Agriculture    2024, 6 (4): 103-115.   DOI: 10.12133/j.smartag.SA202312016
    Abstract2638)   HTML42)    PDF(pc) (2160KB)(976)       Save

    [Objective] Manual disinfection in large-scale sheep farm is laborious, time-consuming, and often results in incomplete coverage and inadequate disinfection. With the rapid development of the application of artificial intelligence and automation technology, the automatic navigation and spraying robot for livestock and poultry breeding, has become a research hotspot. To maintain shed hygiene and ensure sheep health, an automatic navigation and spraying robot was proposed for sheep sheds. [Methods] The automatic navigation and spraying robot was designed with a focus on three aspects: hardware, semantic segmentation model, and control algorithm. In terms of hardware, it consisted of a tracked chassis, cameras, and a collapsible spraying device. For the semantic segmentation model, enhancements were made to the lightweight semantic segmentation model ENet, including the addition of residual structures to prevent network degradation and the incorporation of a squeeze-and-excitation network (SENet) attention mechanism in the initialization module. This helped to capture global features when feature map resolution was high, addressing precision issues. The original 6-layer ENet network was reduced to 5 layers to balance the encoder and decoder. Drawing inspiration from dilated spatial pyramid pooling, a context convolution module (CCM) was introduced to improve scene understanding. A criss-cross attention (CCA) mechanism was adapted to acquire context global features of different scales without cascading, reducing information loss. This led to the development of a double attention enet (DAENet) semantic segmentation model was proposed to achieve real-time and accurate segmentation of sheep shed surfaces. Regarding control algorithms, a method was devised to address the robot's difficulty in controlling its direction at junctions. Lane recognition and lane center point identification algorithms were proposed to identify and mark navigation points during the robot's movement outside the sheep shed by simulating real roads. Two cameras were employed, and a camera switching algorithm was developed to enable seamless switching between them while also controlling the spraying device. Additionally, a novel offset and velocity calculation algorithm was proposed to control the speeds of the robot's left and right tracks, enabling control over the robot's movement, stopping, and turning. [Results and Discussions] The DAENet model achieved a mean intersection over union (mIoU) of 0.945 3 in image segmentation tasks, meeting the required segmentation accuracy. During testing of the camera switching algorithm, it was observed that the time taken for the complete transition from camera to spraying device action does not exceed 15 seconds when road conditions changed. Testing of the center point and offset calculation algorithm revealed that, when processing multiple frames of video streams, the algorithm averages 0.04 to 0.055 per frame, achieving frame rates of 20 to 24 frames per second, meeting real-time operational requirements. In field experiments conducted in sheep farm, the robot successfully completed automatic navigation and spraying tasks in two sheds without colliding with roadside troughs. The deviation from the road and lane centerlines did not exceed 0.3 meters. Operating at a travel speed of 0.2 m/s, the liquid in the medicine tank was adequate to complete the spraying tasks for two sheds. Additionally, the time taken for the complete transition from camera to spraying device action did not exceed 15 when road conditions changed. The robot maintained an average frame rate of 22.4 frames per second during operation, meeting the experimental requirements for accurate and real-time information processing. Observation indicated that the spraying coverage rate of the robot exceeds 90%, meeting the experimental coverage requirements. [Conclusions] The proposed automatic navigation and spraying robot, based on the DAENet semantic segmentation model and center point recognition algorithm, combined with hardware design and control algorithms, achieves comprehensive disinfection within sheep sheds while ensuring safety and real-time operation.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Extraction Method of Maize Plant Skeleton and Phenotypic Parameters Based on Improved YOLOv11-Pose
    NIU Ziang, QIU Zhengjun
    Smart Agriculture    2025, 7 (2): 95-105.   DOI: 10.12133/j.smartag.SA202501001
    Abstract2633)   HTML81)    PDF(pc) (2260KB)(592)       Save

    [Objective] Accurate extraction of maize plant skeletons and phenotypic parameters is fundamental for acquisition of plant growth data, morphological analysis, and agricultural management. However, leaf occlusion and complex backgrounds in dense planting environments pose significant challenges to skeleton and parameters extraction. A maize plant skeleton and phenotypic parameters extraction method suitable for dense field environments was proposed in this research to enhance the extraction precision and efficiency, and provide technical support for maize growth data acquisition. [Methods] An improved YOLOv11-Pose multi-object keypoint detection network was introduced, a top-down detection framework was adopted to detect maize plant keypoints and reconstruct skeletons. A uniform sampling algorithm was used to design a keypoint representation method tailored for maize skeletons and optimize task adaptability. Additionally, a single-head self-attention mechanism and a convolutional block attention module were incorporated to guide the model's focus on occluded regions and connected parts, thereby improve its adaptability to complex scenarios. [Results and Discussion] In dense field maize environments, experimental results showed that when the number of uniformly sampled keypoints was set to 10, the Fréchet distance reached its minimum value of 79.008, effectively preserving the original skeleton's morphological features while avoiding the negative impact of redundant points. Under this configuration, the improved YOLOv11-Pose model achieved a bounding box detection precision of 0.717. The keypoint detection mAP50 and mAP50-95 improved by 10.9% and 23.8%, respectively, compared to the original model, with an inference time of 52.7 ms per image. The results demonstrated the model's superior performance and low computational cost in complex field environments, particularly in keypoint detection tasks with enhanced accuracy and robustness. The study further combined the results of skeleton extraction and spatial geometric information to achieve a plant height measurement mean average error (MAE) of 2.435 cm, the detection error of leaf age was less than one growth period, and the measurement error of leaf length was 3.482%, verifying the effectiveness and practicability of the proposed method in the application of phenotypic parameter measurement. [Conclusion] The proposed improved YOLOv11-Pose model can efficiently and accurately extract maize plant skeletons, meeting the demands of ground-based maize growth data acquisition. The research could provide technical support for phenotypic data acquisition in grain production and precision agricultural management.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Cow Hoof Slippage Detecting Method Based on Enhanced DeepLabCut Model
    NIAN Yue, ZHAO Kaixuan, JI Jiangtao
    Smart Agriculture    2024, 6 (5): 153-163.   DOI: 10.12133/j.smartag.SA202406014
    Abstract2591)   HTML30)    PDF(pc) (1765KB)(1182)       Save

    [Objective] The phenomenon of hoof slipping occurs during the walking process of cows, which indicates the deterioration of the farming environment and a decline in the cows' locomotor function. Slippery grounds can lead to injuries in cows, resulting in unnecessary economic losses for farmers. To achieve automatically recognizing and detecting slippery hoof postures during walking, the study focuses on the localization and analysis of key body points of cows based on deep learning methods. Motion curves of the key body points were analyzed, and features were extracted. The effectiveness of the extracted features was verified using a decision tree classification algorithm, with the aim of achieving automatic detection of slippery hoof postures in cows. [Method] An improved localization method for the key body points of cows, specifically the head and four hooves, was proposed based on the DeepLabCut model. Ten networks, including ResNet series, MobileNet-V2 series, and EfficientNet series, were selected to respectively replace the backbone network structure of DeepLabCut for model training. The root mean square error(RMSE), model size, FPS, and other indicators were chosen, and after comprehensive consideration, the optimal backbone network structure was selected as the pre-improved network. A network structure that fused the convolutional block attention module (CBAM) attention mechanism with ResNet-50 was proposed. A lightweight attention module, CBAM, was introduced to improve the ResNet-50 network structure. To enhance the model's generalization ability and robustness, the CBAM attention mechanism was embedded into the first convolution layer and the last convolution layer of the ResNet-50 network structure. Videos of cows with slippery hooves walking in profile were predicted for key body points using the improved DeepLabCut model, and the obtained key point coordinates were used to plot the motion curves of the cows' key body points. Based on the motion curves of the cows' key body points, the feature parameter Feature1 for detecting slippery hooves was extracted, which represented the local peak values of the derivative of the motion curves of the cows' four hooves. The feature parameter Feature2 for predicting slippery hoof distances was extracted, specifically the minimum local peak points of the derivative curve of the hooves, along with the local minimum points to the left and right of these peaks. The effectiveness of the extracted Feature1 feature parameters was verified using a decision tree classification model. Slippery hoof feature parameters Feature1 for each hoof were extracted, and the standard deviation of Feature1 was calculated for each hoof. Ultimately, a set of four standard deviations for each cow was extracted as input parameters for the classification model. The classification performance was evaluated using four common objective metrics, including accuracy, precision, recall, and F1-Score. The prediction accuracy for slippery hoof distances was assessed using RMSE as the evaluation metric. [Results and Discussion] After all ten models reached convergence, the loss values ranked from smallest to largest were found in the EfficientNet series, ResNet series, and MobileNet-V2 series, respectively. Among them, ResNet-50 exhibited the best localization accuracy in both the training set and validation set, with RMSE values of only 2.69 pixels and 3.31 pixels, respectively. The MobileNet series had the fastest inference speed, reaching 48 f/s, while the inference speeds of the ResNet series and MobileNet series were comparable, with ResNet series performing slightly better than MobileNet series. Considering the above factors, ResNet-50 was ultimately selected as the backbone network for further improvements on DeepLabCut. Compared to the original ResNet-50 network, the ResNet-50 network improved by integrating the CBAM module showed a significant enhancement in localization accuracy. The accuracy of the improved network increased by 3.7% in the training set and by 9.7% in the validation set. The RMSE between the predicted body key points and manually labeled points was only 2.99 pixels, with localization results for the right hind hoof, right front hoof, left hind hoof, left front hoof, and head improved by 12.1%, 44.9%, 0.04%, 48.2%, and 39.7%, respectively. To validate the advancement of the improved model, a comparison was made with the mainstream key point localization model, YOLOv8s-pose, which showed that the RMSE was reduced by 1.06 pixels compared to YOLOv8s-pose. This indicated that the ResNet-50 network integrated with the CBAM attention mechanism possessed superior localization accuracy. In the verification of the cow slippery hoof detection classification model, a 10-fold cross-validation was conducted to evaluate the performance of the cow slippery hoof classification model, resulting in average values of accuracy, precision, recall, and F1-Score at 90.42%, 0.943, 0.949, and 0.941, respectively. The error in the calculated slippery hoof distance of the cows, using the slippery hoof distance feature parameter Feature2, compared to the manually calibrated slippery hoof distance was found to be 1.363 pixels. [Conclusion] The ResNet-50 network model improved by integrating the CBAM module showed a high accuracy in the localization of key body points of cows. The cow slippery hoof judgment model and the cow slippery hoof distance prediction model, based on the extracted feature parameters for slippery hoof judgment and slippery hoof distance detection, both exhibited small errors when compared to manual detection results. This indicated that the proposed enhanced deeplabcut model obtained good accuracy and could provide technical support for the automatic detection of slippery hooves in cows.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    MSH-YOLOv8: Mushroom Small Object Detection Method with Scale Reconstruction and Fusion
    YE Dapeng, JING Jun, ZHANG Zhide, LI Huihuang, WU Haoyu, XIE Limin
    Smart Agriculture    2024, 6 (5): 139-152.   DOI: 10.12133/j.smartag.SA202404002
    Abstract2552)   HTML90)    PDF(pc) (2660KB)(3890)       Save

    [Objective] Traditional object detection algorithms applied in the agricultural field, such as those used for crop growth monitoring and harvesting, often suffer from insufficient accuracy. This is particularly problematic for small crops like mushrooms, where recognition and detection are more challenging. The introduction of small object detection technology promises to address these issues, potentially enhancing the precision, efficiency, and economic benefits of agricultural production management. However, achieving high accuracy in small object detection has remained a significant challenge, especially when dealing with varying image sizes and target scales. Although the YOLO series models excel in speed and large object detection, they still have shortcomings in small object detection. To address the issue of maintaining high accuracy amid changes in image size and target scale, a novel detection model, Multi-Strategy Handling YOLOv8 (MSH-YOLOv8), was proposed. [Methods] The proposed MSH-YOLOv8 model builds upon YOLOv8 by incorporating several key enhancements aimed at improving sensitivity to small-scale targets and overall detection performance. Firstly, an additional detection head was added to increase the model's sensitivity to small objects. To address computational redundancy and improve feature extraction, the Swin Transformer detection structure was introduced into the input module of the head network, creating what was termed the "Swin Head (SH)". Moreover, the model integrated the C2f_Deformable convolutionv4 (C2f_DCNv4) structure, which included deformable convolutions, and the Swin Transformer encoder structure, termed "Swinstage", to reconstruct the YOLOv8 backbone network. This optimization enhanced feature propagation and extraction capabilities, increasing the network's ability to handle targets with significant scale variations. Additionally, the normalization-based attention module (NAM) was employed to improve performance without compromising detection speed or computational complexity. To further enhance training efficacy and convergence speed, the original loss function CIoU was replaced with wise-intersection over union (WIoU) Loss. Furthermore, experiments were conducted using mushrooms as the research subject on the open Fungi dataset. Approximately 200 images with resolution sizes around 600×800 were selected as the main research material, along with 50 images each with resolution sizes around 200×400 and 1 000×1 200 to ensure representativeness and generalization of image sizes. During the data augmentation phase, a generative adversarial network (GAN) was utilized for resolution reconstruction of low-resolution images, thereby preserving semantic quality as much as possible. In the post-processing phase, dynamic resolution training, multi-scale testing, soft non-maximum suppression (Soft-NMS), and weighted boxes fusion (WBF) were applied to enhance the model's small object detection capabilities under varying scales. [Results and Discussions] The improved MSH-YOLOv8 achieved an average precision at 50% (AP50) intersection over union of 98.49% and an AP@50-95 of 75.29%, with the small object detection metric APs reaching 39.73%. Compared to mainstream models like YOLOv8, these metrics showed improvements of 2.34%, 4.06% and 8.55%, respectively. When compared to the advanced TPH-YOLOv5 model, the improvements were 2.14%, 2.76% and 6.89%, respectively. The ensemble model, MSH-YOLOv8-ensemble, showed even more significant improvements, with AP50 and APs reaching 99.14% and 40.59%, respectively, an increase of 4.06% and 8.55% over YOLOv8. These results indicate the robustness and enhanced performance of the MSH-YOLOv8 model, particularly in detecting small objects under varying conditions. Further application of this methodology on the Alibaba Cloud Tianchi databases "Tomato Detection" and "Apple Detection" yielded MSH-YOLOv8-t and MSH-YOLOv8-a models (collectively referred to as MSH-YOLOv8). Visual comparison of detection results demonstrated that MSH-YOLOv8 significantly improved the recognition of dense and blurry small-scale tomatoes and apples. This indicated that the MSH-YOLOv8 method possesses strong cross-dataset generalization capability and effectively recognizes small-scale targets. In addition to quantitative improvements, qualitative assessments showed that the MSH-YOLOv8 model could handle complex scenarios involving occlusions, varying lighting conditions, and different growth stages of the crops. This demonstrates the practical applicability of the model in real-world agricultural settings, where such challenges are common. [Conclusions] The MSH-YOLOv8 improvement method proposed in this study effectively enhances the detection accuracy of small mushroom targets under varying image sizes and target scales. This approach leverages multiple strategies to optimize both the architecture and the training process, resulting in a robust model capable of high-precision small object detection. The methodology's application to other datasets, such as those for tomato and apple detection, further underscores its generalizability and potential for broader use in agricultural monitoring and management tasks.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    A Rapid Detection Method for Wheat Seedling Leaf Number in Complex Field Scenarios Based on Improved YOLOv8
    HOU Yiting, RAO Yuan, SONG He, NIE Zhenjun, WANG Tan, HE Haoxu
    Smart Agriculture    2024, 6 (4): 128-137.   DOI: 10.12133/j.smartag.SA202403019
    Abstract2549)   HTML125)    PDF(pc) (2913KB)(1328)       Save

    [Objective] The enumeration of wheat leaves is an essential indicator for evaluating the vegetative state of wheat and predicting its yield potential. Currently, the process of wheat leaf counting in field settings is predominantly manual, characterized by being both time-consuming and labor-intensive. Despite advancements, the efficiency and accuracy of existing automated detection and counting methodologies have yet to satisfy the stringent demands of practical agricultural applications. This study aims to develop a method for the rapid quantification of wheat leaves to refine the precision of wheat leaf tip detection. [Methods] To enhance the accuracy of wheat leaf detection, firstly, an image dataset of wheat leaves across various developmental stages—seedling, tillering, and overwintering—under two distinct lighting conditions and using visible light images sourced from both mobile devices and field camera equipmen, was constructed. Considering the robust feature extraction and multi-scale feature fusion capabilities of YOLOv8 network, the foundational architecture of the proposed model was based on the YOLOv8, to which a coordinate attention mechanism has been integrated. To expedite the model's convergence, the loss functions were optimized. Furthermore, a dedicated small object detection layer was introduced to refine the recognition of wheat leaf tips, which were typically difficult for conventional models to discern due to their small size and resemblance to background elements. This deep learning network was named as YOLOv8-CSD, tailored for the recognition of small targets such as wheat leaf tips, ascertains the leaf count by detecting the number of leaf tips present within the image. A comparative analysis was conducted on the YOLOv8-CSD model in comparison with the original YOLOv8 and six other prominent network architectures, including Faster R-CNN, Mask R-CNN, YOLOv7, and SSD, within a uniform training framework, to evaluate the model's effectiveness. In parallel, the performance of both the original and YOLOv8-CSD models was assessed under challenging conditions, such as the presence of weeds, occlusions, and fluctuating lighting, to emulate complex real-world scenarios. Ultimately, the YOLOv8-CSD model was deployed for wheat leaf number detection in intricate field conditions to confirm its practical applicability and generalization potential. [Results and Discussions] The research presented a methodology that achieved a recognition precision of 91.6% and an mAP0.5 of 85.1% for wheat leaf tips, indicative of its robust detection capabilities. This method exceled in adaptability within complex field environments, featuring an autonomous adjustment mechanism for different lighting conditions, which significantly enhanced the model's robustness. The minimal rate of missed detections in wheat seedlings' leaf counting underscored the method's suitability for wheat leaf tip recognition in intricate field scenarios, consequently elevating the precision of wheat leaf number detection. The sophisticated algorithm embedded within this model had demonstrated a heightened capacity to discern and focus on the unique features of wheat leaf tips during the detection process. This capability was essential for overcoming challenges such as small target sizes, similar background textures, and the intricacies of feature extraction. The model's consistent performance across diverse conditions, including scenarios with weeds, occlusions, and fluctuating lighting, further substantiated its robustness and its readiness for real-world application. [Conclusions] This research offers a valuable reference for accurately detecting wheat leaf numbers in intricate field conditions, as well as robust technical support for the comprehensive and high-quality assessment of wheat growth.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Method for Calculating Semantic Similarity of Short Agricultural Texts Based on Transfer Learning
    JIN Ning, GUO Yufeng, HAN Xiaodong, MIAO Yisheng, WU Huarui
    Smart Agriculture    2025, 7 (1): 33-43.   DOI: 10.12133/j.smartag.SA202410026
    Abstract2534)   HTML23)    PDF(pc) (1239KB)(661)       Save

    [Objective] Intelligent services of agricultural knowledge have emerged as a current hot research domain, serving as a significant support for the construction of smart agriculture. The platform "China Agricultural Technology Extension" provides users with efficient and convenient agricultural information consultation services via mobile terminals, and has accumulated a vast amount of Q&A data. These data are characterized by a huge volume of information, rapid update and iteration, and a high degree of redundancy, resulting in the platform encountering issues such as frequent repetitive questions, low timeliness of problem responses, and inaccurate information retrieval. There is an urgent requirement for a high-quality text semantic similarity calculation approach to confront these challenges and effectively enhance the information service efficiency and intelligent level of the platform. In view of the problems of incomplete feature extraction and lack of short agro-text annotation data sets in existing text semantic similarity calculation models, a semantic similarity calculation model for short agro-text, namely CWPT-SBERT, based on transfer learning and BERT pre-training model, was proposed. [Methods] CWPT-SBERT was based on Siamese architecture with identical left and right sides and shared parameters, which had the advantages of low structural complexity and high training efficiency. This network architecture effectively reduced the consumption of computational resources by sharing parameters and ensures that input texts were compared in the same feature space. CWPT-SBERT consisted of four main parts: Semantic enhancement layer, embedding layer, pooling layer, and similarity measurement layer. The CWPT method based on the word segmentation unit was proposed in the semantic enhancement layer to further divide Chinese characters into more fine-grained sub-units maximizing the semantic features in short Chinese text and effectively enhancing the model's understanding of complex Chinese vocabulary and character structures. In the embedding layer, a transfer learning strategy was used to extract features from agricultural short texts based on SBERT. It captured the semantic features of Chinese text in the general domain, and then generated a more suitable semantic feature vector representation after fine-tuning. Transfer learning methods to train models on large-scale general-purposed domain annotation datasets solve the problem of limited short agro-text annotation datasets and high semantic sparsity. The pooling layer used the average pooling strategy to map the high-dimensional semantic vector of Chinese short text to a low-dimensional vector space. The similarity measurement layer used the cosine similarity calculation method to measure the similarity between the semantic feature vector representations of the two output short texts, and the computed similarity degree was finally input into the loss function to guide model training, optimize model parameters, and improve the accuracy of similarity calculation. [Results and Discussions] For the task of calculating semantic similarity in agricultural short texts, on a dataset containing 19 968 pairs of short ago-texts, the CWPT-SBERT model achieved an accuracy rate of 97.18% and 96.93%, a recall rate of 97.14%, and an F1-Score value of 97.04%, which are higher than 12 models such as TextCNN_Attention, MaLSTM and SBERT. By analyzing the Pearson and Spearman coefficients of CWPT-SBERT, SBERT, SALBERT and SRoBERTa trained on short agro-text datasets, it could be observed that the initial training value of the CWPT-SBERT model was significantly higher than that of the comparison models and was close to the highest value of the comparison models. Moreover, it exhibited a smooth growth trend during the training process, indicating that CWPT-SBERT had strong correlation, robustness, and generalization ability from the initial state. During the training process, it could not only learn the features in the training data but also effectively apply these features to new domain data. Additionally, for ALBERT, RoBERTa and BERT models, fine-tuning training was conducted on short agro-text datasets, and optimization was performed by utilizing the morphological structure features to enrich text semantic feature expression. Through ablation experiments, it was evident that both optimization strategies could effectively enhance the performance of the models. By analyzing the attention weight heatmap of Chinese character morphological structure, the importance of Chinese character radicals in representing Chinese character attributes was highlighted, enhancing the semantic representation of Chinese characters in vector space. There was also complex correlation within the morphological structure of Chinese characters. [Conclusions] CWPT-SBERT uses transfer learning methods to solve the problem of limited short agro-text annotation datasets and high semantic sparsity. By leveraging the Chinese-oriented word segmentation method CWPT to break down Chinese characters, the semantic representation of word vectors is enhanced, and the semantic feature expression of short texts is enriched. CWPT-SBERT model has high accuracy of semantic similarity on small-scale short agro-text and obvious performance advantages, which provides an effective technical reference for semantic intelligence matching.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Lightweight Detection Method for Pepper Leaf Diseases and Pests Based on Improved YOLOv12s
    YAO Xiaotong, QU Shaoye
    Smart Agriculture    2026, 8 (1): 1-14.   DOI: 10.12133/j.smartag.SA202506005
    Abstract2488)   HTML195)    PDF(pc) (2085KB)(195)       Save

    [Objective] Pepper cultivation frequently faces challenges from diseases and pests, and early detection is critical for reducing yield losses. However, existing detection models often suffer from limitations such as insufficient feature extraction for subtle lesions, loss of edge information due to complex backgrounds, and high missed detection rates for small lesions. To address these issues, the YOLO-MDFR (You Only Look Once), a lightweight detection algorithm was proposed based on an enhanced YOLOv12s, specifically designed for accurate identification of pepper leaf diseases and pests in complex natural environments. [Methods] The dataset was established in the primary pepper cultivation zone of Gangu county, Tianshui city, Gansu province. The cultivated variety was the locally dominant Capsicum annuum L. var. conoides (Mill.). Data collection was conducted from March 15 to May 20, 2024. The collected samples included four categories of pepper leaves: healthy leaves, leaves damaged by thrips, leaves infected with tobacco mosaic virus exhibiting yellowing symptoms, and leaves affected by bacterial leaf spot. First, the original YOLOv12s backbone was replaced with an improved MobileNetV4 architecture to enhance lightweight performance while preserving feature extraction capability. Specifically, the original 5×5 standard convolutions in the bottleneck layers of MobileNetV4 were substituted with two sequential 3×3 depthwise separable convolutions. This design was based on the principle that two 3×3 convolutions achieve an equivalent receptive field (matching the 5×5 coverage) while reducing parameter count—depthwise separable convolutions further decompose spatial and channel convolution, minimizing redundant computations. Second, a novel dimensional frequency reciprocal attention mixing transformer (D-F-Ramit) module was introduced to enhance sensitivity to lesion boundaries and fine-grained textures. The module first converted feature maps from the spatial domain to the frequency domain using discrete cosine transform (DCT), capturing high-frequency components often lost in spatial-only attention. It then integrated three parallel branches: channel attention, spatial attention, and frequency-domain attention. Finally, a residual aggregation gate-controlled convolution (RAGConv) module was developed for the neck network. This module included a residual aggregation path to collect multi-layer feature information and a gate control unit that dynamically weighted feature components based on their relevance. The residual structure provided a direct gradient propagation path, alleviating gradient vanishing during backpropagation and ensuring efficient information transfer during feature fusion. A systematic experimental framework was established to comprehensively evaluate model performance: (1) Ablation studies were conducted using a controlled variable approach to verify the individual contributions of the improved MobileNetV4, D-F-Ramit, and RAGConv modules; (2) Lesion scale sensitivity analysis assessed detection performance across different lesion sizes, with emphasis on small-spot recognition; (3) Resolution impact analysis evaluated five common input resolutions (320×320–736×736) to explore the trade-offs among accuracy, speed, and computational efficiency; and (4) Embedded deployment validation involved model quantization and implementation on the Rockchip RK3588 platform to measure inference speed and power consumption on edge devices. [Results and Discussions] The proposed YOLO-MDFR achieved an mAP@0.5 of 95.6% on this dataset. Compared to YOLOv12s, it improved accuracy by 2.0%, reduced parameters by 61.5%, and lowered computational complexity by 68.5%. Real-time testing showed 43.4 f/s on an NVIDIA RTX 4060 GPU (CUDA 12.2) and 22.8 f/s on a Rockchip RK3588 embedded platform with only 3.5 W power consumption—suitable for battery-powered field devices. Lesion-scale analysis revealed 33.5% accuracy for <16×16 pixel lesions critical for early detection. Confusion matrix evaluation reduced misclassification, bacterial leaf spot/thrips damage misrates fell from 5.8% to 2.1%, and tobacco mosaic virus/healthy leaves from 3.2% to 1.5%, resulting in an overall 2.3% misrate. Experiments across varying input resolutions revealed a clear performance–resolution trade-off. As resolution increased from 320×320 to 736×736, mAP rose from 89.5% to 96.2%, showing diminishing returns beyond 512×512. Concurrently, computational cost grew roughly quadratically, reducing inference speed from 65.2 f/s to 35.1 f/s. [Conclusions] This study presents YOLO-MDFR, a lightweight detection model for identifying pepper leaf diseases and pests under complex natural conditions. By integrating an improved MobileNetV4 backbone, a multi-dimensional frequency reciprocal attention mixing transformer (D-F-Ramit), and a residual aggregation gate-controlled convolution (RAGConv) module, YOLO-MDFR outperforms mainstream detection models in both accuracy and efficiency. Systematic deployment experiments yielded optimized configurations for different application scenarios. Despite its strong performance, the model shows limitations in robustness under extreme lighting, generalization to emerging diseases, and detection of small targets under occlusion. Future work will address these issues through ambient light data fusion, domain adaptation with semi-supervised learning, and binocular vision integration.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Precision Target Spraying System Integrated with Remote Deep Learning Recognition Model for Cabbage Plant Centers
    ZHANG Hui, HU Jun, SHI Hang, LIU Changxi, WU Miao
    Smart Agriculture    2024, 6 (6): 85-95.   DOI: 10.12133/j.smartag.SA202406013
    Abstract2449)   HTML31)    PDF(pc) (1923KB)(1106)       Save

    [Objective] Spraying calcium can effectively prevent the occurrence of dry burning heart disease in Chinese cabbage. Accurately targeting spraying calcium can more effectively improve the utilization rate of calcium. Since the sprayer needs to move rapidly in the field, this can lead to over-application or under-application of the pesticide. This study aims to develop a targeted spray control system based on deep learning technology, explore the relationship between the advance speed, spray volume, and coverage of the sprayer, thereby addressing the uneven application issues caused by different nebulizer speeds by studying the real scenario of calcium administration to Chinese cabbage hearts. [Methods] The targeted spraying control system incorporates advanced sensors and computing equipment that were capable of obtaining real-time data regarding the location of crops and the surrounding environmental conditions. This data allowed for dynamic adjustments to be made to the spraying system, ensuring that pesticides were delivered with high precision. To further enhance the system's real-time performance and accuracy, the YOLOv8 object detection model was improved. A Ghost-Backbone lightweight network structure was introduced, integrating remote sensing technologies along with the sprayer's forward speed and the frequency of spray responses. This innovative combination resulted in the creation of a YOLOv8-Ghost-Backbone lightweight model specifically tailored for agricultural applications. The model operated on the Jetson Xavier NX controller, which was a high-performance, low-power computing platform designed for edge computing. The system was allowed to process complex tasks in real time directly in the field. The targeted spraying system was composed of two essential components: A pressure regulation unit and a targeted control unit. The pressure regulation unit was responsible for adjusting the pressure within the spraying system to ensure that the output remains stable under various operational conditions. Meanwhile, the targeted control unit played a crucial role in precisely controlling the direction, volume, and coverage of the spray to ensure that the pesticide was applied effectively to the intended areas of the plants. To rigorously evaluate the performance of the system, a series of intermittent spray tests were conducted. During these tests, the forward speed of the sprayer was gradually increased, allowing to assess how well the system responded to changes in speed. Throughout the testing phase, the response frequency of the electromagnetic valve was measured to calculate the corresponding spray volume for each nozzle. [Results and Conclusions] The experimental results indicated that the overall performance of the targeted spraying system was outstanding, particularly under conditions of high-speed operation. By meticulously recording the response times of the three primary components of the system, the valuable data were gathered. The average time required for image processing was determined to be 29.50 ms, while the transmission of decision signals took an average of 6.40 ms. The actual spraying process itself required 88.83 ms to complete. A thorough analysis of these times revealed that the total response time of the spraying system lagged by approximately 124.73 ms when compared to the electrical signal inputs. Despite the inherent delays, the system was able to maintain a high level of spraying accuracy by compensating for the response lag of the electromagnetic valve. Specifically, when tested at a speed of 7.2 km/h, the difference between the actual spray volume delivered and the required spray volume, after accounting for compensation, was found to be a mere 0.01 L/min. This minimal difference indicates that the system met the standard operational requirements for effective pesticide application, thereby demonstrating its precision and reliability in practical settings. [Conclusions] In conclusion, this study developed and validated a deep learning-based targeted spraying control system that exhibited excellent performance regarding both spraying accuracy and response speed. The system serves as a significant technical reference for future endeavors in agricultural automation. Moreover, the research provides insights into how to maintain consistent spraying effectiveness and optimize pesticide utilization efficiency by dynamically adjusting the spraying system as the operating speed varies. The findings of this research will offer valuable experiences and guidance for the implementation of agricultural robots in the precise application of pesticides, with a particular emphasis on parameter selection and system optimization.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Knowledge Graph Driven Grain Big Data Applications: Overview and Perspective
    YANG Chenxue, LI Xian, ZHOU Qingbo
    Smart Agriculture    2025, 7 (2): 26-40.   DOI: 10.12133/j.smartag.SA202501004
    Abstract2439)   HTML100)    PDF(pc) (1435KB)(699)       Save

    [Significance] Grain production spans multiple stages and involves numerous heterogeneous factors, including agronomic inputs, natural resources, environmental conditions, and socio-economic variables. However, the associated data generated throughout the entire production process, ranging from cultivation planning to harvest evaluation, remains highly fragmented, unstructured, and semantically diverse. This complexity data, combined with the lack of integrated core algorithms to support decision-making, has severely limited the potential of big data to drive innovation in grain production. Knowledge graph technology, by offering structured and semantically-rich representations of complex data, enables the integration of multi-source and heterogeneous data, enhances semantic mining and reasoning capabilities, and provides intelligent, knowledge-driven support for sustainable grain production, thereby addressing these challenges effectively. [Progress] This paper systematically reviewed the current research and application progress of knowledge graphs in the grain production big data. A comprehensive knowledge graph driven framework was proposed based on a hybrid paradigm combining data-driven modeling and domain knowledge guidance to support the entire grain production lifecycle and addressed three primary dimensions of data complexity: Structural diversity, relational heterogeneity, and semantic ambiguity. The key techniques of constructing multimodal knowledge map and temporal reasoning for grain production were described. First, an agricultural ontology system for grain production was designed, incorporating domain-specific concepts, hierarchical relationships, and attribute constraints. This ontology provided the semantic foundation for knowledge modeling and alignment. Second, multimodal named entity recognition (NER) techniques were employed to extract entities such as crops, varieties, weather conditions, operations, and equipment from structured and unstructured data sources, including satellite imagery, agronomic reports, Internet of Things sensor data, and historical statistics. Advanced deep learning models, such as bidirectional encoder representations from transformers (BERT) and vision-language transformers, were used to enhance recognition accuracy across text and image modalities. Third, the system implemented multimodal entity linking and disambiguation, which connected identical or semantically similar entities across different data sources by leveraging graph embeddings, semantic similarity measures, and rule-based matching. Finally, temporal reasoning modules were constructed using temporal knowledge graphs and logical rules to support dynamic inference over time-sensitive knowledge, such as crop growth stages, climate variations, and policy interventions. The proposed knowledge graph driven system enabled the development of intelligent applications across multiple stages of grain production. In the pre-production stage, knowledge graphs supported decision-making in resource allocation, crop variety selection, and planting schedule optimization based on past data patterns and predictive inference. During the in-production stage, the system facilitated precision operations, such as real-time fertilization and irrigation by reasoning over current field status, real-time sensor inputs, and historical trends. In the post-production stage, it enabled yield assessment and economic evaluation through integration of production outcomes, environmental factors, and policy constraints. [Conclusions and Prospects] Knowledge graph technologies offer a scalable and semantically-enhanced approach for unlocking the full potential of grain production big data. By integrating heterogeneous data sources, representing domain knowledge explicitly, and supporting intelligent reasoning, knowledge graphs can provide visualization, explainability, and decision support across various spatial scales, including national, provincial, county-level, and large-scale farm contexts. These technologies are of great scientific and practical significance in supporting China's national food security strategy and advancing the goals of storing grain in the land and storing grain in technology. Future directions include the construction of cross-domain agricultural knowledge fusion systems, dynamic ontology evolution mechanisms, and federated knowledge graph platforms for multi-region data collaboration under data privacy constraints.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Rapid and Non-Destructive Analysis Method of Hawthorn Moisture Content Based on Hyperspectral Imaging Technology
    BAI Ruibin, WANG Hui, WANG Hongpeng, HONG Jiashun, ZHOU Junhui, YANG Jian
    Smart Agriculture    2025, 7 (4): 95-107.   DOI: 10.12133/j.smartag.SA202505033
    Abstract2387)   HTML7)    PDF(pc) (2379KB)(48)       Save

    [Objective] This study aimed to develop a rapid and non-destructive method for determining the moisture content of hawthorn fruits using hyperspectral imaging (HSI) integrated with machine learning algorithms. By evaluating the effects of different fruit orientations and spectral ranges, the research provides theoretical insights and technical support for real-time moisture monitoring and intelligent fruit sorting. [Methods] A total of 458 fresh hawthorn samples, representing various regions and cultivars, were collected to ensure diversity and robustness. Hyperspectral images were acquired in two spectral ranges: visible-near-infrared (VNIR, 400~1 000 nm) and short-wave infrared (SWIR, 940~2 500 nm). A threshold segmentation algorithm was used to extract the region of interest (ROI) from each image, and the average reflectance spectrum of the ROI served as the raw input data. To enhance spectral quality and reduce noise, five preprocessing techniques were applied: Savitzky-Golay (SG) smoothing, multiplicative scatter correction (MSC), standard normal variate (SNV), first derivative (FD), and second derivative (SD). Four regression algorithms were then employed to build predictive models: partial least squares regression (PLSR), support vector regression (SVR), random forest (RF), and multilayer perceptron (MLP). The models were evaluated under varying fruit orientations (stem-side facing downward, upward, sideways, and a combined set of all three) and spectral ranges (VNIR, SWIR, and VNIR+SWIR). To further reduce the dimensionality of the hyperspectral data and minimize redundancy, four feature selection methods were applied: successive projections algorithm (SPA), competitive adaptive reweighted sampling (CARS), variable iterative space shrinkage approach (VISSA), and discrete wavelet transform combined with stepwise regression (DWT-SR). The DWT-SR method utilized the Daubechies 6 (db6) wavelet basis function at a decomposition level of 1. [Results and Discussions] Both fruit orientation and spectral range had a significant impact on model performance. The optimal prediction results were achieved when the stem-side of the fruit was facing downward, using the SWIR range (940~2 500 nm) and FD preprocessing. Under these conditions, the SVR model exhibited the highest predictive accuracy, with a coefficient of determination (R2ₚ) of 0.860 5, mean absolute error (MAEₚ) of 0.711 1, root mean square error (RMSEₚ) of 0.914 2, and residual prediction deviation (RPD) of 2.677 6. Further feature reduction using the DWT-SR method resulted in the selection of 17 key wavelengths. Despite the reduced input size, the SVR model based on these features maintained strong predictive capability, achieving R2ₚ = 0.857 1, MAEₚ = 0.669 2, RMSEₚ = 0.925 2, and RPD = 2.645 7. These findings confirm that the DWT-SR method effectively balances dimensionality reduction with model performance. The results demonstrate that the SWIR range contains more moisture-relevant spectral information than the VNIR range, and that first derivative preprocessing significantly improves the correlation between spectral features and moisture content. The SVR model proved particularly well-suited for handling nonlinear relationships in small datasets. Additionally, the DWT-SR method efficiently reduced data dimensionality while preserving key information, making it highly applicable for real-time industrial use. [Conclusions] In conclusion, hyperspectral imaging combined with appropriate preprocessing, feature selection, and machine learning techniques offers a promising and accurate approach for non-destructive moisture determination in hawthorn fruits. This method provides a valuable reference for quality control, moisture monitoring, and automated fruit sorting in the agricultural and food processing industries.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Rapid Tea Identification and Polyphenol Detection Method in Fresh Tea Leaves Using Visible/Shortwave and Longwave Near-Infrared Spectroscopy
    XU Jinchai, LI Xiaoli, WENG Haiyong, HE Yong, ZHU Xuesong, LIU Hongfei, HUANG Zhenxiong, YE Dapeng
    Smart Agriculture    2025, 7 (4): 58-70.   DOI: 10.12133/j.smartag.SA202505034
    Abstract2370)   HTML28)    PDF(pc) (9234KB)(79)       Save

    [Objective] Tea polyphenols, as a key indicator for evaluating tea quality, possess significant health benefits. Traditional detection methods are limited by poor timeliness, high cost, and destructive sampling, making them difficult to meet the demands of tea cultivar breeding and real-time monitoring of tea quality. Meanwhile, rapid identification of tea cultivars and leaf positions is critical for guiding tea production. Therefore, this study aims to develop a non-destructive detection device for quality components of fresh tea leaves based on the combined technology of visible/short-wave near-infrared and long-wave near-infrared spectroscopy, to realize rapid non-destructive detection of tea polyphenol content and rapid identification of tea cultivars and leaf positions. [Methods] A rapid non-destructive detection device for quality components of fresh tea leaves was developed by combining visible/short-wave near-infrared spectroscopy (400~1 050 nm) and long-wave near-infrared spectroscopy (1 051~1 650 nm). The Savitzky-Golay (SG) convolution smoothing method was used for preprocessing the spectral data. The Folin-Ciocalteu method was employed to determine the tea polyphenol content, and abnormal samples were eliminated using the interquartile range (IQR) method. Data-level and feature-level fusion methods were adopted, with the competitive adaptive reweighted sampling (CARS) algorithm used to extract characteristic wavelengths. Prior to modeling, the Kennard-Stone algorithm was applied to partition the dataset into a training set and a prediction set at a ratio of 4∶1. Models such as principal component analysis (PCA), partial least squares-discriminant analysis (PLS-DA), least squares support vector machine (LS-SVM), extreme learning machine (ELM), and 1D convolutional neural network (1D-CNN) were constructed for the identification of 3 cultivars (Huangdan, Tieguanyin, and Benshan) and 4 leaf positions. For predicting tea polyphenol content, models including partial least squares regression (PLSR), least squares support vector regression (LS-SVR), ELM, and 1D-CNN were established for predicting the tea polyphenol content in fresh tea leaves. [Results and Discussions] The results showed that there were significant differences in tea polyphenol contents among different cultivars and leaf positions (P<0.05). Specifically, the tea polyphenol content of Huangdan was 17.54%±1.82%, which was 1.16 times and 1.04 times that of Tieguanyin (15.04%±1.22%) and Benshan (16.81%±1.24%), respectively. For each cultivar, the tea polyphenol content generally showed a decreasing trend from the 1st to 4th leaf positions, with the highest content in the 1st leaf position. Principal component analysis (PCA) revealed that for cultivar identification, the scatter distribution of the principal components of Huangdan, Tieguanyin, and Benshan, as well as their projections in the directions of PC1 and PC2, showed a clear trend of clustering into three groups, indicating a good classification effect, although there was still some overlap among individual samples. For leaf position identification, the scatter distributions of the principal components of the 1st, 2nd, 3rd, and 4th leaf positions overlapped with each other, with no obvious clustering among leaf positions. Compared with single-source data, models based on data fusion effectively improved prediction performance. Among them, the PLS-DA model established by combining SG preprocessing with feature-level fusion achieved prediction accuracies of 100% and 87.93% for the identification of 3 tea cultivars and 4 leaf positions, respectively. Furthermore, the 1D-CNN model based on data-level fusion exhibited superior performance in predicting tea polyphenol content, with a coefficient of determination (R2P), root mean square error of prediction (RMSEP), and residual predictive deviation (RPD) of 0.802 0, 0.636 8%, and 2.268 4, respectively, which outperformed models using only visible/short-wave near-infrared spectroscopy or long-wave near-infrared spectroscopy. [Conclusions] The developed detection device combining visible/short-wave near-infrared and long-wave near-infrared spectroscopy, mainly composed of spectrometers, Y-type optical fibers, plant probes, polymer lithium batteries, DC uninterruptible power supplies, voltage conversion modules, and aluminum alloy casings, could synchronously collect multi-source spectral data of visible/short-wave near-infrared and long-wave near-infrared from fresh tea leaves. Combined with data fusion methods and machine learning algorithms, it enabled rapid detection of tea polyphenol content and efficient identification of cultivars and leaf positions in fresh tea leaves, providing new insights for the application of multi-source data fusion technology in elite tea cultivar breeding and non-destructive detection of fresh tea leaf quality.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Corn Borer Pests Infestations Detection Method Using Low-Altitude Close-Range UAV Imagery
    ZHAO Jun, NIE Zhigang, LI Guang, LIU Jiayu
    Smart Agriculture    2025, 7 (6): 111-123.   DOI: 10.12133/j.smartag.SA202505006
    Abstract2355)   HTML66)    PDF(pc) (3745KB)(158)       Save

    [Objective] The detection of corn borer infestations is essential for improving corn yield and quality, as corn borer pests pose a significant threat to global corn production. In traditional agricultural practices, identifying corn borer infestations relies on manual field inspections or trapping tools, which are labor-intensive, time-consuming, and difficult to implement over large areas. These methods are further limited by their susceptibility to human error and inability to meet the demands of modern precision agriculture. To address these challenges, a method for detecting corn borer infestations using low-altitude, close-range imagery captured by unmanned aerial vehicles (UAVs) was investigated. By focusing on detecting boreholes rather than insect bodies, this approach overcomes the difficulties of detecting corn borers, which are nocturnal and often concealed within plant tissues, thereby enhancing the applicability of field-based detection and aligning with practical field conditions. [Methods] Based on the YOLOv11 (You Only Look Once v11) object detection algorithm, a model named YOLO-ESN was introduced, for corn borer infestation detection. The YOLO-ESN model was optimized through multiple modifications. In the Backbone, an enhanced lightweight attention (ELA) mechanism was incorporated to increase sensitivity and improve the extraction of small visual features, such as boreholes, by modeling spatial dependencies in horizontal and vertical directions using one-dimensional convolutions. In the Neck, a C3k2-Spatial and channel reconstruction convolution (C3k2-SCConv) module was introduced to reduce the number of model parameters while improving feature fusion efficiency through spatial and channel reconstruction, suppressing redundant information. In the Head, a small-object detection branch, termed the P2 detection head, was added, enabling YOLO-ESN to directly utilize shallow, high-resolution features from early network layers to enhance the detection of fine-grained targets like boreholes. Additionally, a combined loss function of normalized Wasserstein distance (NWD) and efficient intersection over union (EIoU) was employed to optimize bounding box regression accuracy, addressing gradient vanishing issues for small targets and improving target localization stability and robustness. A decision tree algorithm was applied to classify infestation severity levels based on borehole detection results, and heatmaps were generated to visualize the spatial distribution of corn borer infestations across the field. [Results and Discussions] Multiple experiments were conducted using a constructed dataset of corn borer infestation images. The results demonstrated that YOLO-ESN achieved an mAP@50 of 88.6% and an mAP@50:95 of 40.5%, representing an improvement of 7.6 and 4.9 percentage points, respectively, compared to the original YOLOv11 model. The total number of parameters in YOLO-ESN was reduced by 11.52%, contributing to a lighter model suitable for UAV deployment. Ablation studies evaluated individual contributions: incorporating the ELA mechanism alone improved mAP@50 by 0.3 percentage points, and the parameters are reduced by 10.57%; replacing the C3k2 module with C3k2-SCConv reduced parameters by 2.5% while increasing mAP@50 by 0.9 percentage points; adding the P2 detection head enhanced mAP@50 and mAP@50:95 by 4.1 and 1.2 percentage points, respectively; and introducing the NWD+EIoU loss function improved mAP@50 and mAP@50:95 by 1.9 and 1.2 percentage points, respectively. Comparative experiments demonstrate that YOLO-ESN outperforms a range of mainstream object detection models, including Faster R-CNN, SSD, YOLOv8, YOLOv11, and YOLOv12. YOLO-ESN achieves an mAP@50 and an mAP@50:95, surpassing Faster R-CNN by 14.9 and 9.7 percentage points, respectively, and SSD by 17.8 and 11.4 percentage points, respectively. With a compact parameter size of 8.37 M, YOLO-ESN delivers excellent detection accuracy and generalization, striking a strong balance between performance and efficiency. Although its inference speed (32.48 frame/s) was slightly slower than YOLOv12 (75.44 frame/s), it offered a superior trade-off between accuracy and efficiency. These results validated YOLO-ESN as a lightweight, high-performing solution for small object detection tasks, such as dense small targets in remote sensing images. The decision tree algorithm classified infestation severity with high accuracy, achieving F1-Scores of 0.906, 0.803, and 0.842 for mild, moderate, and severe infestations, respectively. Heatmaps generated from borehole detection results enabled spatial visualization of infestation severity, providing a scientific basis for quantitative monitoring and targeted pesticide application in field infestations. [Conclusions] The proposed YOLO-ESN model has more advantages in overall detection accuracy and running speed. While improving the lightweight degree and deployment efficiency of the model, it also shows better recognition ability in small target detection, and can accurately locate the wormhole area on the corn leaf, effectively improving the bounding box regression accuracy and feature extraction efficiency. Compared with the traditional insect recognition method, the use of wormholes as detection objects is more in line with the actual field situation, effectively avoiding the problems of insect occlusion and strong concealment, and improving the availability of field image data and algorithm robustness. The heat map generated by the model detection results can also effectively display the distribution changes of insect pests in farmland, providing a scientific basis for precision pesticide spraying and farmland management. Overall, this study provides an effective solution for the intelligent detection of corn borer pests, has strong versatility and promotion prospects, and can provide strong technical support for precision agriculture and smart farmland management.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Research Status and Prospect of Quality Intelligent Control Technology in Facilities Environment of Characteristic Agricultural Products
    GUO Wei, WU Huarui, GUO Wang, GU Jingqiu, ZHU Huaji
    Smart Agriculture    2024, 6 (6): 44-62.   DOI: 10.12133/j.smartag.SA202411017
    Abstract2352)   HTML86)    PDF(pc) (3153KB)(2218)       Save

    [Significance] In view of the lack of monitoring means of quality influence factors in the production process of characteristic agricultural products with in central and western regions of China, the weak ability of intelligent control, the unclear coupling relationship of quality control elements and the low degree of systematic application, the existing technologies described such as intelligent monitoring of facility environment, growth and nutrition intelligent control model, architecture of intelligent management and control platform and so on. Through the application of the Internet of Things, big data and the new generation of artificial intelligence technology, it provides technical support for the construction and application of intelligent process quality control system for the whole growth period of characteristic agricultural products. [Progress] The methods of environmental regulation and nutrition regulation are analyzed, including single parameters and combined control methods, such as light, temperature, humidity, CO2 concentration, fertilizer and water, etc. The multi-parameter coupling control method has the advantage of more comprehensive scene analysis. Based on the existing technology, a multi-factor coupling method of integrating growth state, agronomy, environment, input and agricultural work is put forward. This paper probes into the system architecture of the whole process service of quality control, the visual identification system of the growth process of agricultural products and the knowledge-driven agricultural technical service system, and introduces the technology of the team in the disease knowledge Q & A scene through multi-modal knowledge graph and large model technology. [Conclusions and Prospects] Based on the present situation of the production of characteristic facility agricultural products and the overall quality of farmers in the central and western regions of China, it is appropriate to transfer the whole technical system such as facility tomato, facility cucumber and so on. According to the varieties of characteristic agricultural products, cultivation models, quality control objectives to adapt to light, temperature, humidity and other parameters, as well as fertilizer, water, medicine and other input plans, a multi-factor coupling model suitable for a specific planting area is generated and long-term production verification and model correction are carried out. And popularize it in a wider area, making full use of the advantages of intelligent equipment and data elements will promote the realization of light simplification of production equipment, scene of intelligent technology, diversification of service models, on-line quality control, large-scale production of digital intelligence, and value of data elements, further cultivate facilities to produce new quality productivity.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Advances in the Application of Multi-source Data Fusion Technology in Non-Destructive Detection of Apple
    GUO Qi, FAN Yixuan, YAN Xinhuan, LIU Xuemei, CAO Ning, WANG Zhen, PAN Shaoxiang, TAN Mengnan, ZHENG Xiaodong, SONG Ye
    Smart Agriculture    2025, 7 (4): 31-46.   DOI: 10.12133/j.smartag.SA202505036
    Abstract2350)   HTML28)    PDF(pc) (1579KB)(86)       Save

    [Significance] Apple industry is a prominent agricultural sector that is of considerable importance globally. Ensuring the highest standards of quality and safety is paramount for achieving consumer satisfaction. Non-destructive testing technologies have emerged as a powerful tool, enabling rapid and objective evaluation of fruit attributes. However, individual non-destructive testing technologies methods frequently possess inherent limitations, proving insufficient for comprehensive assessment. The synergistic application of multi-source data fusion technology in the non-destructive testing integrates information from multiple sensors to overcome the shortcomings of single-modality systems. The integration of disparate data streams constitutes the foundational technological framework that enables the advancement of apple quality control. This technological framework facilitates enhanced detection of defects and diseases, thereby contributing to the intelligent transformation of the apple industry value chain in its entirety. [Progress] This paper presents a systematic and comprehensive examination of recent advancements in multi-source data fusion for apple non-destructive testing. The principles, advantages, and typical application scenarios of five mainstream non-destructive testing technologies are first introduced: near-infrared (NIR) spectroscopy, particularly adept at quantifying internal chemical compositions such as soluble solids content (SSC) and firmness by analyzing molecular vibrations; hyperspectral imaging (HSI), which combines spectroscopy and imaging to provide both spatial and spectral information, making it ideal for visualizing the distribution of chemical components and identifying defects like bruises; electronic nose (E-nose) technology, a method for detecting unique patterns of volatile organic compounds (VOCs) to profile aroma and detect mold; machine vision, a process that analyzes external features such as color, size, shape, and texture for grading and surface defect identification; and nuclear magnetic resonance (NMR), a technique that provides detailed insights into internal structures and water content, useful for detecting internal defects such as core rot. A critical evaluation of the fundamental methodologies in data fusion is conducted, with these methodologies categorized into three distinct levels. Data-level fusion entails the direct concatenation of raw data from homogeneous sensors or preprocessed heterogeneous sensors. This approach is straightforward. It can result in high dimensionality and is susceptible to issues related to data co-registration. Feature-level fusion, the most prevalent strategy, involves extracting salient features from each data source (e.g., spectral wavelengths, textural features, gas sensor responses) and subsequently combining these feature vectors prior to model training. This intermediate approach effectively reduces redundancy and noise, and enhances model robustness. Decision-level fusion operates at the highest level of abstraction, where independent models are trained for each data modality, and their outputs or predictions are integrated using algorithms such as weighted averaging, voting schemes, or fuzzy logic. This strategy offers maximum flexibility for integrating highly disparate data types. The paper also thoroughly elaborates on the practical implementation of these strategies, and presents case studies on the fusion of different spectral data (e.g., NIR and HSI), the integration of spectral and E-nose data for combined internal quality and aroma assessment, and the powerful combination of machine vision with spectral data for simultaneous evaluation of external appearance and internal composition. [Conclusions and Prospects] The integration of multi-source data fusion technology has driven significant advancements in the field of apple non-destructive testing. This progress has substantially improved the accuracy, reliability, and comprehensiveness of quality evaluation and control systems. By synergistically combining the strengths of different sensors, it enables a holistic assessment that is unattainable with any single technology. However, the field faces persistent challenges, including the effective management of data heterogeneity (i.e., varying scales, dimensions, and physical meanings), the high computational complexity of sophisticated fusion models, and the poor portability of current multi-sensor laboratory equipment—all of which hinder online industrial applications. Future research should prioritize several key areas. First, developing automated, user-friendly fusion platforms is imperative to simplify data processing and model deployment. Second, optimizing and developing lightweight algorithms (e.g., through model compression and knowledge distillation) is critical to enhancing real-time performance for high-throughput sorting lines. Third, creating compact, cost-effective, integrated hardware that combines multiple detection technologies into a single portable device will improve stability and accessibility. Additionally, new application frontiers should be explored, such as in-field monitoring of fruit maturation and predicting post-harvest shelf life. The innovative integration of advanced algorithms and hardware holds the potential to provide substantial support for the intelligent and sustainable development of the global apple industry.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Grape Recognition and Localization Method Based on 3C-YOLOv8n and Depth Camera
    LIU Chang, SUN Yu, YANG Jing, WANG Fengchao, CHEN Jin
    Smart Agriculture    2024, 6 (6): 121-131.   DOI: 10.12133/j.smartag.SA202407008
    Abstract2346)   HTML53)    PDF(pc) (2020KB)(1208)       Save

    [Objective] Grape picking is a key link in increasing production. However, in this process, a large amount of manpower and material resources are required, which makes the picking process complex and slow. To enhance harvesting efficiency and achieve automated grape harvesting, an improved YOLOv8n object detection model named 3C-YOLOv8n was proposed, which integrates the RealSense D415 depth camera for grape recognition and localization. [Methods] The propoesed 3C-YOLOv8n incorporated a convolutional block attention module (CBAM) between the first C2f module and the third Conv module in the backbone network. Additionally, a channel attention (CA) module was added at the end of the backbone structure, resulting in a new 2C-C2f backbone network architecture. This design enabled the model to sequentially infer attention maps across two independent dimensions (channel and spatial), optimize features by considering relationships between channels and positional information. The network structure was both flexible and lightweight. Furthermore, the Content-aware ReAssembly of Features up sampling operator was implemented to support instance-specific kernels (such as deconvolution) for feature reconstruction with neighboring pixels, replacing the nearest neighbor interpolation operator in the YOLOv8n neck network. This enhancement increased the receptive field and guided the reconstruction process based on input features while maintaining low parameter and computational complexity, thereby forming the 3C-YOLOv8n model. The pyrealsense2 library was utilized to obtain pixel position information from the target area using the Intel RealSense D415 camera. During this process, the depth camera was used to capture images, and target detection algorithms were employed to pinpoint the location of grapes. The camera's depth sensor facilitated the acquisition of the three-dimensional point cloud of grapes, allowing for the calculation of the distance from the pixel point to the camera and the subsequent determination of the three-dimensional coordinates of the center of the target's bounding box in the camera coordinate system, thus achieving grape recognition and localization. [Results and Discussions] Comparative and ablation experiments were conducted. it was observed that the 3C-YOLOv8n model achieved a mean average precision (mAP) of 94.3% at an intersection ratio of 0.5 (IOU=0.5), surpassing the YOLOv8n model by 1%. The accuracy (P) and recall (R) rates were recorded at 91.6% and 86.4%, respectively, reflecting increases of 0.1% and 0.7%. The F1-Score also improved by 0.4%, demonstrating that the improved network model met the experimental accuracy and recall requirements. In terms of loss, the 3C-YOLOv8n algorithm exhibited superior performance, with a rapid decrease in loss values and minimal fluctuations, ultimately leading to a minimized loss value. This indicated that the improved algorithm quickly reached a convergence state, enhancing both model accuracy and convergence speed. The ablation experiments revealed that the original YOLOv8n model yielded a mAP of 93.3%. The integration of the CBAM and CA attention mechanisms into the YOLOv8n backbone resulted in mAP values of 93.5% each. The addition of the Content-aware ReAssembly of Features up sampling operator to the neck network of YOLOv8n produced a 0.5% increase in mAP, culminating in a value of 93.8%. The combination of the three improvement strategies yielded mAP increases of 0.3, 0.7, and 0.8%, respectively, compared to the YOLOv8n model. Overall, the 3C-YOLOv8n model demonstrated the best detection performance, achieving the highest mAP of 94.3%. The ablation results confirmed the positive impact of the proposed improvement strategies on the experimental outcomes. Compared to other mainstream YOLO series algorithms, all evaluation metrics showed enhancements, with the lowest missed detection and false detection rates among all tested algorithms, underscoring its practical advantages in detection tasks. [Conclusions] By effectively addressing the inefficiencies of manual labor, 3C-YOLOv8n network model not only enhances the precision of grape recognition and localization but also significantly optimizes overall harvesting efficiency. Its superior performance in evaluation metrics such as precision, recall, mAP, and F1-Score, alongside the lowest recorded loss values among YOLO series algorithms, indicates a remarkable advancement in model convergence and operational effectiveness. Furthermore, the model's high accuracy in grape target recognition not only lays the groundwork for automated harvesting systems but also enables the implementation of complementary intelligent operations.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Non-destructive Detection of Apple Water Core Disease Based on Hyperspectral and X-ray CT Imaging
    YU Xinyuan, WANG Zhenjie, YOU Sicong, TU Kang, LAN Weijie, PENG Jing, ZHU Lixia, CHEN Tao, PAN Leiqing
    Smart Agriculture    2025, 7 (4): 108-118.   DOI: 10.12133/j.smartag.SA202507022
    Abstract2343)   HTML19)    PDF(pc) (2324KB)(67)       Save

    [Objective] Apple "sugar-glazed core" (also known as watercore) is a common physiological disorder in apple fruits. Apples with watercore possess a distinctive flavor and are highly favored by consumers. However, severely affected apples are prone to mold growth during storage, posing potential food safety risks. Currently, the primary method for detecting sugar-glazed core in apple relies on manual destructive inspection, which is inefficient for large-scale applications and fails to meet the demands of modern automated and intelligent industrial production. To achieve rapid and non-destructive detection of apples with varying watercore severity levels, effective grading and soluble solids content (SSC) prediction models were developed in this study. [Methods] The Xinjiang Aksu Red Fuji apples were used as the research subject. A total of 230 apple samples were selected, comprising 113 normal, 61 mild, 47 moderate, and 9 severe watercore apples. The watercore severity was quantified through image processing of the apples' cross-sectional images. X-ray computed tomography (X-ray CT) data were acquired, and SSC values were measured. A hyperspectral imaging system was used to collect reflectance spectra within the 400~1 000 nm range. After performing black-and-white correction and selecting regions of interest (ROI), the Sample Set Partitioning based on Joint X-Y Distances (SPXY) algorithm was applied to divide the dataset into modeling (training) and prediction sets at a 3:1 ratio. Using the iToolbox in MATLAB, discriminant models were constructed based on partial least squares discriminant analysis (PLS-DA), support vector machine (SVM), and convolutional neural network (CNN) algorithms with reflectance spectral data as the input. Regression models for predicting SSC across different watercore severity levels were also established. Feature wavelength selection was carried out using competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA), and uninformative variable elimination (UVE) methods. [Results and Discussions] The results indicated that as watercore severity increased, the SSC of Red Fuji apples exhibited an upward trend. The average SSC values were 13.4% for normal apples, 14.9% for mild watercore apples, 15.0% for moderate watercore apples, and 16.0% for severe watercore apples. X-ray CT imaging revealed that the average tissue density of watercore-affected regions was higher than that of healthy tissues. Three-dimensional reconstruction algorithms allowed visualization of the internal spatial distribution of watercore tissues at different severity levels. The spatial volume proportions of watercore tissues were 3.92% in mild, 6.11% in moderate, and 10.23% in severe watercore apples. Apples with severe watercore demonstrated higher spectral reflectance. The PLS-DA-based grading model achieved accuracies of 98.7% in the training set and 95.9% in the test set. The model based on feature wavelengths selected by the UVE algorithm also showed high precision, with accuracies of 95.67% in the training set and 86.06% in the test set. For SSC regression modeling, the partial least squares regression (PLSR) model performed best, with a coefficient of determination for calibration (RC2) of 0.962, root mean square error of calibration (RMSEC) of 0.264, coefficient of determination for prediction (RP2) of 0.879, and root mean square error of prediction (RMSEP) of 0.435. The model based on feature wavelengths selected by the SPA algorithm exhibited further improved prediction performance, yielding RC2 0.846, RMSEC 0.532, RP2 0.792, RMSEP 0.576, coefficient of determination for cross-validation (RCV2) 0.781, and root mean square error of cross-validation (RMSECV) 0.637. [Conclusions] This study leveraged hyperspectral imaging and X-ray CT technologies to analyze differences in optical reflectance and microstructural characteristics of apple tissues across different watercore severity levels. The developed grading model effectively predicted watercore severity in apples, providing critical technical support for the development of intelligent post-harvest sorting equipment. The SSC regression model accurately predicted SSC values in apples with varying watercore severity, offering an efficient method for non-destructive detection and quality assessment of watercore-affected apples.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Non-Destructive Inspection and Intelligent Grading Method of Fu Brick Tea at Fungal Fermentation Stage Based on Hyperspectral Imaging Technology
    HU Yan, WANG Yujie, ZHANG Xuechen, ZHANG Yiqiang, YU Huahao, SONG Xinbei, YE Sitan, ZHOU Jihong, CHEN Zhenlin, ZONG Weiwei, HE Yong, LI Xiaoli
    Smart Agriculture    2025, 7 (4): 71-83.   DOI: 10.12133/j.smartag.SA202505012
    Abstract2332)   HTML26)    PDF(pc) (2982KB)(75)       Save

    [Objective] Fu brick tea is a popular fermented black tea, and its "Jin hua" fermentation process determines the quality, flavor and function of the tea. Therefore, the establishment of a rapid and non-destructive detection method for the fungal fermentation stage is of great significance to improve the quality control and processing efficiency. [Methods] The variation trend of Fu brick tea was analyzed through the acquisition of visible-near-infrared (VIS-NIR) and near-infrared (NIR) hyperspectral images during the fermentation stage, and combined with the key quality indexes such as moisture, free amino acids, tea polyphenols, and tea pigments (including theaflavins, thearubigins, and theabrownines), the variation trend was analyzed. This study combined support vector machine (SVM) and convolutional neural network (CNN) to establish quantitative detection of key quality indicators and qualitative identification of the fungal fermentation stage. To enhance model performance, the squeeze-and-excitation (SE) attention mechanism was incorporated, which strengthens the adaptive weight adjustment of feature channels, resulting in the development of the Spectra-SE-CNN model. Additionally, t-distributed stochastic neighbor embedding (t-SNE) was used for feature dimensionality reduction, aiding in the visualization of feature distributions during the fermentation process. To improve the interpretability of the model, the Grad-CAM technique was employed for CNN and Spectra-SE-CNN visualization, helping to identify the key regions the model focuses on. [Results and Discussions] In the quantitative detection of Fu brick tea quality, the best models were all Spectra-SE-CNN, with R2p of 0.859 5, 0.852 5 and 0.838 3 for moisture, tea pigments and tea polyphenols, respectively, indicating a high correlation and modeling stability. These values suggest that the models were capable of accurately predicting these key quality indicators based on hyperspectral data. However, the R2p for free amino acids was lower (0.670 2), which could be attributed to their relatively minor changes during the fermentation process or a weak spectral response, making it more challenging to detect this component reliably with the current hyperspectral imaging approach. The Spectra-SE-CNN model significantly outperformed traditional CNN models, demonstrating the effectiveness of incorporating the SE attention mechanism. The SE attention mechanism enhanced the model's ability to extract and discriminate important spectral features, thereby improving both classification accuracy and generalization. This indicated that the Spectra-SE-CNN model excels not only in feature extraction but also in enhancing the model's robustness to variations in the fermentation stage. Furthermore, t-SNE revealed a clear separation of the different fungal fermentation stages in the low-dimensional space, with distinct boundaries. This visualization highlighted the model's ability to distinguish between subtle spectral differences during the fermentation process. The heatmap generated by Grad-CAM emphasized key regions, such as the fermentation location and edges, providing valuable insights into the specific features the model deemed important for accurate predictions. This improved the model's transparency and helped validate the spectral features that were most influential in identifying the fermentation stages. [Conclusions] A Spectra-SE-CNN model was proposed in this research, which incorporates the SE attention mechanism into a convolutional neural network to enhance spectral feature learning. This architecture adaptively recalibrates channel-wise feature responses, allowing the model to focus on informative spectral bands and suppress irrelevant signals. As a result, the Spectra-SE-CNN achieved improved classification accuracy and training efficiency compared to CNN models, demonstrating the strong potential of deep learning in hyperspectral spectral feature extraction. The findings validate Hyperspectral imaging technology(HIS) enables rapid, non-destructive, and high-resolution assessment of Fu brick tea during its critical fungal fermentation stage and the feasibility of integrating HSI with intelligent algorithms for real-time monitoring of the Fu brick tea fermentation process. Furthermore, this approach offers a pathway for broader applications of hyperspectral imaging and deep learning in intelligent agricultural product monitoring, quality control, and automation of traditional fermentation processes.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Lightweight Tea Shoot Picking Point Recognition Model Based on Improved DeepLabV3+
    HU Chengxi, TAN Lixin, WANG Wenyin, SONG Min
    Smart Agriculture    2024, 6 (5): 119-127.   DOI: 10.12133/j.smartag.SA202403016
    Abstract2318)   HTML65)    PDF(pc) (1379KB)(1410)       Save

    [Objective] The picking of famous and high-quality tea is a crucial link in the tea industry. Identifying and locating the tender buds of famous and high-quality tea for picking is an important component of the modern tea picking robot. Traditional neural network methods suffer from issues such as large model size, long training times, and difficulties in dealing with complex scenes. In this study, based on the actual scenario of the Xiqing Tea Garden in Hunan Province, proposes a novel deep learning algorithm was proposed to solve the precise segmentation challenge of famous and high-quality tea picking points. [Methods] The primary technical innovation resided in the amalgamation of a lightweight network architecture, MobilenetV2, with an attention mechanism known as efficient channel attention network (ECANet), alongside optimization modules including atrous spatial pyramid pooling (ASPP). Initially, MobilenetV2 was employed as the feature extractor, substituting traditional convolution operations with depth wise separable convolutions. This led to a notable reduction in the model's parameter count and expedited the model training process. Subsequently, the innovative fusion of ECANet and ASPP modules constituted the ECA_ASPP module, with the intention of bolstering the model's capacity for fusing multi-scale features, especially pertinent to the intricate recognition of tea shoots. This fusion strategy facilitated the model's capability to capture more nuanced features of delicate shoots, thereby augmenting segmentation accuracy. The specific implementation steps entailed the feeding of image inputs through the improved network, whereupon MobilenetV2 was utilized to extract both shallow and deep features. Deep features were then fused via the ECA_ASPP module for the purpose of multi-scale feature integration, reinforcing the model's resilience to intricate backgrounds and variations in tea shoot morphology. Conversely, shallow features proceeded directly to the decoding stage, undergoing channel reduction processing before being integrated with upsampled deep features. This divide-and-conquer strategy effectively harnessed the benefits of features at differing levels of abstraction and, furthermore, heightened the model's recognition performance through meticulous feature fusion. Ultimately, through a sequence of convolutional operations and upsampling procedures, a prediction map congruent in resolution with the original image was generated, enabling the precise demarcation of tea shoot harvesting points. [Results and Discussions] The experimental outcomes indicated that the enhanced DeepLabV3+ model had achieved an average Intersection over Union (IoU) of 93.71% and an average pixel accuracy of 97.25% on the dataset of tea shoots. Compared to the original model based on Xception, there was a substantial decrease in the parameter count from 54.714 million to a mere 5.818 million, effectively accomplishing a significant lightweight redesign of the model. Further comparisons with other prevalent semantic segmentation networks revealed that the improved model exhibited remarkable advantages concerning pivotal metrics such as the number of parameters, training duration, and average IoU, highlighting its efficacy and precision in the domain of tea shoot recognition. This considerable decreased in parameter numbers not only facilitated a more resource-economical deployment but also led to abbreviated training periods, rendering the model highly suitable for real-time implementations amidst tea garden ecosystems. The elevated mean IoU and pixel accuracy attested to the model's capacity for precise demarcation and identification of tea shoots, even amidst intricate and varied datasets, demonstrating resilience and adaptability in pragmatic contexts. [Conclusions] This study effectively implements an efficient and accurate tea shoot recognition method through targeted model improvements and optimizations, furnishing crucial technical support for the practical application of intelligent tea picking robots. The introduction of lightweight DeepLabV3+ not only substantially enhances recognition speed and segmentation accuracy, but also mitigates hardware requirements, thereby promoting the practical application of intelligent picking technology in the tea industry.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    High-Precision Fish Pose Estimation Method Based on Improved HRNet
    PENG Qiujun, LI Weiran, LIU Yeqiang, LI Zhenbo
    Smart Agriculture    2025, 7 (3): 160-172.   DOI: 10.12133/j.smartag.SA202502001
    Abstract2317)   HTML59)    PDF(pc) (2577KB)(107)       Save

    [Objective] Fish pose estimation (FPE) provides fish physiological information, facilitating health monitoring in aquaculture. It aids decision-making in areas such as fish behavior recognition. When fish are injured or deficient, they often display abnormal behaviors and noticeable changes in the positioning of their body parts. Moreover, the unpredictable posture and orientation of fish during swimming, combined with the rapid swimming speed of fish, restrict the current scope of research in FPE. In this research, a FPE model named HPFPE is presented to capture the swimming posture of fish and accurately detect their key points. [Methods] On the one hand, this model incorporated the CBAM module into the HRNet framework. The attention module enhanced accuracy without adding computational complexity, while effectively capturing a broader range of contextual information. On the other hand, the model incorporated dilated convolution to increase the receptive field, allowing it to capture more spatial context. [Results and Discussions] Experiments showed that compared with the baseline method, the average precision (AP) of HPFPE based on different backbones and input sizes on the oplegnathus punctatus datasets had increased by 0.62, 1.35, 1.76, and 1.28 percent point, respectively, while the average recall (AR) had also increased by 0.85, 1.50, 1.40, and 1.00, respectively. Additionally, HPFPE outperformed other mainstream methods, including DeepPose, CPM, SCNet, and Lite-HRNet. Furthermore, when compared to other methods using the ornamental fish data, HPFPE achieved the highest AP and AR values of 52.96%, and 59.50%, respectively. [Conclusions] The proposed HPFPE can accurately estimate fish posture and assess their swimming patterns, serving as a valuable reference for applications such as fish behavior recognition.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Accurate Detection of Tree Planting Locations in Inner Mongolia for The Three North Project Based on YOLOv10-MHSA
    XIE Jiyuan, ZHANG Dongyan, NIU Zhen, CHENG Tao, YUAN Feng, LIU Yaling
    Smart Agriculture    2025, 7 (3): 108-119.   DOI: 10.12133/j.smartag.SA202410010
    Abstract2280)   HTML92)    PDF(pc) (3031KB)(7949)       Save

    [Objective] The traditional manual field investigation method of the tree planting locations is not only inefficient but also error-prone, and the low-altitude unmanned aerial vehicle (UAV) has become the best choice to solve these problems. To solve the problem of accuracy and efficiency in the detection of tree planting locations (tree pits) in Inner Mongolia of China's Three North Project, an accurate recognition and detection model of tree planting locations based on YOLOv10-MHSA was proposed. [Methods] A long-endurance, multi-purpose vertical take-off and landing (VTOL) fixed-wing UAV was used to collect images of tree planting locations. Equipped with a 26-megapixel camera with high spatial resolution, the UAV was well-suited for high-precision field mapping. Aerial photography was conducted between 11:00 and 12:00 on August 1, 2024. Flight parameters were set as follows: Altitude of 150 m (yielding a ground resolution of approximately 2.56 cm), course overlap rate of 75%, side overlap rate of 65%, and flight speed of 20 m/s. To prevent overfitting during network training, the original data set was enhanced. To improve the quality and efficiency of model training, different attention mechanisms and optimizing loss functions were introduced. Specifically, a more effective EIOU loss function was introduced, comprising three components: IOU loss, distance loss, and azimuth loss. This function directly minimizes the width and height discrepancies between the target frame and anchor, leading to faster convergence and more accurate positioning. Additionally, the Focal-EIOU loss function was adopted to address sample imbalance in bounding box regression tasks, further improving the model's convergence speed and positioning precision. [Results and Discussions] After the introduction of the multi-head self-attention mechanism (MHSA), the model achieved improvements of 1.4% and 1.7% in the evaluation metrics AP@0.5 and AP@0.5:0.95, respectively, and the accuracy and recall rate were also improved. This indicates that MHSA effectively aids the model in extracting the feature information of the target and improving the detection accuracy in complex background. Although the processing speed of the model decreases slightly after adding the attention mechanism, it could still meet the requirements of real-time detection. The experiment compared four loss functions: CIOU, SIOU, EIOU and Focal-EIOU. The results showed that the Focal-EIOU loss function yielded significant increases in precision and recall. This demonstrated that the Focal-EIOU loss function could accelerate the convergence speed of the model and improve the positioning accuracy when dealing with the sample imbalance problem in small target detection. Finally, an improved model, YOLOv10-MHSA, was proposed, incorporating MHSA attention mechanism, small target detection layer and Focal-EIOU loss function. The results of ablation experiments showed that AP@0.5 and AP@0.5:0.95 were increased by 2.2% and 0.9%, respectively, after adding only small target detection layer on the basis of YOLOv10n, and the accuracy and recall rate were also significantly improved. When the MHSA and Focal-EIOU loss functions were further added, the model detection effect was significantly improved. Compared with the baseline model YOLOv10n, the AP@0.5, AP@0.5:0.95, P-value and R-value were improved by 6.6%, 10.0%, 4.1% and 5.1%, respectively. Although the FPS was reduced, the detection performance of the improved model was significantly better than that of the original model in various complex scenes, especially for small target detection in densely distributed and occluded scenes. [Conclusions] By introducing MHSA and the optimized loss function (Focal-EIOU) into YOLOv10n model, the research significantly improved the accuracy and efficiency of tree planting location detection in the Three North Project in Inner Mongolia. The experimental results show that MHSA can enhance the ability of the model to extract local and global information of the target in complex background, and effectively reduce the phenomenon of missed detection and false detection. The Focal-EIOU loss function accelerates the convergence speed of the model and improves the positioning accuracy by optimizing the sample imbalance problem in the bounding box regression task. Although the model processing speed has decreased, the method proposed still meets the real-time detection requirements, provides strong technical support for the scientific afforestation of the Three North Project.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Extracting Method of the Cultivation Aera of Rice Based on Sentinel-1/2 and Google Earth Engine (GEE): A Case Study of the Hangjiahu Plain
    E Hailin, ZHOU Decheng, LI Kun
    Smart Agriculture    2025, 7 (2): 81-94.   DOI: 10.12133/j.smartag.SA202502003
    Abstract2243)   HTML70)    PDF(pc) (2961KB)(350)       Save

    [Objective] Accurate monitoring of rice planting areas is vital for ensuring national food security, evaluating greenhouse gas emissions, optimizing water resource allocation, and maintaining agricultural ecosystems. In recent years, the integration of remote sensing technologies—particularly the fusion of optical and synthetic aperture radar (SAR) data—has significantly enhanced the capacity to monitor crop distribution, even under challenging weather conditions. However, many current studies still rely heavily on phenological features captured at specific key stages, such as the transplanting phase, while overlooking the complete temporal dynamics of vegetation and water-related indices throughout the entire rice growth cycle. There is an urgent need for a method that fully leverages the time-series characteristics of remote sensing indices to enable accurate, scalable, and timely rice mapping. [Methods] Focusing on the Hangjiahu Plain, a typical rice-growing region in eastern China, a novel approach—dynamic NDVI-SDWI Fusion method for rice mapping (DNSF-Rice) was proposed in this research to accurately extract rice planting areas by synergistically integrating Sentinel-1 SAR and Sentinel-2 optical imagery on the google earth engine (GEE) platform. The methodological framework included the following three steps: First, using Sentinel-2 imagery, a time series of the normalized difference vegetation index (NDVI) was constructed. By analyzing its temporal dynamics across key rice growth stages, potential rice planting areas were identified through a threshold-based classification method; Second, a time series of the Sentinel-1 dual-polarized water index (SDWI) was generated to analyze its dynamic changes throughout the rice growth cycle. A thresholding algorithm was then applied to extract rice field distribution based on microwave data, considering the significant irrigation involved in rice cultivation; Finally, the spatial intersection of the NDVI-derived and SDWI-derived results was intersected to generate the final rice planting map. This step ensures that only pixels exhibiting both vegetation growth and irrigation signals were classified as rice. The classification datasets spanned five consecutive years from 2019 to 2023, with a spatial resolution of 10 m. [Results and Discussions] The proposed method demonstrated high accuracy and robust performance in mapping rice planting areas. Over the study period, the method achieved an overall accuracy of over 96% and an F1-Score exceeding 0.96, outperforming several benchmark products in terms of spatial consistency and precision. The integration of NDVI and SDWI time-series features enabled effective identification of rice fields, even under the challenging conditions of frequent cloud cover and variable precipitation typical in the study area. Interannual analysis revealed a consistent increase in rice planting areas across the Hangjiahu Plain from 2019 to 2023. The remote sensing-based rice area estimates were in strong agreement with official agricultural statistics, further validating the reliability of the proposed method. The fusion of optical and SAR data proved to be a valuable strategy, effectively compensating for the limitations inherent in single-source imagery, especially during the cloudy and rainy seasons when optical imagery alone was often insufficient. Furthermore, the use of GEE facilitated the rapid processing of large-scale time-series data, supporting the operational scalability required for regional rice monitoring. This study emphasized the critical importance of capturing the full temporal dynamics of both vegetation and water signals throughout the entire rice growth cycle, rather than relying solely on fixed phenological stages. [Conclusions] By leveraging the complementary advantages of optical and SAR imagery and utilizing the complete time-series behavior of NDVI and SDWI indices, the proposed approach successfully mapped rice planting areas across a complex monsoon climate region over a five-year period. The method has been proven to be stable, reproducible, and adaptable for large-scale agricultural monitoring applications.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Key Technologies and Construction model for Unmanned Smart Farms: Taking the "1.5-Ton Grain per Mu" Unmanned Farm as An Example
    LIU lining, ZHANG Hongqi, ZHANG Ziwen, ZHANG Zhenghui, WANG Jiayu, LI Xuanxuan, ZHU Ke, LIU Pingzeng
    Smart Agriculture    2025, 7 (1): 70-84.   DOI: 10.12133/j.smartag.SA202410033
    Abstract2229)   HTML93)    PDF(pc) (2674KB)(931)       Save

    [Objective] As a key model of smart agriculture, the unmanned smart farm aims to develop a highly intelligent and automated system for high grain yields. This research uses the "1.5-Ton grain per Mu" farm in Dezhou city, Shandong province, as the experimental site, targeting core challenges in large-scale smart agriculture and exploring construction and service models for such farms. [Methods] The "1.5-Ton grain per Mu" unmanned smart farm comprehensively utilized information technologies such as the internet of things (IoT) and big data to achieve full-chain integration and services for information perception, transmission, mining, and application. The overall construction architecture consisted of the perception layer, transmission layer, processing layer, and application layer. This architecture enabled precise perception, secure transmission, analysis and processing, and application services for farm data. A perception system for the unmanned smart farm of wheat was developed, which included a digital perception network and crop phenotypic analysis. The former achieved precise perception, efficient transmission, and precise measurement and control of data information within the farm through perception nodes, self-organizing networks, and edge computing core processing nodes. Phenotypic analysis utilized methods such as deep learning to extract phenotypic characteristics at different growth stages, such as the phenological classification of wheat and wheat ear length. An intelligent controlled system had been developed. The system consisted of an intelligent agricultural machinery system, a field irrigation system, and an aerial pesticided application system. The intelligent agricultural machinery system was composed of three parts: the basic layer, decision-making layer, and application service layer. They were responsible for obtaining real-time status information of agricultural machinery, formulating management decisions for agricultural machinery, and executing operational commands, respectively. Additionally, appropriate agricultural machinery models and configuration references were provided. A refined irrigation scheme was designed based on the water requirements and soil conditions at different developmental stages of wheat. And, an irrigation control algorithm based on fuzzy PID was proposed. Finally, relying on technologies such as multi-source data fusion, distributed computing, and geographic information system (GIS), an intelligent management and control platform for the entire agricultural production process was established. [Results and Discussions] The digital perception network enabled precise sensing and networked transmission of environmental information within the farm. The data communication quality of the sensor network remained above 85%, effectively ensuring data transmission quality. The average relative error in extracting wheat spike length information based on deep learning algorithms was 1.24%. Through the coordinated operation of intelligent control system, the farm achieved lean and unmanned production management, enabling intelligent control throughout the entire production chain, which significantly reduced labor costs and improved the precision and efficiency of farm management. The irrigation model not only saved 20% of irrigation water but also increased the yield of "Jinan 17" and "Jimai 44" by 10.18% and 7%, respectively. Pesticide application through spraying drones reduced pesticide usage by 55%. The big data platform provided users with production guidance services such as meteorological disaster prediction, optimal sowing time, environmental prediction, and water and fertilizer management through intelligent scientific decision support, intelligent agricultural machinery operation, and producted quality and safety traceability modules, helping farmers manage their farms scientifically. [Conclusions] The study achieved comprehensive collection of environmental information within the farm, precise phenotypic analysis, and intelligent control of agricultural machinery, irrigation equipment, and other equipment. Additionally, it realized digital services for agricultural management through a big data platform. The development path of the "1.5-Ton grain per Mu" unmanned smart farm can provid references for the construction of smart agriculture.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Research on Agricultural Drought Prediction Based on GCN-BiGRU-STMHSA
    QUAN Jialu, CHEN Wenbai, WANG Yiqun, CHENG Jiajing, LIU Yilong
    Smart Agriculture    2025, 7 (1): 156-164.   DOI: 10.12133/j.smartag.SA202410027
    Abstract2221)   HTML41)    PDF(pc) (1086KB)(736)       Save

    [Objective] Agricultural drought has a negative impact on the development of agricultural production and even poses a threat to food security. To reduce disaster losses and ensure stable crop yields, accurately predicting and classifying agricultural drought severity based on the standardized soil moisture index (SSMI) is of significant importance. [Methods] An agricultural drought prediction model, GCN-BiGRU-STMHSA was proposed, which integrated a graph convolutional network (GCN), a bidirectional gated recurrent unit (BiGRU), and a multi-head self-attention (MHSA) mechanism, based on remote sensing data. In terms of model design, the proposed method first employed GCN to fully capture the spatial correlations among different meteorological stations. By utilizing GCN, a spatial graph structure based on meteorological stations was constructed, enabling the extraction and modeling of spatial dependencies between stations. Additionally, a spatial multi-head self-attention mechanism (S-MHSA) was introduced to further enhance the model's ability to capture spatial features. For temporal modeling, BiGRU was utilized as the time-series feature extraction module. BiGRU considers both forward and backward dependencies in time-series data, enabling a more comprehensive understanding of the temporal dynamics of agricultural drought. Meanwhile, a temporal multi-head self-attention mechanism (T-MHSA) was incorporated to enhance the model's capability to learn long-term temporal dependencies and improve prediction stability across different time scales. Finally, the model employed a fully connected layer to perform regression prediction of the SSMI. Based on the classification criteria for agricultural drought severity levels, the predicted SSMI values were mapped to the corresponding drought severity categories, achieving precise agricultural drought classification. To validate the effectiveness of the proposed model, the global land data assimilation system (GLDAS_2.1) dataset and conducted modeling and experiments was utilized on five representative meteorological stations in the North China Plain (Xinyang, Gushi, Fuyang, Huoqiu, and Dingyuan). Additionally, the proposed model was compared with multiple deep learning models, including GRU, LSTM, and Transformer, to comprehensively evaluate its performance in agricultural drought prediction tasks. The experimental design covered different forecasting horizons to analyze the model's generalization capability in both short-term and long-term predictions, thereby providing a more reliable early warning system for agricultural drought. [Results and Discussions] Experimental results demonstrated that the proposed GCN-BiGRU-STMHSA model outperforms baseline models in both SSMI prediction and agricultural drought classification tasks. Specifically, across the five study stations, the model achieved significantly lower mean absolute error (MAE) and root mean squared error (RMSE), while attaining higher coefficient of determination ( R²), classification accuracy (ACC), and F1-Score ( F1). Notably, at the Gushi station, the model exhibited the best performance in predicting SSMI 10 days ahead, achieving an MAE of 0.053, a RMSE of 0.071, a R² of 0.880, an ACC of 0.925, and a F1 of 0.924. Additionally, the model's generalization capability was investigated under different forecasting horizons (7, 14, 21, and 28 days). Results indicated that the model achieved the highest accuracy in short-term predictions (7 days). Although errors increase slightly as the prediction horizon extends, the model maintained high classification accuracy even for long-term predictions (up to 28 days). This highlighted the model's robustness and effectiveness in agricultural drought prediction over varying time scales. [Conclusions] The proposed model achieves superior accuracy and generalization capability in agricultural drought prediction and classification. By effectively integrating spatial graph modeling, temporal sequence feature extraction, and self-attention mechanisms, the model outperforms conventional deep learning approaches in both short-term and long-term forecasting tasks. Its strong performance provides accurate drought early warnings, assisting agricultural management authorities in formulating efficient water resource management strategies and optimizing irrigation plans. This contributes to safeguarding agricultural production and mitigating the potential adverse effects of agricultural drought.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Monte Carlo Simulation of Light Propagation in Orah Mandarin Tissues and Optimization of Spectral Detection in Diffuse Reflection Mode
    OUYANG Aiguo, WANG Yang, LIU Yande, HOU Youfei, WANG Guantian
    Smart Agriculture    2025, 7 (4): 47-57.   DOI: 10.12133/j.smartag.SA202505029
    Abstract2186)   HTML20)    PDF(pc) (1690KB)(69)       Save

    [Objective] Visible light/near-infrared (Vis/NIR) spectroscopy serves as an effective method for quality assessment of orah mandarin. However, as a multi-layered thick-skinned fruit, the optical properties (OPs) of different tissue layers in orah mandarin affect quality evaluation, resulting in weak signals and difficulties in extracting pulp information when applying Vis/NIR spectroscopy in practical applications. This research utilizes Monte Carlo methods to reveal the light propagation mechanism within the multi-layered tissues of orah mandarin, clarify the optical properties of each tissue layer and their contributions to detection signals, and provide theoretical basis and technical support for optimizing spectral detection systems under diffuse reflectance mode. [Methods] Orah mandarin was selected as the research material. The optical parameters of its oil sac layer, albedo layer, and pulp tissue were measured in the 500~1 050 nm band using a single integrating sphere system combined with the Inverse Adding-Doubling method (Integrating Sphere-Inverse Adding-Doubling method, IS-IAD). Based on the optical parameters of different tissue layers, a three-layer concentric sphere model (oil sac layer, albedo layer, and pulp tissue) was established. The voxel-based Monte Carlo eXtreme (MCX) method was employed to study the transmission patterns of simulated photons in orah mandarin under diffuse reflectance mode, in order to optimize the configuration of detection devices. [Results and Discussions] The experimental results demonstrated that throughout the entire wavelength range, the oil sac layer and albedo layer exhibited identical variation trends in average absorption coefficient and average reduced scattering coefficient. The oil sac layer, rich in liposoluble pigments such as carotenoids, resulted in a peak absorption coefficient at 500 nm, while the porous structure of the albedo layer led to a higher reduced scattering coefficient, and the pulp tissue exhibited the lowest reduced scattering coefficient due to its translucent structure. Light penetration depth analysis revealed that in the 500~620 nm band, the light penetration depth of the oil sac layer was higher than that of the albedo layer, while at 980 nm, due to water molecule absorption, the light penetration depth of the pulp tissue showed a significant valley. Monte Carlo simulation results indicated that light was primarily absorbed within orah mandarin tissue, with transmitted photons accounting for less than 4.2%. As the source-detector distance increased, the average optical path and light attenuation in orah mandarin tissue showed an upward trend, while the contribution rates of the oil sac layer, albedo layer, and pulp tissue to the detected signal showed decreasing, decreasing, and increasing trends, respectively. Additionally, the optical diffuse reflectance decreased significantly with increasing source-detector distance. Based on the simulation results, it was recommended that the source-detector distance for orah mandarin quality detection devices should be set in the range of 13~15 mm. This configuration could maintain a high signal contribution rate from pulp tissue while obtaining sufficient diffuse reflectance signal strength, thereby improving detection accuracy and reliability. [Conclusions] The combination of Vis/NIR spectroscopy and Monte Carlo simulation methods systematically reveals the light propagation patterns and energy distribution within orah mandarin tissue, providing important theoretical basis and methodological support for non-destructive detection of orah mandarin. By employing a single integrating sphere system with the Inverse Adding-Doubling method to obtain optical parameters of each tissue layer and utilizing voxel-based Monte Carlo simulation to thoroughly investigate photon propagation patterns within the fruit, this research accurately quantifies the contribution rates of different tissue layers to diffuse reflectance signals and effectively optimizes key parameters of the detection system. These findings provide important references for developing more precise non-destructive detection methods and equipment for orah mandarin.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Automatic Detection Method of Dairy Cow Lameness from Top-view Based on the Fusion of Spatiotemporal Stream Features
    DAI Xin, WANG Junhao, ZHANG Yi, WANG Xinjie, LI Yanxing, DAI Baisheng, SHEN Weizheng
    Smart Agriculture    2024, 6 (4): 18-28.   DOI: 10.12133/j.smartag.SA202405025
    Abstract2181)   HTML45)    PDF(pc) (1828KB)(789)       Save

    [Objective] The detection of lameness in dairy cows is an important issue that needs to be solved urgently in the process of large-scale dairy farming. Timely detection and effective intervention can reduce the culling rate of young dairy cows, which has important practical significance for increasing the milk production of dairy cows and improving the economic benefits of pastures. Due to the low efficiency and low degree of automation of traditional manual detection and contact sensor detection, the mainstream cow lameness detection method is mainly based on computer vision. The detection perspective of existing computer vision-based cow lameness detection methods is mainly side view, but the side view perspective has limitations that are difficult to eliminate. In the actual detection process, there are problems such as cows blocking each other and difficulty in deployment. The cow lameness detection method from the top view will not be difficult to use on the farm due to occlusion problems. The aim is to solve the occlusion problem under the side view. [Methods] In order to fully explore the movement undulations of the trunk of the cow and the movement information in the time dimension during the walking process of the cow, a cow lameness detection method was proposed from a top view based on fused spatiotemporal flow features. By analyzing the height changes of the lame cow in the depth video stream during movement, a spatial stream feature image sequence was constructed. By analyzing the instantaneous speed of the lame cow's body moving forward and swaying left and right when walking, optical flow was used to capture the instantaneous speed of the cow's movement, and a time flow characteristic image sequence was constructed. The spatial flow and time flow features were combined to construct a fused spatiotemporal flow feature image sequence. Different from traditional image classification tasks, the image sequence of cows walking includes features in both time and space dimensions. There would be a certain distinction between lame cows and non-lame cows due to their related postures and walking speeds when walking, so using video information analysis was feasible to characterize lameness as a behavior. The video action classification network could effectively model the spatiotemporal information in the input image sequence and output the corresponding category in the predicted result. The attention module Convolutional Block Attention Module (CBAM) was used to improve the PP-TSMv2 video action classification network and build the Cow-TSM cow lameness detection model. The CBAM module could perform channel weighting on different modes of cows, while paying attention to the weights between pixels to improve the model's feature extraction capabilities. Finally, cow lameness experiments were conducted on different modalities, different attention mechanisms, different video action classification networks and comparison of existing methods. The data was used for cow lameness included a total of 180 video streams of cows walking. Each video was decomposed into 100‒400 frames. The ratio of the number of video segments of lame cows and normal cows was 1:1. For the feature extraction of cow lameness from the top view, RGB images had less extractable information, so this work mainly used depth video streams. [Results and Discussions] In this study, a total of 180 segments of cow image sequence data were acquired and processed, including 90 lame cows and 90 non-lame cows with a 1:1 ratio of video segments, and the prediction accuracy of automatic detection method for dairy cow lameness based on fusion of spatiotemporal stream features reaches 88.7%, the model size was 22 M, and the offline inference time was 0.046 s. The prediction accuracy of the common mainstream video action classification models TSM, PP-TSM, SlowFast and TimesFormer models on the data set of automatic detection method for dairy cow lameness based on fusion of spatiotemporal stream features reached 66.7%, 84.8%, 87.1% and 85.7%, respectively. The comprehensive performance of the improved Cow-TSM model in this paper was the most. At the same time, the recognition accuracy of the fused spatiotemporal flow feature image was improved by 12% and 4.1%, respectively, compared with the temporal mode and spatial mode, which proved the effectiveness of spatiotemporal flow fusion in this method. By conducting ablation experiments on different attention mechanisms of SE, SK, CA and CBAM, it was proved that the CBAM attention mechanism used has the best effect on the data of automatic detection method for dairy cow lameness based on fusion of spatiotemporal stream features. The channel attention in CBAM had a better effect on fused spatiotemporal flow data, and the spatial attention could also focus on the key spatial information in cow images. Finally, comparisons were made with existing lameness detection methods, including different methods from side view and top view. Compared with existing methods in the side-view perspective, the prediction accuracy of automatic detection method for dairy cow lameness based on fusion of spatiotemporal stream features was slightly lower, because the side-view perspective had more effective cow lameness characteristics. Compared with the method from the top view, a novel fused spatiotemporal flow feature detection method with better performance and practicability was proposed. [Conclusions] This method can avoid the occlusion problem of detecting lame cows from the side view, and at the same time improves the prediction accuracy of the detection method from the top view. It is of great significance for reducing the incidence of lameness in cows and improving the economic benefits of the pasture, and meets the needs of large-scale construction of the pasture.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Applications Research Progress and Prospects of Multi-Agent Large Language Models in Agricultural
    ZHAO Yingping, LIANG Jinming, CHEN Beizhang, DENG Xiaoling, ZHANG Yi, XIONG Zheng, PAN Ming, MENG Xiangbao
    Smart Agriculture    2025, 7 (5): 37-51.   DOI: 10.12133/j.smartag.SA202503026
    Abstract2142)   HTML99)    PDF(pc) (1978KB)(195)       Save

    [Significance] With the rapid advancement of large language models (LLM) and multi-agent systems, their integration, multi-agent large language models, is emerging as a transformative force in modern agriculture. Agricultural production involves complex, sequential, and highly environment-dependent processes, including tillage, planting, management, and harvesting. Traditional intelligent systems often struggle with the diversity, uncertainty, and coordination of these stages' demand. Multi-agent LLMs offer a new paradigm for agricultural intelligence by combining deep semantic understanding with distributed collaboration and adaptive coordination. Through role specialization, real-time perception, and cooperative decision-making, they can decompose complex workflows, adapt to changing conditions, and enable robust, full-process automation, making them well-suited to the challenges of modern agriculture. More importantly, their application marks a critical step toward the digital transformation, precision management, and sustainable development of agriculture. By enabling intelligent decision-making across the entire agricultural lifecycle, they provide both theoretical foundations and practical tools for building next-generation smart and unmanned farming systems. [Progress] The core concepts of multi-agent LLMs are first elucidated, covering the composition and characteristics of multi-agent systems as well as the development and training pipelines of LLMs. Then, the overall architecture of multi-agent systems is presented, encompassing both the environments in which agents operate and their internal structures. The collaborative patterns of multi-agent LLMs are then examined in terms of coordination structures and temporal organization. Following this, interaction mechanisms are discussed from multiple dimensions, including interactions between agents and the external environment, inter-agent communication, communication protocol frameworks, and communication security. To demonstrate the varying task specializations of different multi-agent frameworks, a comparative benchmark survey table is provided by synthesizing benchmark tasks and results reported in existing studies. The results show that different multi-agent large language model architectures tend to perform better on specific types of tasks, reflecting the influence of agent framework design characteristics such as role assignment strategies, communication protocols, and decision-making mechanisms. Furthermore, several representative architectures of multi-agent LLMs, as proposed in existing studies, are briefly reviewed. Based on their design features, their potential applicability to agricultural scenarios is discussed. Finally, current research progress and practical applications of LLMs, multimodal large models, and multi-agent LLMs in the agricultural domain are surveyed. The application architecture of agricultural LLMs is summarized, using rice cultivation as a representative scenario to illustrate the collaborative process of a multi-agent system powered by LLMs. This process involves data acquisition agents, data processing agents, task allocation and coordination agents, task execution agents, and feedback and optimization agents. The roles and functions of each kind of agent in enabling automated and intelligent operations throughout the entire agricultural lifecycle, including tillage, planting, management, and harvesting, are comprehensively described. In addition, drawing on existing research on multimodal data processing, the pseudocode is provided to illustrate the basic logic of the data processing agents. [Conclusions and Prospects] Multi-agent LLMs technology holds vast promise in agriculture but still confronts several challenges. First, limited model interpretability, stemming from opaque internal reasoning and high-dimensional parameter mappings, hinders decision transparency, traceability, user trust, and debugging efficiency. Second, model hallucination is significant, probabilistic generation may deviate from facts, leading to erroneous environmental perception and decisions that cause resource waste or crop damage. Third, multi-modal agricultural data acquisition and processing remain complex due to non-uniform equipment standards, heterogeneous data, and insufficient cross-modal reasoning, complicating data fusion and decision-making. Future directions include: (1) enhancing interpretability via chain-of-thought techniques to improve reasoning transparency and traceability; (2) reducing hallucinations by integrating knowledge bases, retrieval-augmented generation, and verification mechanisms to bolster decision reliability; and (3) standardizing data formats to strengthen cross-modal fusion and reasoning. These measures will improve system stability and efficiency, providing solid support for the advancement of smart agriculture.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Acoustic-Vibration Detection Method for The Apple Moldy Core Disease Based on D-S Evidence Theory
    LIU Jie, ZHAO Kang, ZHAO Qinjun, SONG Ye
    Smart Agriculture    2025, 7 (4): 119-131.   DOI: 10.12133/j.smartag.SA202505032
    Abstract2121)   HTML9)    PDF(pc) (2371KB)(47)       Save

    [Objective] Moldy core disease is a common internal disease of the apple and is highly infectious. In the early storage stage, the mold symptoms are confined to the interior of the core. The apple tissue is in a sub-healthy state and still has commercial value, so early detection of moldy-core apples is critical. [Methods] In this study, a non-destructive acoustic vibration detection system was used to acquire acoustic vibration response signals. Symmetrized dot pattern (SDP), gramian angular field (GAF), and stockwell transform (ST) were applied to obtain multi-domain acoustic vibration spectra, including SDP images, gramian angular summation field (GASF) images, gramian angular difference field (GADF) images, and ST images. These images were uniformly converted to grayscale, transforming the time-domain signals into multi-domain visual spectra to facilitate subsequent feature analysis and recognition. Uniform local binary pattern (ULBP) and gray-level-gradient co-occurrence matrix (GLGCM) methods were used to extract handcrafted features from the multi-domain visualized images. Subsequently, the maximum relevance and minimum redundancy (mRMR) criterion was applied to select the dominant features from each analysis domain that were sensitive to early disease information. Principal component analysis (PCA) was employed to reduce the dimensionality of the multi-domain spectral ULBP texture features. From the statistical features extracted from one-dimensional acoustic-vibration signals in the time and frequency domains, and the GLGCM texture features extracted from two-dimensional images in each domain, 5 to 8 features sensitive to early moldy core detection were selected. From the high-dimensional sensitive ULBP texture features extracted from each domain, 3 to 7 principal components were obtained through dimensionality reduction using principal component analysis. This selection aimed to maximize the relevance between features and class labels while minimizing redundancy among features, thereby identifying the most informative features for early mold core apple detection in each domain. Meanwhile, a ResNet50 feature extractor improved with a convolutional attention mechanism module and the Adam optimizer (Adam-IResNet50) was designed to automatically extract deep features from visualized images in each domain. The optimal shallow features were used to train a multiple support vector machine (MSVM) classifier, while the optimal deep features were used to train an extreme learning machine (ELM) classifier. The Adam-IResNet50 network was employed as a feature extractor. The deep features extracted from the time-domain and frequency-domain GADF images, as well as time-frequency images, resulted in higher sample matching scores (SC) and cluster compactness (CHS) values, along with lower inter-class overlap (DBI) values for the three apple categories. These results clearly indicate that the deep features extracted by the Adam-IResNet50 model from multi-domain images exhibit strong capability in identifying subhealth and moldy core apples. The preliminary outputs of the two classifiers were converted into basic probability assignments for independent evidence bodies. Dempster's combination rule and the associated decision criterion of Dempster-Shafer (D-S) theory were then applied to yield the final decision on early-stage moldy apples. Consequently, a decision-level fusion model was established for both shallow and deep features of the acoustic-vibration multi-domain spectra. [Results and Discussions] The constructed Adam-IResNet50-IPSO-ELM-DS model based on D-S evidence theory achieved a Kappa coefficient and Matthews Correlation Coefficient (MCC) slightly below 90% for multi-class classification of apples from known origins. The F1-Score and Overall Accuracy (OA) reached 93.01% and 93.22%, respectively. The classification accuracy for sub-healthy apples was 87.37%, while the misclassification rate for diseased apples was 8.33%. These results indicate that the model maintains a balanced precision and recall while achieving high detection accuracy for three classes of apples from unknown origins. After decision fusion, the IPSO-MSVM-DS and Adam-IResNet50-IPSO-ELM-DS models demonstrated significant performance improvements. Among them, the Adam-IResNet50-IPSO-ELM-DS model achieved an accuracy of 93.22%, which was significantly higher than that of other methods. This demonstrates that decision-level fusion could effectively enhance the model's discriminative ability and further improve classification performance. [Conclusions] The proposed acoustic vibration detection method for mold core apples, based on Dempster-Shafer evidence theory, provides technical support for future online batch detection of early mold core apples. Early screening of sub-healthy apples is of great significance for quality control during postharvest storage. In future work, the model will be further optimized to develop a rapid acoustic vibration-based prediction method for early detection of mold core, providing technical support for quality control during apple distribution.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Real-time Detection Algorithm of Expanded Feed Image on the Water Surface Based on Improved YOLOv11
    ZHOU Xiushan, WEN Luting, JIE Baifei, ZHENG Haifeng, WU Qiqi, LI Kene, LIANG Junneng, LI Yijian, WEN Jiayan, JIANG Linyuan
    Smart Agriculture    2024, 6 (6): 155-167.   DOI: 10.12133/j.smartag.SA202408014
    Abstract2121)   HTML89)    PDF(pc) (1858KB)(2784)       Save

    [Objective] During the feeding process of fish populations in aquaculture, the video image characteristics of floating extruded feed on the water surface undergo continuous variations due to a myriad of environmental factors and fish behaviors. These variations pose significant challenges to the accurate detection of feed particles, which is crucial for effective feeding management. To address these challenges and enhance the detection of floating extruded feed particles on the water surface, ,thereby providing precise decision support for intelligent feeding in intensive aquaculture modes, the YOLOv11-AP2S model, an advanced detection model was proposed. [Methods] The YOLOv11-AP2S model enhanced the YOLOv11 algorithm by incorporating a series of improvements to its backbone network, neck, and head components. Specifically, an attention for fine-grained categorization (AFGC) mechanism was introduced after the 10th layer C2PSA of the backbone network. This mechanism aimed to boost the model's capability to capture fine-grained features, which were essential for accurately identifying feed particles in complex environments with low contrast and overlapping objects. Furthermore, the C3k2 module was replaced with the VoV-GSCSP module, which incorporated more sophisticated feature extraction and fusion mechanisms. This replacement further enhanced the network's ability to extract relevant features and improve detection accuracy. To improve the model's detection of small targets, a P2 layer was introduced. However, adding a P2 layer may increase computational complexity and resource consumption, so the overall performance and resource consumption of the model must be carefully balanced. To maintain the model's real-time performance while improving detection accuracy, a lightweight VoV-GSCSP module was utilized for feature fusion at the P2 layer. This approach enabled the YOLOv11-AP2S model to achieve high detection accuracy without sacrificing detection speed or model lightweights, making it suitable for real-time applications in aquaculture. [Results and Discussions] The ablation experimental results demonstrated the superiority of the YOLOv11-AP2S model over the original YOLOv11 network. Specifically, the YOLOv11-AP2S model achieved a precision ( P) and recall ( R) of 78.70%. The mean average precision (mAP50) at an intersection over union (IoU) threshold of 0.5 was as high as 80.00%, and the F1-Score had also reached 79.00%. These metrics represented significant improvements of 6.7%, 9.0%, 9.4% (for precision, as previously mentioned), and 8.0%, respectively, over the original YOLOv11 network. These improvements showed the effectiveness of the YOLOv11-AP2S model in detecting floating extruded feed particles in complex environments. When compared to other YOLO models, the YOLOv11-AP2S model exhibits clear advantages in detecting floating extruded feed images on a self-made dataset. Notably, under the same number of iterations, the YOLOv11-AP2S model achieved higher mAP50 values and lower losses, demonstrating its superiority in detection performance. This indicated that the YOLOv11-AP2S model strikes a good balance between learning speed and network performance, enabling it to efficiently and accurately detect images of floating extruded feed on the water surface. Furthermore, the YOLOv11-AP2S model's ability to handle complex detection scenarios, such as overlapping and adhesion of feed particles and occlusion by bubbles, was noteworthy. These capabilities were crucial for accurate detection in practical aquaculture environments, where such challenges were common and can significantly impair the performance of traditional detection systems. The improvements in detection accuracy and efficiency made the YOLOv11-AP2S model a valuable tool for intelligent feeding systems in aquaculture, as it could provide more reliable and timely information on fish feeding behavior. Additionally, the introduction of the P2 layer and the use of the lightweight VoV-GSCSP module for feature fusion at this layer contributed to the model's overall performance. These enhancements enabled the model to maintain high detection accuracy while keeping computational costs and resource consumption within manageable limits. This was particularly important for real-time applications in aquaculture, where both accuracy and efficiency were critical for effective feeding management. [Conclusions] The successful application of the YOLOv11-AP2S model in detecting floating extruded feed particles demonstrates its potential to intelligent feeding systems in aquaculture. By providing accurate and timely information on fish feeding behavior, the model can help optimize feeding strategies, reduce feed waste, and improve the overall efficiency and profitability of aquaculture operations. Furthermore, the model's ability to handle complex detection scenarios and maintain high detection accuracy while keeping computational costs within manageable limits makes it a practical and valuable tool for real-time applications in aquaculture. Therefore, the YOLOv11-AP2S model holds promise for wide application in intelligent aquaculture management, contributing to the sustainability and growth of the aquaculture industry.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Application of Photoacoustic Spectroscopy in Quality Assessment of Agricultural and Forestry Products
    XIE Weijun, CHEN Keying, QIAO Mengmeng, WU Bin, GUO Qing, ZHAO Maocheng
    Smart Agriculture    2025, 7 (4): 18-30.   DOI: 10.12133/j.smartag.SA202505026
    Abstract2107)   HTML15)    PDF(pc) (1651KB)(90)       Save

    [Significance] The quality assessment of agricultural and forestry products is a core process in ensuring food safety and enhancing product competitiveness. Traditional detection methods suffer from drawbacks such as sample destruction, expensive equipment, and poor adaptability. As an innovative analytical technique combining optical and acoustic detection principles, photoacoustic spectroscopy technology (PAS) overcomes the limitations of conventional detection techniques that rely on transmitted or reflected optical signals through its unique light-thermal-acoustic energy conversion mechanism. With its non-contact, high-sensitivity, and multi-form adaptability characteristics, PAS has been increasingly applied in the quality assessment of agricultural and forestry products in recent years, providing a new solution for the simultaneous detection of internal and external quality in these products. [Progress] In the specific applications of agricultural and forestry product testing, PAS has demonstrated practical value in multiple aspects. In seed testing, researchers have established quantitative relationship models between photoacoustic signals and seed viability also achieved dynamic assessment of seed health by monitoring respiratory metabolic gases (e.g., CO2 and ethylene). In fruit and vegetable quality analysis, PAS can capture characteristic substance changes during ripening. In the quality control of grain and oil products, Fourier-transform infrared PAS technology has been successfully applied to the rapid detection of protein content in wheat flour and aflatoxin in corn. In food safety monitoring, PAS has achieved breakthrough progress in heavy metal residue detection, pesticide residue analysis, and food authenticity identification. [Conclusions and Prospects] Despite its evident advantages, PAS technology still faces multiple challenges in practical implementation. ​Technically​​, the complex matrix of agricultural and forestry products causes non-uniform generation and propagation of photoacoustic signals, complicating data analysis. And environmental noise interference (e.g., mechanical vibrations, temperature fluctuations) compromises detection stability, while spectral peak overlap in multi-component systems limits quantitative analysis accuracy. ​​Equipment-wise​​, current PAS systems remain bulky and costly, primarily due to reliance on imported core components like high-power lasers and precision lock-in amplifiers, severely hindering widespread adoption. Moreover, the absence of standardized photoacoustic databases and universal analytical models restricts the technology's adaptability across diverse agricultural products. Looking forward, PAS development may focus on these key directions.​Firstly, multi-technology integration by combining with Raman spectroscopy, near-infrared spectroscopy, and other sensing methods to construct multidimensional data spaces for enhanced detection specificity. Moreover, ​​miniaturization​​ through developing chip-based detectors via micro-electromechanical technology, replacing conventional solid-state lasers with vertical-cavity surface-emitting lasers (VCSELs), and adopting 3D printing for integrated photoacoustic cell fabrication to significantly reduce system size and cost. Furthermore, intelligent algorithm innovation with incorporating advanced deep learning models like attention mechanisms and transfer learning to improve interpretation of complex photoacoustic spectra. As these technical bottlenecks are progressively overcome, PAS is poised to establish a quality monitoring network spanning the entire "field-to-market" chain—from ​​harvesting​​ to ​​processing/storage​​ to ​​distribution​​—thereby transforming agricultural quality control from traditional sampling-based methods to ​​intelligent, standardized, full-process monitoring​​. This will provide technical support for ​​food safety assurance​​ and ​​agricultural industry advancement​​.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Remote Sensing for Rice Growth Stages Monitoring: Research Progress, Bottleneck Problems and Technical Optimization Paths
    LI Ruijie, WANG Aidong, WU Huaxing, LI Ziqiu, FENG Xiangqian, HONG Weiyuan, TANG Xuejun, QIN Jinhua, WANG Danying, CHU Guang, ZHANG Yunbo, CHEN Song
    Smart Agriculture    2025, 7 (3): 89-107.   DOI: 10.12133/j.smartag.SA202412019
    Abstract2070)   HTML80)    PDF(pc) (2568KB)(376)       Save

    [Significance] ​The efficient and precise identification of rice growth stages through remote sensing technology holds critical significance for varietal breeding optimization and production management enhancement. Remote sensing, characterized by high spatial-temporal resolution and automated monitoring capabilities, provides transformative solutions for large-scale dynamic phenology monitoring, offering essential technical support to address climate change impacts and food security challenges in complex agroecosystems where precise monitoring of growth stage transitions enables yield prediction and stress-resilient cultivation management.​ [Progress] In recent years, the technical system for monitoring rice growth stages has achieved systematic breakthroughs in the perception layer, decision-making layer, and execution layer, forming a technological ecosystem covering the entire chain of "data acquisition-feature analysis-intelligent decision-making-precise operation". At the perception layer, a "space-air-ground" three-dimensional monitoring network has been constructed: High-altitude satellites (Sentinel-2, Landsat) realize regional-scale phenological dynamic tracking through wide-spectrum multi-temporal observations; low-altitude unmanned aerial vehicle (UAV) equipped with hyperspectral and light detection and ranging (LiDAR) sensors analyze the heterogeneity of canopy three-dimensional structure; near-ground sensor networks real-timely capture leaf-scale photosynthetic efficiency and nitrogen metabolism parameters. Radiometric calibration and temporal interpolation algorithms eliminate the spatio-temporal heterogeneity of multi-source data, forming continuous and stable monitoring capabilities. Innovations in technical methods show three integration trends: Firstly, multimodal data collaboration mechanisms break through the physical characteristic barriers between optical and radar data; secondly, deep integration of mechanistic models and data-driven approaches embeds the scattering by arbitrarily inclined leaves by arbitrary inclined leaves (PROSPECT + SAIL, PROSAIL) radiative transfer model into the long short-term memory (LSTM) network architecture; thirdly, cross-scale feature analysis technology breaks through by constructing organ-population association models based on dynamic attention mechanisms, realizing multi-granularity mapping between panicle texture features and canopy leaf area index (LAI) fluctuations. The current technical system has completed three-dimensional leaps: From discrete manual observations to full-cycle continuous perception, with monitoring frequency upgraded from weekly to hourly; from empirical threshold-based judgment to mechanism-data hybrid-driven, the cross-regional generalization ability of the model can be significantly improved; from independent link operations to full-chain collaboration of "perception-decision-execution", constructing a digital management closed-loop covering rice sowing to harvest, providing core technical support for smart farm construction. [Conclusions and Prospects] Current technologies face three-tiered challenges in data heterogeneity, feature limitations and algorithmic constraints. Future research should focus on three aspects: 1) Multi-source data assimilation systems to reconcile spatiotemporal heterogeneity through UAV-assisted satellite calibration and GAN-based cloud-contaminated data reconstruction; 2) Cross-scale physiological-spectral models integrating 3D canopy architecture with adaptive soil-adjusted indices to overcome spectral saturation; 3) Mechanism-data hybrid paradigms embedding thermal-time models into LSTM networks for environmental adaptation, developing lightweight CNNs with multi-scale attention for occlusion-resistant panicle detection, and implementing transfer learning for cross-regional model generalization. The convergence of multi-source remote sensing, intelligent algorithms, and physiological mechanisms will establish a full-cycle dynamic monitoring system based on agricultural big data.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Improvement of HLM Modeling for Winter Wheat Yield Estimation Under Drought Conditions
    ZHAO Peiqin, LIU Changbin, ZHENG Jie, MENG Yang, MEI Xin, TAO Ting, ZHAO Qian, MEI Guangyuan, YANG Xiaodong
    Smart Agriculture    2025, 7 (2): 106-116.   DOI: 10.12133/j.smartag.SA202408009
    Abstract2057)   HTML24)    PDF(pc) (1608KB)(365)       Save

    [Objective] Winter wheat yield is crucial for national food security and the standard of living of the population. Existing crop yield prediction models often show low accuracy under disaster-prone climatic conditions. This study proposed an improved hierarchical linear model (IHLM) based on a drought weather index reduction rate, aiming to enhance the accuracy of crop yield estimation under drought conditions. [Methods] HLM was constructed using the maximum enhanced vegetation index-2 (EVI2max), meteorological data (precipitation, radiation, and temperature from March to May), and observed winter wheat yield data from 160 agricultural survey stations in Shandong province (2018-2021). To validate the model's accuracy, 70% of the data from Shandong province was randomly selected for model construction, and the remaining data was used to validate the accuracy of the yield model. HLM considered the variation in meteorological factors as a key obstacle affecting crop growth and improved the model by calculating the relative meteorological factors. The calculation of relative meteorological factors helped reduce the impact of inter-annual differences in meteorological data. The accuracy of the HLM model was compared with that of the random forest (RF), Support Vector Regression (SVR), and Extreme Gradient Boosting (XGBoost) models. The HLM model provided more intuitive interpretation, especially suitable for processing hierarchical data, which helped capture the variability of winter wheat yield data under drought conditions. Therefore, a drought weather index reduction rate model from the agricultural insurance industry was introduced to further optimize the HLM model, resulting in the construction of the IHLM model. The IHLM model was designed to improve crop yield prediction accuracy under drought conditions. Since the precipitation differences between Henan and Shandong provinces were small, to test the transferability of the IHLM model, Henan province sample data was processed in the same way as in Shandong, and the IHLM model was applied to Henan province to evaluate its performance under different geographical conditions. [Results and Discussions] The accuracy of the HLM model, improved based on relative meteorological factors (rMF), was higher than that of RF, SVR, and XGBoost. The validation accuracy showed a Pearson correlation coefficient (r) of 0.76, a root mean squared error (RMSE) of 0.60 t/hm2, and a normalized RMSE (nRMSE) of 11.21%. In the drought conditions dataset, the model was further improved by incorporating the relationship between the winter wheat drought weather index and the reduction rate of winter wheat yield. After the improvement, the RMSE decreased by 0.48 t/hm2, and the nRMSE decreased by 28.64 percentage points, significantly enhancing the accuracy of the IHLM model under drought conditions. The IHLM model also demonstrated good applicability when transferred to Henan province. [Conclusions] The IHLM model developed in this study improved the accuracy and stability of crop yield predictions, especially under drought conditions. Compared to RF, SVR, and XGBoost models, the IHLM model was more suitable for predicting winter wheat yield. This research can be widely applied in the agricultural insurance field, playing a significant role in the design of agricultural insurance products, rate setting, and risk management. It enables more accurate predictions of winter wheat yield under drought conditions, with results that are closer to actual outcomes.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Lightweight YOLOv8s-Based Strawberry Plug Seedling Grading Detection and Localization via Channel Pruning
    CHEN Junlin, ZHAO Peng, CAO Xianlin, NING Jifeng, YANG Shuqin
    Smart Agriculture    2024, 6 (6): 132-143.   DOI: 10.12133/j.smartag.SA202408001
    Abstract2048)   HTML80)    PDF(pc) (3614KB)(1313)       Save

    [Objective] Plug tray seedling cultivation is a contemporary method known for its high germination rates, uniform seedling growth, shortened transplant recovery period, diminished pest and disease incidence, and enhanced labor efficiency. Despite these advantages, challenges such as missing or underdeveloped seedlings can arise due to seedling quality and environmental factors. To ensure uniformity and consistency of the seedlings, sorting is frequently necessary, and the adoption of automated seedling sorting technology can significantly reduce labor costs. Nevertheless, the overgrowth of seedlings within the plugs can effect the accuracy of detection algorithms. A method for grading and locating strawberry seedlings based on a lightweight YOLOv8s model was presented in this research to effectively mitigate the interference caused by overgrown seedlings. [Methods] The YOLOv8s model was selected as the baseline for detecting different categories of seedlings in the strawberry plug tray cultivation process, namely weak seedlings, normal seedlings, and plug holes. To improve the detection efficiency and reduce the model's computational cost, the layer-adaptive magnitude-based pruning(LAMP) score-based channel pruning algorithm was applied to compress the base YOLOv8s model. The pruning procedure involved using the dependency graph to derive the group matrices, followed by normalizing the group importance scores using the LAMP Score, and ultimately pruning the channels according to these processed scores. This pruning strategy effectively reduced the number of model parameters and the overall size of the model, thereby significantly enhancing its inference speed while maintaining the capability to accurately detect both seedlings and plug holes. Furthermore, a two-stage seedling-hole matching algorithm was introduced based on the pruned YOLOv8s model. In the first stage, seedling and plug hole bounding boxes were matched according to their the degree of overlap (Dp), resulting in an initial set of high-quality matches. This step helped minimize the number of potential matching holes for seedlings exhibiting overgrowth. Subsequently, before the second stage of matching, the remaining unmatched seedlings were ranked according to their potential matching hole scores (S), with higher scores indicating fewer potential matching holes. The seedlings were then prioritized during the second round of matching based on these scores, thus ensuring an accurate pairing of each seedling with its corresponding plug hole, even in cases where adjacent seedling leaves encroached into neighboring plug holes. [Results and Discussions] The pruning process inevitably resulted in the loss of some parameters that were originally beneficial for feature representation and model generalization. This led to a noticeable decline in model performance. However, through meticulous fine-tuning, the model's feature expression capabilities were restored, compensating for the information loss caused by pruning. Experimental results demonstrated that the fine-tuned model not only maintained high detection accuracy but also achieved significant reductions in FLOPs (86.3%) and parameter count (95.4%). The final model size was only 1.2 MB. Compared to the original YOLOv8s model, the pruned version showed improvements in several key performance metrics: precision increased by 0.4%, recall by 1.2%, mAP by 1%, and the F1-Score by 0.1%. The impact of the pruning rate on model performance was found to be non-linear. As the pruning rate increased, model performance dropped significantly after certain crucial channels were removed. However, further pruning led to a reallocation of the remaining channels' weights, which in some cases allowed the model to recover or even exceed its previous performance levels. Consequently, it was necessary to experiment extensively to identify the optimal pruning rate that balanced model accuracy and speed. The experiments indicated that when the pruning rate reached 85.7%, the mAP peaked at 96.4%. Beyond this point, performance began to decline, suggesting that this was the optimal pruning rate for achieving a balance between model efficiency and performance, resulting in a model size of 1.2 MB. To further validate the improved model's effectiveness, comparisons were conducted with different lightweight backbone networks, including MobileNetv3, ShuffleNetv2, EfficientViT, and FasterNet, while retaining the Neck and Head modules of the original YOLOv8s model. Results indicated that the modified model outperformed these alternatives, with mAP improvements of 1.3%, 1.8%, 1.5%, and 1.1%, respectively, and F1-Score increases of 1.5%, 1.8%, 1.1%, and 1%. Moreover, the pruned model showed substantial advantages in terms of floating-point operations, model size, and parameter count compared to these other lightweight networks. To verify the effectiveness of the proposed two-stage seedling-hole matching algorithm, tests were conducted using a variety of complex images from the test set. Results indicated that the proposed method achieved precise grading and localization of strawberry seedlings even under challenging overgrowth conditions. Specifically, the correct matching rate for normal seedlings reached 96.6%, for missing seedlings 84.5%, and for weak seedlings 82.9%, with an average matching accuracy of 88%, meeting the practical requirements of the strawberry plug tray cultivation process. [Conclusions] The pruned YOLOv8s model successfully maintained high detection accuracy while reducing computational costs and improving inference speed. The proposed two-stage seedling-hole matching algorithm effectively minimized the interference caused by overgrown seedlings, accurately locating and classifying seedlings of various growth stages within the plug tray. The research provides a robust and reliable technical solution for automated strawberry seedling sorting in practical plug tray cultivation scenarios, offering valuable insights and technical support for optimizing the efficiency and precision of automated seedling grading systems.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Advances, Problems and Challenges of Precise Estrus Perception and Intelligent Identification Technology for Cows
    ZHANG Zhiyong, CAO Shanshan, KONG Fantao, LIU Jifang, SUN Wei
    Smart Agriculture    2025, 7 (3): 48-68.   DOI: 10.12133/j.smartag.SA202305005
    Abstract2021)   HTML64)    PDF(pc) (2463KB)(2666)       Save

    [Significance] Estrus monitoring and identification in cows is a crucial aspect of breeding management in beef and dairy cattle farming. Innovations in precise sensing and intelligent identification methods and technologies for estrus in cows are essential not only for scientific breeding, precise management, and smart breeding on a population level but also play a key supportive role in health management, productivity enhancement, and animal welfare improvement at the individual level. The aims are to provide a reference for scientific management and the study of modern production technologies in the beef and dairy cattle industry, as well as theoretical methodologies for the research and development of key technologies in precision livestock farming. [Progress] Based on describing the typical characteristics of normal and abnormal estrus in cows, this paper systematically categorizes and summarizes the recent research progress, development trends, and methodological approaches in estrus monitoring and identification technologies, focusing on the monitoring and diagnosis of key physiological signs and behavioral characteristics during the estrus period. Firstly, the paper outlines the digital monitoring technologies for three critical physiological parameters, body temperature, rumination, and activity levels, and their applications in cow estrus monitoring and identification. It analyzes the intrinsic reasons for performance bottlenecks in estrus monitoring models based on body temperature, compares the reliability issues faced by activity-based estrus monitoring, and addresses the difficulties in balancing model generalization and robustness design. Secondly, the paper examines the estrus sensing and identification technologies based on three typical behaviors: feeding, vocalization, and sexual desire. It highlights the latest applications of new artificial intelligence technologies, such as computer vision and deep learning, in estrus monitoring and points out the critical role of these technologies in improving the accuracy and timeliness of monitoring. Finally, the paper focuses on multi-factor fusion technologies for estrus perception and identification, summarizing how different researchers combine various physiological and behavioral parameters using diverse monitoring devices and algorithms to enhance accuracy in estrus monitoring. It emphasizes that multi-factor fusion methods can improve detection rates and the precision of identification results, being more reliable and applicable than single-factor methods. The importance and potential of multi-modal information fusion in enhancing monitoring accuracy and adaptability are underlined. The current shortcomings of multi-factor information fusion methods are analyzed, such as the potential impact on animal welfare from parameter acquisition methods, the singularity of model algorithms used for representing multi-factor information fusion, and inadequacies in research on multi-factor feature extraction models and estrus identification decision algorithms. [Conclusions and Prospects] From the perspectives of system practicality, stability, environmental adaptability, cost-effectiveness, and ease of operation, several key issues are discussed that need to be addressed in the further research of precise sensing and intelligent identification technologies for cow estrus within the context of high-quality development in digital livestock farming. These include improving monitoring accuracy under weak estrus conditions, overcoming technical challenges of audio extraction and voiceprint construction amidst complex background noise, enhancing the adaptability of computer vision monitoring technologies, and establishing comprehensive monitoring and identification models through multi-modal information fusion. It specifically discusses the numerous challenges posed by these issues to current technological research and explains that future research needs to focus not only on improving the timeliness and accuracy of monitoring technologies but also on balancing system cost-effectiveness and ease of use to achieve a transition from the concept of smart farming to its practical implementation.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Current Status and Development Trend of Low-Altitude Economy Industry in Orchards
    WANG Xuechang, XU Wenbo, ZHENG Yongjun, YANG Shenghui, LIU Xingxing, SU Daobilige, WANG Zimeng
    Smart Agriculture    2025, 7 (6): 35-57.   DOI: 10.12133/j.smartag.SA202506008
    Abstract2020)   HTML39)    PDF(pc) (2540KB)(136)       Save

    [Significance] The low-altitude economy in orchards represents a key emerging direction in the integrated development of new-quality productive forces in agriculture. As a burgeoning industry driving the high-quality development of the fruit sector, it relies on the integration of advanced equipment manufacturing, the application of smart agriculture technologies and the expansion of consumer-centric ecosystems. These elements contribute to building a full-cycle industrial chain encompassing orchard production, management and services. This fosters the coordinated development of the entire low-altitude value chain and supports the formation of a closed-loop industrial ecosystem. This paper systematically reviews the key technological pathways and development trends of the orchard low-altitude economy across three dimensions: upstream equipment manufacturing, midstream operational processes and downstream service systems. The aim is to provide strategic reference for technological innovation and industrial planning in related fields. [Progress] In the upstream segment, research and industrial development are increasingly focused on lightweight and multifunctional aerial platforms tailored to the complex terrain of mountainous orchards. By utilizing carbon fiber composites, high energy-density batteries and hybrid power systems, these platforms achieve significant reductions in weight and improvements in flight endurance. The integration of artificial intelligence (AI) computing chips, light detection and ranging (LiDAR) and multispectral sensors equips drones with advanced capabilities for precise fruit tree recognition, obstacle avoidance in complex landscapes and multimodal environmental perception. With centimeter-level real-time kinematic (RTK) positioning and multi-sensor fusion flight control algorithms, operational safety and autonomy have been greatly enhanced. Furthermore, low-altitude infrastructure, such as distributed takeoff and landing points and mobile battery-swapping stations, based on integrated 5G-Advanced and BeiDou navigation communication systems, is being systematically deployed. This provides strong support for continuous unmanned operations in hilly and mountainous orchards. The midstream segment, encompassing the pre-production, in-production and post-production stages, serves as the core scenario for value realization in the low-altitude economy. In the pre-production stage, high-resolution remote sensing imagery, combined with machine learning models such as extreme gradient boosting (XGBoost) and convolutional neural networks, enables detailed diagnostics of soil nutrients, micro-topography and vegetation cover. These insights support the precise planning of digital orchards. During the in-production stage, monitoring models based on indices such as normalized difference vegetation index (NDVI) and leaf area index (LAI) facilitate real-time assessment of tree vigor and early detection of pests and diseases, enhancing the management of plant health and growth conditions. Intelligent systems that integrate target recognition, path optimization and electric atomizing nozzles allow for precise, demand-driven application of pesticides and fertilizers, thereby improving resource efficiency and reducing environmental impact. Additionally, collaborative multi-UAV (unmanned aerial vehicle) operations and ground-aerial collaboration, optimized through genetic algorithms and digital twin models, further enhance task scheduling, flight path planning and energy utilization. In the post-production stage, drones equipped with robotic arms or vacuum suction grippers, coupled with thermal imaging, are increasingly effective in fruit identification and targeted harvesting, achieving higher levels of automation and reliability. At the same time, low-altitude logistics networks, supported by autonomous navigation and multi-sensor obstacle avoidance technologies, are addressing the last-mile challenges in cold-chain transportation. This significantly shortens the time window from field to sorting center, improving overall supply chain efficiency. At the downstream service level, the orchard low-altitude economy has evolved beyond single-equipment sales into a diversified service ecosystem. This emerging model centers on pilot training, drone insurance, equipment leasing and the integration of orchard tourism, forming a new type of business landscape. On one hand, standardized pilot training programs and operational quality evaluation systems have enhanced both talent development and safety assurance. On the other hand, risk control models developed by insurers based on operational data, along with "rent-to-own" financing schemes, have effectively lowered entry barriers for farmers. Moreover, the rise of integrated low-altitude agri-tourism models is steadily boosting the brand value of fruit products and generating new income streams through cultural and tourism-related activities. [Conclusions and Prospects] As a vital carrier of new-quality productive forces in agriculture, the orchard low-altitude economy has established a comprehensive industrial chain encompassing equipment manufacturing, operational systems and service platforms. This integrated structure is driving the transformation of orchard management toward greater intelligence, precision and sustainability. Despite current challenges such as limited equipment endurance and underdeveloped service systems, the sector is expected to achieve continuous breakthroughs through the development of high-payload aerial platforms, the integration of data-driven operational systems, the construction of diversified service ecosystems, and the refinement of relevant policies and standards. With the gradual opening of low-altitude airspace and the rapid iteration of core technologies, the orchard low-altitude economy is poised to become a key driver of agricultural modernization and rural revitalization.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Lightweight Detection and Recognition Model for Small Target Pests on Sticky Traps in Multi-Source Scenarios
    YANG Xinting, HU Huan, CHEN Xiao, LI Wenzheng, ZHOU Zijie, LI Wenyong
    Smart Agriculture    2025, 7 (1): 111-123.   DOI: 10.12133/j.smartag.SA202410019
    Abstract2010)   HTML46)    PDF(pc) (2514KB)(545)       Save

    [Objective] In crop cultivation and production, pests have gradually become one of the main issues affecting agricultural yield. Traditional models often focus on achieving high accuracy, however, to facilitate model application, lightweighting is necessary. The targets in yellow sticky trap images are often very small with low pixel resolution, so modifications in network structure, loss functions, and lightweight convolutions need to adapt to the detection of small-object pests. Ensuring a balance between model lightweighting and small-object pest detection is particularly important. To improve the detection accuracy of small target pests on sticky trap images from multi-source scenarios, a lightweight detection model named MobileNetV4+VN-YOLOv5s was proposed in this research to detect two main small target pests in agricultural production, whiteflies and thrips. [Methods] In the backbone layer of MobileNetV4+VN-YOLOv5s, an EM block constructed with the MobileNetV4 backbone network was introduced for detecting small, high-density, and overlapping targets, making it suitable for deployment on mobile devices. Additionally, the Neck layer of MobileNetV4+VN-YOLOv5s incorporates the GSConv and VoV-GSCSP modules to replace regular convolutional modules with lightweight design, effectively reducing the parameter size of the model while improving detection accuracy. Lastly, a normalized wasserstein distance (NWD)loss function was introduced into the framework to enhance the sensitivity for low-resolution small target pests. Extensive experiments including state-of-the-art comparison, ablation evaluation, performance analysis on image splitting, pest density and multi-source data were conducted. [Results and Discussions] Through ablation tests, it was concluded that the EM module and the VoV-GSCSP convolution module had significant effects in reducing the model parameter size and frame rate, the NWD loss function significantly improved the mean average precision (mAP) of the model. By comparing tests with different loss functions, the NWD loss function improves the mAP by 6.1, 10.8 and 8.2 percentage compared to the DIoU, GIoU and EIoU loss functions, respectively, so the addition of the NWD loss function achieved good results. Comparative performance tests were detected wiht different light weighting models, the experimental results showed that the mAP of the proposed MobileNetV4+VN-YOLOv5s model in three scenarios (Indoor, Outdoor, Indoor&Outdoor) was 82.5%, 70.8%, and 74.7%, respectively. Particularly, the MobileNetV4+VN-YOLOv5s model had a parameter size of only 4.2 M, 58% of the YOLOv5s model, the frame rate was 153.2 fps, an increase of 6.0 fps compared to the YOLOv5s model. Moreover, the precision and mean average precision reach 79.7% and 82.5%, which were 5.6 and 8.4 percentage points higher than the YOLOv5s model, respectively. Comparative tests were conducted in the upper scenarios based on four splitting ratios: 1×1, 2×2, 5×5, and 10×10. The most superior was the result by using 5×5 ratio in indoor scenario, and the mAP of this case reached 82.5%. The mAP of the indoor scenario was the highest in the low-density case, reaching 83.8%, and the model trained based on the dataset from indoor condition achieves the best performance. Comparative tests under different densities of pest data resulted in a decreasing trend in mAP from low to high densities for the MobileNetV4+VN-YOLOv5s model in the three scenarios. Based on the comparison of the experimental results of different test sets in different scenarios, all three models achieved the best detection accuracy on the IN dataset. Specifically, the IN-model had the highest mAP at 82.5%, followed by the IO-model. At the same time, the detection performance showed the same trend across all three test datasets: The IN model performed the best, followed by the IO-model, and the OUT-model performed the lowest. By comparing the tests with different YOLO improvement models, it was concluded that MobileNetV4+VN-YOLOv5s had the highest mAP, EVN-YOLOv8s was the second highest, and EVN-YOLOv11s was the lowest. Besides, after deploying the model to the Raspberry Pi 4B motherboard, it was concluded that the detection results of the YOLOv5s model had more misdetections and omissions than those of the MobileNetV4+VN-YOLOv5s model, and the time of the model was shortened by about 33% compared to that of the YOLOv5s model, which demonstrated that the model had a good prospect of being deployed in the application. [Conclusions] The MobileNetV4+VN-YOLOv5s model proposed in this study achieved a balance between lightweight design and accuracy. It can be deployed on embedded devices, facilitating practical applications. The model can provide a reference for detecting small target pests in sticky trap images under various multi-source scenarios.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Agricultural Big Data Governance: Key Technologies, Applications Analysis and Future Directions
    GUO Wei, WU Huarui, ZHU Huaji, WANG Feifei
    Smart Agriculture    2025, 7 (3): 17-34.   DOI: 10.12133/j.smartag.SA202503020
    Abstract1993)   HTML128)    PDF(pc) (4090KB)(716)       Save

    [Significance] To provide a reference for advancing high-quality agricultural production driven by data, this paper focuses on the issues of inconsistent acquisition standards, incomplete data collection, and ambiguous governance mechanisms in China's agricultural production data, examines existing governance models for agricultural production big data, and clarifies the technical pathways for realizing the value of data elements through the integrated and innovative application of key big data governance technologies and tools in practical scenarios. [Progress] From the perspective of agricultural production big data governance, this paper explores 17 types of big data governance technologies and tools across six core processes: Data acquisition and processing, data storage and exchange, data management, data analysis, large models, and data security guarantee. It conducts in-depth research on the application methods of big data governance technologies in agricultural production, revealing that: Remote sensing, unmanned aerial vehicle(UAV), Internet of Things (IoT), and terminal data acquisition and processing systems are already reatively mature; data storage and exchange system are developing rapidly, data management technologies remain in the initial stage; data analysis technologies have been widely applied; large model technology systems have taken initially shape; and data security assurance systems are gradually being into parctice. The above technologies are effectively applied in scenarios through tools and middleware such as data matching, computing power matching, network adaptation, model matching, scenario matching, and business configuration. This paper also analyzes the data governance throughout the entire agricultural production chain, including pre-production, in-production, and post-production, stages, as well as service cases involving different types of agricultural parks, research institutes and universities, production entities, and farmers. It demonstrates that sound data governance can provide sufficient planning and input analysis prior to production, helping planting entities in making rational plans. In production, it can provide data-driven guidance for key scenarios such as agricultural machinery operations and agricultural technical services, thereby fully supporting decision-making in the production process; and based on massive data, it can achieve reliable results in yield assessment and production benefit evaluation. Additionally, the paper introduces governance experience from national-level industrial parks, provincial-level agricultural science and technology parks, and some single-product entities, and investigates domestic and international technologies, practices, and tools related to agricultural production big data governance, indicating that there is a need to break through the business chains and service model of agricultural production across regions, themes, and scenarios. [Conclusions and Prospects] This paper presents insights into the future development directions of agricultural production big data governance, encompassing the promotion of standard formulation and implementation for agricultural production big data governance, the establishment of a universal resource pool for such governance, the expansion of diversified application scenarios, adaptation to the new paradigm of large-model- and massive-data-driven agricultural production big data governance, and the enhancement of security and privacy protection for agricultural production big data.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Detection Method of Effective Tillering of Rice in Field Based on Lightweight Ghost-YOLOv8 and Smart Phone
    CUI Jiale, ZENG Xiangfeng, REN Zhengwei, SUN Jian, TANG Chen, YANG Wanneng, SONG Peng
    Smart Agriculture    2024, 6 (5): 98-107.   DOI: 10.12133/j.smartag.SA202407012
    Abstract1989)   HTML95)    PDF(pc) (2128KB)(1190)       Save

    [Objective] The number of effective tillers per plant is one of the important agronomic traits affecting rice yield. In order to solve the problems of high cost and low accuracy of effective tiller detection caused by dense tillers, mutual occlusion and ineffective tillers in rice, a method for dividing effective tillers and ineffective tillers in rice was proposed. Combined with the deep learning model, a high-throughput and low-cost mobile phone App for effective tiller detection in rice was developed to solve the practical problems of effective tiller investigation in rice under field conditions. [Methods] The investigations of rice tillering showed that the number of effective tillers of rice was often higher than that of ineffective tillers. Based on the difference in growth height between effective and ineffective tillers of rice, a new method for distinguishing effective tillers from ineffective tillers was proposed. A fixed height position of rice plants was selected to divide effective tillers from ineffective tillers, and rice was harvested at this position. After harvesting, cross-sectional images of rice tillering stems were taken using a mobile phone, and the stems were detected and counted by the YOLOv8 model. Only the cross-section of the stem was identified during detection, while the cross-section of the panicle was not identified. The number of effective tillers of rice was determined by the number of detected stems. In order to meet the needs of field work, a mobile phone App for effective tiller detection of rice was developed for real-time detection. GhostNet was used to lighten the YOLOv8 model. Ghost Bottle-Neck was integrated into C2f to replace the original BottleNeck to form C2f-Ghost module, and then the ordinary convolution in the network was replaced by Ghost convolution to reduce the complexity of the model. Based on the lightweight Ghost-YOLOv8 model, a mobile App for effective tiller detection of rice was designed and constructed using the Android Studio development platform and intranet penetration counting. [Results and Discussions] The results of field experiments showed that there were differences in the growth height of effective tillers and ineffective tillers of rice. The range of 52 % to 55 % of the total plant height of rice plants was selected for harvesting, and the number of stems was counted as the number of effective tillers per plant. The range was used as the division standard of effective tillers and ineffective tillers of rice. The accuracy and recall rate of effective tillers counting exceeded 99%, indicating that the standard was accurate and comprehensive in guiding effective tillers counting. Using the GhostNet lightweight YOLOv8 model, the parameter quantity of the lightweight Ghost-YOLOv8 model was reduced by 43%, the FPS was increased by 3.9, the accuracy rate was 0.988, the recall rate was 0.980, and the mAP was 0.994. The model still maintains excellent performance while light weighting. Based on the lightweight Ghost-YOLOv8 model, a mobile phone App for detecting effective tillers of rice was developed. The App was tested on 100 cross-sectional images of rice stems collected under the classification criteria established in this study. Compared with the results of manual counting of effective tillers per plant, the accuracy of the App's prediction results was 99.61%, the recall rate was 98.76%, and the coefficient of determination was 0.985 9, indicating the reliability of the App and the established standards in detecting effective tillers of rice. [Conclusions] Through the lightweight Ghost-YOLOv8 model, the number of stems in the cross-sectional images of stems collected under the standard was detected to obtain the effective tiller number of rice. An Android-side rice effective tillering detection App was developed, which can meet the field investigation of rice effective tillering, help breeders to collect data efficiently, and provide a basis for field prediction of rice yield. Further research could supplement the cross-sectional image dataset of multiple rice stems to enable simultaneous measurement of effective tillers across multiple rice plants and improve work efficiency. Further optimization and enhancement of the App's functionality is necessary to provide more tiller-related traits, such as tiller angle.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Lightweight Daylily Grading and Detection Model Based on Improved YOLOv10
    JIN Xuemeng, LIANG Xiyin, DENG Pengfei
    Smart Agriculture    2024, 6 (5): 108-118.   DOI: 10.12133/j.smartag.SA202407022
    Abstract1980)   HTML74)    PDF(pc) (1532KB)(2551)       Save

    [Objective] In the agricultural production, accurately classifying dried daylily grades is a critical task with significant economic implications. However, current target detection models face challenges such as inadequate accuracy and excessive parameters when applied to dried daylily grading, limiting their practical application and widespread use in real-world settings. To address these issues, an innovative lightweight YOLOv10-AD network model was proposed. The model aims to enhance detection accuracy by optimizing the network structure and loss functions while reducing parameters and computational costs, making it more suitable for deployment in resource-constrained agricultural production environments. [Methods] The dried daylilies selected from the Qingyang region of Gansu province as the research subject. A large number of images of dried daylilies, categorized into three grades superior, medium, and inferior, were collected using mobile phones under varying lighting conditions and backgrounds. The images were carefully annotated and augmented to build a comprehensive dataset for dried daylily grade classification. YOLOv10 was chosen as the base network, and a newly designed backbone network called AKVanillaNet was introduced. AKVanillaNet combines AKConv (adaptive kernel convolution) with VanillaNet's deep learning and shallow inference mechanisms. The second convolutional layer in VanillaNet was replaced with AKConv, and AKConv was merged with standard convolution layers at the end of the training phase to optimize the model for capturing the unique shape characteristics of dried daylilies. This innovative design not only improved detection accuracy but also significantly reduced the number of parameters and computational costs. Additionally, the DysnakeConv module was integrated into the C2f structure, replacing the Bottleneck layer with a Bottleneck-DS layer to form the new C2f-DysnakeConv module. This module enhanced the model's sensitivity to the shapes and boundaries of targets, allowing the neural network to better capture the shape information of irregular objects like dried daylilies, further improving the model's feature extraction capability. The Powerful-IOU (PIOU) loss function was also employed, which introduced a target-size-adaptive penalty factor and a gradient adjustment function. This design guided the anchor box regression along a more direct path, helping the model better fit the data and improve overall performance. [Results and Discussions] The testing results on the dried daylily grade classification dataset demonstrated that the YOLOv10-AD model achieved a mean average precision (mAP) of 85.7%. The model's parameters, computational volume, and size were 2.45 M, 6.2 GFLOPs, and 5.0 M, respectively, with a frame rate of 156 FPS. Compared to the benchmark model, YOLOv10-AD improved mAP by 5.7% and FPS by 25.8%, while reducing the number of parameters, computational volume, and model size by 9.3%, 24.4%, and 9.1%, respectively. These results indicated that YOLOv10-AD not only improved detection accuracy but also reduced the model's complexity, making it easier to deploy in real-world production environments. Furthermore, YOLOv10-AD outperformed larger models in the same series, such as YOLOv10s and YOLOv10m. Specifically, the weight, parameters, and computational volume of YOLOv10-AD were only 31.6%, 30.5%, and 25.3% of those in YOLOv10s, and 15.7%, 14.8%, and 9.8% of YOLOv10m. Despite using fewer resources, YOLOv10-AD achieved a mAP increase of 2.4% over YOLOv10s and 1.9% over YOLOv10m. These findings confirm that YOLOv10-AD maintains high detection accuracy while requiring significantly fewer resources, making it more suitable for agricultural production environments where computational capacity may be limited. The study also examined the performance of YOLOv10-AD under different lighting conditions. The results showed that YOLOv10-AD achieved an average accuracy of 92.3% in brighter environments and 78.6% in darker environments. In comparison, the YOLOv10n model achieved 88.9% and 71.0% in the same conditions, representing improvements of 3.4% and 7.6%, respectively. These findings demonstrate that YOLOv10-AD has a distinct advantage in maintaining high accuracy and confidence in grading dried daylilies across varying lighting conditions. [Conclusions] The YOLOv10-AD network model proposed significantly reduces the number of parameters and computational costs without compromising detection accuracy. This model presents a valuable technical reference for intelligent classification of dried daylily grades in agricultural production environments, particularly where resources are constrained.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Embodied Intelligent Agricultural Robots: Key Technologies, Application Analysis, Challenges and Prospects
    WEI Peigang, CAO Shanshan, LIU Jifang, LIU Zhenhu, SUN Wei, KONG Fantao
    Smart Agriculture    2025, 7 (4): 141-158.   DOI: 10.12133/j.smartag.SA202505008
    Abstract1959)   HTML107)    PDF(pc) (2592KB)(225)       Save

    [Significance] Most current agricultural robots lack the ability to adapt to complex agricultural environments and still have limitations when facing variable, uncertain and unstructured agricultural scenarios. With the acceleration of agricultural intelligent transformation, embodied intelligence, as an intelligent system integrating environment perception, information cognition, autonomous decision-making and action, is giving agricultural robots stronger autonomous perception and complex environment adaptation ability, and becoming an important direction to promote the development of agricultural intelligent robots. In this paper, the technical system and application practice of embodied intelligence are sorted out systematically in the field of agricultural robots, its important value is revealed in improving environmental adaptability, decision-making autonomy and operational flexibility, and theoretical and practical references are provided to promote the development of agricultural robots to a higher level. [Progress] Firstly, the key supporting technologies of embodied intelligent agricultural robots are systematically sorted out, focusing on four aspects, namely, multimodal fusion perception, intelligent autonomous decision-making, autonomous action control and feedback autonomous learning. In terms of multimodal fusion perception, the modular artificial intelligence (AI) algorithm architecture and multimodal large model architecture are summarised. In terms of intelligent autonomous decision-making, two types of approaches based on artificial programming and dedicated task algorithms, and on large-scale pre-trained models are outlined. In terms of autonomous action control, three types of approaches based on the fusion of reinforcement learning and mainstream transformer, large model-assisted reinforcement learning, end-to-end mapping of semantics to action and action end-to-end mapping are summarised. In the area of feedback autonomous learning, the focus is on the related technological advances in the evolution of large model-driven feedback modules. Secondly, it analysed the typical application scenarios of embodied intelligence in agriculture, constructed a technical framework with "embodied perception - embodied cognition - embodied execution - embodied evolution" as the core, and discussed the implementation paths of each module according to the agricultural scenarios. The paths of each module are classified and discussed. Finally, the key technical bottlenecks and application challenges are analysed in depth, mainly including the high complexity of system integration, the significant gap between real and virtual data, and the limited ability of cross-scene generalisation. [Conclusions and Prospects] The future development trend of embodied intelligent agricultural robots is summarised and prospected from the construction of high-quality datasets and simulation platforms, the application of domain large model fusion, and the design of layered collaborative architectures, etc. It mainly focuses on the following aspects. Firstly, the construction of high-quality agricultural scenarios of embodied intelligence datasets is a key prerequisite to realise the embodied intelligence landing in agriculture. The development of embodied intelligent agricultural robots needs to rely on rich and accurate agricultural scene task datasets and highly realistic simulators to support physical interaction and behavioural learning. Secondly, the fusion of basic big model and agricultural domain model is the accelerator of intelligent perception and decision-making of agricultural robots. The in-depth fusion of general basic models in agricultural scenarios will bring stronger perception, understanding and reasoning capabilities to the embodied-intelligent agricultural robots. Thirdly, the "big model high-level planning + small model bottom-level control" architecture is an effective solution to balance intelligence and efficiency. Although large models have advantages in semantic understanding and global strategy planning, their reasoning latency and arithmetic demand can hardly meet the real-time and low-power requirements of agricultural robots. The use of large models for high-level task decomposition, scene semantic parsing and decision making, coupled with lightweight small models or traditional control algorithms to complete the underlying sensory response and motion control, can achieve the complementary advantages of the two.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Electrochemical Sensors for Plant Active Small Molecule Detection: A review
    ZHANG Le, LI Aixue, CHEN Liping
    Smart Agriculture    2025, 7 (3): 69-88.   DOI: 10.12133/j.smartag.SA202502023
    Abstract1938)   HTML50)    PDF(pc) (6524KB)(1081)       Save

    [Significance] Plant active small molecules play an indispensable role in plants. They form the basis of the core physiological mechanisms that regulate the plant growth and development and enhance resilience to environmental stress. Achieving highly precise quantitative analysis of these active small molecules is therefore vital for promoting precise management practice in the agricultural and accelerating the development of smart agriculture. Currently, various technologies exist for the detection and analysis of these small molecules in plants. Among them, electrochemical sensing platforms have attracted extensive attention due to their significant advantages, including high sensitivity, excellent selectivity, and low cost. These advantages enable them to effectively detect trace levels of various active small molecules in plant samples. They also have the potential for real-time and in-situ detection. [Progress] Based on a comprehensive review of relevant academic literature, this article systematically summarizes the current research progress and status of electrochemical sensors applied in detecting plant active small molecule. Based on this, the article further analyzes the core sensing mechanisms of different electrochemical sensors types, signal amplification technologies for enhancing detection performance, and their huge potential in practical applications. Furthermore, this paper explores a notable development direction in this field: Sensor technology is evolving from the traditional in vitro detection mode to more challenging in vivo detection and in-situ real-time monitoring methods. Meanwhile, the article particularly emphasizes and elaborates in detail the indispensable and significant role of nanomaterials in key links such as constructing high-performance sensing interfaces and significantly enhancing detection sensitivity and selectivity. Finally, it prospectively discusses the innovative integration of electrochemical sensors with cutting-edge flexible electronic technology and powerful artificial intelligence (AI)-based data analysis, along with their potential for broad application. [Conclusions and Prospects] This article comprehensively identifies and summarizes the core technical challenges that electrochemical sensors currently face in detecting plant active small molecule. In terms of environmental detection, due to the influence of the complex matrix within plants, the response signal of the sensor is prone to drift, and its stability and sensitivity show a decline. Regarding electrolytes, the external application of liquid electrolytes dilutes the target molecules concentration in plant samples, lowering the detection accuracy. Furthermore, the transition from principle development to mature productization and industrialization of electrochemical sensors is relatively lengthy, and there are few types of sensors available for the detection of plant physiological indicators: Limiting their application in actual agricultural production. On this basis, the article prospectively analyzes the key directions of future research. First, continuously improving sensor performance indicators such as sensitivity, selectivity and reliability. Second, exploring and optimizing electrolyte material systems with stronger adaptability to significantly improve detection accuracy and long-term stability. Third, promoting deeper integration and innovation of sensor technology with advanced micro-nano electronic technology and powerful AI algorithms. The core objective of this review is to provide a theoretical guidance framework for in-depth research and systematic performance optimization of electrochemical sensing technology for plant active small molecules, as well as practical guidance for the actual application of related sensors in complex plant substrate environments.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Chilli-YOLO: An Intelligent Maturity Detection Algorithm for Field-Grown Chilli Based on Improved YOLOv10
    SI Chaoguo, LIU Mengchen, WU Huarui, MIAO Yisheng, ZHAO Chunjiang
    Smart Agriculture    2025, 7 (2): 160-171.   DOI: 10.12133/j.smartag.SA202411002
    Abstract1930)   HTML98)    PDF(pc) (2545KB)(3078)       Save

    [Objective] In modern agriculture, the rapid and accurate detection of chillies at different maturity stages is a critical step for determining the optimal harvesting time and achieving intelligent sorting of field-grown chillies. However, existing target detection models face challenges in efficiency and accuracy when applied to the task of detecting chilli maturity, which limit their widespread use and effectiveness in practical applications. To address these challenges, a new algorithm, Chilli-YOLO, was proposed for achieving efficient and precise detection of chilli maturity in complex environments. [Methods] A comprehensive image dataset was collected, capturing chillis under diverse and realistic agricultural conditions, including varying lighting conditions, camera angles, and background complexities. These images were then meticulously categorized into four distinct maturity stages: Immature, transitional, mature, and dried. Data augmentation techniques were employed to expand the dataset and enhance the model's generalization capabilities. To develop an accurate and efficient chili maturity detection system, the YOLOv10s object detection network was chosen as the foundational architecture. The model's performance was further enhanced through strategic optimizations targeting the backbone network. Specifically, standard convolutional layers were replaced with Ghost convolutions. This technique generated more feature maps from fewer parameters, resulting in significant computational savings and improved processing speed without compromising feature extraction quality. Additionally, the C2f module was substituted with the more computationally efficient GhostConv module, further reducing redundancy and enhancing the model's overall efficiency. To improve the model's ability to discern subtle visual cues indicative of maturity, particularly in challenging scenarios involving occlusion, uneven lighting, or complex backgrounds, the partial self-attention (PSA) module within YOLOv10s was replaced with the second-order channel attention (SOCA) mechanism. SOCA leverages higher-order feature correlations to more effectively capture fine-grained characteristics of the chillis. This enabled the model to focus on relevant feature channels and effectively identify subtle maturity-related features, even when faced with significant visual noise and interference. Finally, to refine the precision of target localization and minimize bounding box errors, the extended intersection over union (XIoU) loss function was integrated into the model training process. XIoU enhances the traditional IoU loss by considering factors such as the aspect ratio difference and the normalized distance between the predicted and ground truth bounding boxes. By optimizing for these factors, the model achieved significantly improved localization accuracy, resulting in a more precise delineation of chillis in the images and contributing to the overall enhancement of the detection performance. The combined implementation of these improvements aimed to construct an effective approach to correctly classify the maturity level of chillis within the challenging and complex environment of a real-world farm. [Results and Discussion] The experimental results on the custom-built chilli maturity detection dataset showed that the Chilli-YOLO model performed excellently across multiple evaluation metrics. The model achieved an accuracy of 90.7%, a recall rate of 82.4%, and a mean average precision (mAP) of 88.9%. Additionally, the model's computational load, parameter count, model size, and inference time were 18.3 GFLOPs, 6.37 M, 12.6 M, and 7.3 ms, respectively. Compared to the baseline model, Chilli-YOLO improved accuracy by 2.6 percent point, recall by 2.8 percent point and mAP by 2.8 percent point. At the same time, the model's computational load decreased by 6.2 GFLOPs, the parameter count decreased by 1.67 M, model size reduced by 3.9 M. These results indicated that Chilli-YOLO strikes a good balance between accuracy and efficiency, making it capable of fast and precise detection of chilli maturity in complex agricultural environments. Moreover, compared to earlier versions of the YOLO model, Chilli-YOLO showed improvements in accuracy of 2.7, 4.8, and 5 percent point over YOLOv5s, YOLOv8n, and YOLOv9s, respectively. Recall rates were higher by 1.1, 0.3, and 2.3 percent point, and mAP increased by 1.2, 1.7, and 2.3 percent point, respectively. In terms of parameter count, model size, and inference time, Chilli-YOLO outperformed YOLOv5. This avoided the issue of YOLOv8n's lower accuracy, which was unable to meet the precise detection needs of complex outdoor environments. When compared to the traditional two-stage network Faster RCNN, Chilli-YOLO showed significant improvements across all evaluation metrics. Additionally, compared to the one-stage network SSD, Chilli-YOLO achieved substantial gains in accuracy, recall, and mAP, with increases of 16.6%, 12.1%, and 16.8%, respectively. Chilli-YOLO also demonstrated remarkable improvements in memory usage, model size, and inference time. These results highlighted the superior overall performance of the Chilli-YOLO model in terms of both memory consumption and detection accuracy, confirming its advantages for chilli maturity detection. [Conclusions] The proposed Chilli-YOLO model optimizes the network structure and loss functions, not only can significantly improve detection accuracy but also effectively reduce computational overhead, making it better suites for resource-constrained agricultural production environments. The research provides a reliable technical reference for intelligent harvesting of chillies in agricultural production environments, especially in resource-constrained settings.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    The Lightweight Bee Pollination Recognition Model Based On YOLOv10n-CHL
    CHANG Jian, WANG Bingbing, YIN Long, LI Yanqing, LI Zhaoxin, LI Zhuang
    Smart Agriculture    2025, 7 (3): 185-198.   DOI: 10.12133/j.smartag.SA202503033
    Abstract1905)   HTML23)    PDF(pc) (2411KB)(52)       Save

    [Objective] Bee pollination is pivotal to plant reproduction and crop yield, making its identification and monitoring highly significant for agricultural production. However, practical detection of bee pollination poses various challenges, including the small size of bee targets, their low pixel occupancy in images, and the complexity of floral backgrounds. Aimed to scientifically evaluate pollination efficiency, accurately detect the pollination status of flowers, and provide reliable data to guide flower and fruit thinning in orchards, ultimately supports the scientific management of bee colonies and enhances agricultural efficiency, a lightweight recognition model that can effectively overcome the above obstacles was proposed, thereby advancing the practical application of bee pollination detection technology in smart agriculture. [Methods] A specialized bee pollination dataset was constructed comprising three flower types: strawberry, blueberry, and chrysanthemum. High-resolution cameras were used to record videos of the pollination process, which were then subjected to frame sampling to extract representative images. These initial images underwent manual screening to ensure quality and relevance. To address challenges such as limited data diversity and class imbalance, a comprehensive data augmentation strategy was employed. Techniques including rotation, flipping, brightness adjustment, and mosaic augmentation were applied, significantly expanding the dataset's size and variability. The enhanced dataset was subsequently split into training and validation sets at an 8:2 ratio to ensure robust model evaluation. The base detection model was built upon an improved YOLOv10n architecture. The conventional C2f module in the backbone was replaced with a novel cross stage partial network_multi-scale edge information enhance (CSP_MSEE) module, which synergizes the cross-stage partial connections from cross stage partial network (CSPNet) with a multi-scale edge enhancement strategy. This design greatly improved feature extraction, particularly in scenarios involving fine-grained structures and small-scale targets like bees. For the neck, a hybrid-scale feature pyramid network (HS-FPN) was implemented, incorporating a channel attention (CA) mechanism and a dimension matching (DM) module to refine and align multi-scale features. These features were further integrated through a selective feature fusion (SFF) module, enabling the effective combination of low-level texture details and high-level semantic representations. The detection head was replaced with the lightweight shared detail enhanced convolutional detection head (LSDECD), an enhanced version of the Lightweight shared convolutional detection head (LSCD) detection head. It incorporated detail enhancement convolution (DEConv) from DEA-Net to improve the extraction of fine-grained bee features. Additionally, the standard convolution_groupnorm (Conv_GN) layers were replaced with detail enhancement convolution_ groupnorm (DEConv_GN), significantly reducing model parameters and enhancing the model's sensitivity to subtle bee behaviors. This lightweight yet accurate model design made it highly suitable for real-time deployment on resource-constrained edge devices in agricultural environments. [Results and Discussions] Experimental results on the three bee pollination datasets: strawberry, blueberry, and chrysanthemum, demonstrated the effectiveness of the proposed improvements over the baseline YOLOv10n model. The enhanced model achieved significant reductions in computational overhead, lowering the computational complexity by 3.1 GFLOPs and the number of parameters by 1.3 M. The computational cost of the improved model reached 5.1 GFLOPS, and the number of parameters was 1.3 M. These reductions contribute to improved efficiency, making the model more suitable for deployment on edge devices with limited processing capabilities, such as mobile platforms or embedded systems used in agricultural monitoring. In terms of detection performance, the improved model showed consistent gains across all three datasets. Specifically, the recall rates reached 82.6% for strawberry flowers, 84.0% for blueberry flowers, and 84.8% for chrysanthemum flowers. Corresponding mAP50 (Mean Average Precision at IoU threshold of 0.5) scores were 89.3%, 89.5%, and 88.0%, respectively. Compared to the original YOLOv10n model, these results marked respective improvements of 2.1% in recall and 1.7% in mAP50 on the strawberry dataset, 2.0% and 2.6% on the blueberry dataset, and 2.1% and 2.2% on the chrysanthemum dataset. [Conclusions] The proposed YOLOv10n-CHL lightweight bee pollination detection model, through coordinated enhancements at multiple architectural levels, achieved notable improvements in both detection accuracy and computational efficiency across multiple bee pollination datasets. The model significantly improved the detection performance for small objects while substantially reducing computational overhead, facilitating its deployment on edge computing platforms such as drones and embedded systems. This research could provide a solid technical foundation for the precise monitoring of bee pollination behavior and the advancement of smart agriculture. Nevertheless, the model's adaptability to extreme lighting and complex weather conditions remains an area for improvement. Future work will focus on enhancing the model's robustness in these scenarios to support its broader application in real-world agricultural environments.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Artificial Intelligence for Agricultural Science (AI4AS): Key Elements, Challenges and Pathways
    ZHAO Ruixue, YANG Xiao, ZHANG Dandan, LI Jiao, HUANG Yongwen, XIAN Guojian, KOU Yuantao, SUN Tan
    Smart Agriculture    2025, 7 (3): 35-47.   DOI: 10.12133/j.smartag.SA202502019
    Abstract1883)   HTML40)    PDF(pc) (1295KB)(114)       Save

    [Significance] Artificial intelligence for science (AI4S), as an emerging paradigm that deeply integrates artificial intelligence(AI) with scientific research, has triggered profound transformations in research methodologies. By accelerating scientific discovery through AI technologies, it is driving a shift in scientific research from traditional approaches reliant on experience and intuition to methodologies co-driven by data and AI. This transition has spurred innovative breakthroughs across numerous scientific domains and presents new opportunities for the transformation of agricultural research. With its powerful capabilities in data processing, intelligent analysis, and pattern recognition, AI can transcend the cognitive limitations of researchers in the field and is gradually emerging as an indispensable tool in modern agricultural scientific research, injecting new impetus into the intelligent, efficient, and collaborative development of agricultural scientific research. [Progress] This paper systematically reviews the current advancements in AI4S and its implications for agricultural research. It reveals that AI4S has triggered a global race among countries around the world vying for the commanding heights of a new round of scientific and technological strategies. Developed nations in Europe and America, for instance, have laid out the frontier areas in AI4S and rolled out relevant policies. Meanwhile, some top universities and research institutions are accelerating related research, and tech giants are actively cultivating related industries to advance the application and deployment of AI technologies in scientific research. In recent years, AI4S has achieved remarkable development, showing great potential across multiple disciplines and finding widespread application in data mining, model construction, and result prediction. In the field of agricultural scientific research, AI4S has played an important role in accelerating multi-disciplinary integration, promoting the improvement of the scientific research efficiency, facilitating the breakthrough of complex problems, driving the transformation of the scientific research paradigm, and upgrading scientific research infrastructure. The continuous progress of information technology and synthetic biology has made the interdisciplinary integration of agriculture and multiple disciplines increasingly closer. The deep integration of AI and agricultural scientific research not only improves the application level of AI in the agricultural field but also drives the transformation of traditional agricultural scientific research models towards intelligence, data-driven, and collaborative directions, providing new possibilities for agricultural scientific and technological innovation. The new agricultural digital infrastructure is characterized by intelligent data collection, edge computing power deployment, high-throughput network transmission, and distributed storage architecture, aiming to break through the bottlenecks of traditional agricultural scientific research facilities in terms of real-time performance, collaboration, and scalability. Taking emerging disciplines such as Agrinformatics and climate-focused Agriculture-Forestry-AI (AgFoAI) as examples, they focus on using AI technology to analyze agricultural data, construct crop growth models, and climate change models, etc., to promote the development and innovation of agricultural scientific research. [Conclusions and Prospects] With its robust capabilities in data processing, intelligent analysis, and pattern recognition, AI is increasingly becoming an indispensable tool in modern agricultural scientific research. To address emerging demands, core domains, and research processes in agricultural research, the concept of agricultural intelligent research is proposed, characterized by human-machine collaboration and interdisciplinary integration. This paradigm employs advanced data analytics, pattern recognition, and predictive modeling to perform in-depth mining and precise interpretation of multidimensional, full-lifecycle, large-scale agricultural datasets. By comprehensively unraveling the intrinsic complexities and latent patterns of research subjects, it autonomously generates novel, scientifically grounded, and high-value research insights, thereby driving agricultural research toward greater intelligence, precision, and efficiency. The framework's core components encompass big science infrastructure (supporting large-scale collaborative research), big data resources (integrating heterogeneous agricultural datasets), advanced AI model algorithms (enabling complex simulations and predictions), and collaborative platforms (facilitating cross-disciplinary and cross-institutional synergy). Finally, in response to challenges related to data resources, model capabilities, research ecosystems, and talent development, actionable pathways and concrete recommendations are outlined from the perspectives of top-level strategic planning, critical technical ecosystems, collaborative innovation ecosystems, disciplinary system construction, and interdisciplinary talent cultivation, aiming to establish a new AI4S-oriented agricultural research framework.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Rice Leaf Disease Image Enhancement Based on Improved CycleGAN
    YAN Congkuan, ZHU Dequan, MENG Fankai, YANG Yuqing, TANG Qixing, ZHANG Aifang, LIAO Juan
    Smart Agriculture    2024, 6 (6): 96-108.   DOI: 10.12133/j.smartag.SA202407019
    Abstract1849)   HTML52)    PDF(pc) (1744KB)(326)       Save

    Objective Rice diseases significantly impact both the yield and quality of rice production. Automatic recognition of rice diseases using computer vision is crucial for ensuring high yields, quality, and efficiency. However, rice disease image recognition faces challenges such as limited availability of datasets, insufficient sample sizes, and imbalanced sample distributions across different disease categories. To address these challenges, a data augmentation method for rice leaf disease images was proposed based on an improved CycleGAN model in this reseach which aimed to expand disease image datasets by generating disease features, thereby alleviating the burden of collecting real disease data and providing more comprehensive and diverse data to support automatic rice disease recognition. Methods The proposed approach built upon the CycleGAN framework, with a key modification being the integration of a convolutional block attention module (CBAM) into the generator's residual module. This enhancement strengthened the network's ability to extract both local key features and global contextual information pertaining to rice disease-affected areas. The model increased its sensitivity to small-scale disease targets and subtle variations between healthy and diseased domains. This design effectively mitigated the potential loss of critical feature information during the image generation process, ensuring higher fidelity in the resulting images. Additionally, skip connections were introduced between the residual modules and the CBAM. These connections facilitate improved information flow between different layers of the network, addressing common issues such as gradient vanishing during the training of deep networks. Furthermore, a perception similarity loss function, designed to align with the human visual system, was incorporated into the overall loss function. This addition enabled the deep learning model to more accurately measure perceptual differences between the generated images and real images, thereby guiding the network towards producing higher-quality samples. This adjustment also helped to reduce visual artifacts and excessive smoothing, while concurrently improving the stability of the model during the training process. To comprehensively evaluate the quality of the rice disease images generated by the proposed model and to assess its impact on disease recognition performance, both subjective and objective evaluation metrics were utilized. These included user perception evaluation (UPE), structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), and the performance of disease recognition within object detection frameworks. Comparative experiments were conducted across multiple GAN models, enabling a thorough assessment of the proposed model's performance in generating rice disease images. Additionally, different attention mechanisms, including efficient channel attention (ECA), coordinate attention (CA), and CBAM, were individually embedded into the generator's residual module. These variations allowed for a detailed comparison of the effects of different attention mechanisms on network performance and the visual quality of the generated images. Ablation studies were further performed to validate the effectiveness of the CBAM residual module and the perception similarity loss function in the network's overall architecture. Based on the generated rice disease samples, transfer learning experiments were conducted using various object detection models. By comparing the performance of these models before and after transfer learning, the effectiveness of the generated disease image data in enhancing the performance of object detection models was empirically verified. Results and Discussions The rice disease images generated by the improved CycleGAN model surpassed those produced by other GAN variants in terms of image detail clarity and the prominence of disease-specific features. In terms of objective quality metrics, the proposed model exhibited a 3.15% improvement in SSIM and an 8.19% enhancement in PSNR compared to the original CycleGAN model, underscoring its significant advantage in structural similarity and signal-to-noise ratio. The comparative experiments involving different attention mechanisms and ablation studies revealed that embedding the CBAM into the generator effectively increased the network's focus on critical disease-related features, resulting in more realistic and clearly defined disease-affected regions in the generated images. Furthermore, the introduction of the perception similarity loss function substantially enhanced the network's ability to perceive and represent disease-related information, thereby improving the visual fidelity and realism of the generated images. Additionally, transfer learning applied to object detection models such as YOLOv5s, YOLOv7-tiny, and YOLOv8s led to significant improvements in disease detection performance on the augmented dataset. Notably, the detection accuracy of the YOLOv5s model increased from 79.7% to 93.8%, representing a considerable enhancement in both generalization ability and robustness. This improvement also effectively reduced the rates of false positives and false negatives, resulting in more stable and reliable performance in rice disease detection tasks. Conclusions The rice leaf disease image generation method based on the improved CycleGAN model, as proposed in this study, effectively transforms images of healthy leaves into those depicting disease symptoms. By addressing the challenge of insufficient disease samples, this method significantly improves the disease recognition capabilities of object detection models. Therefore, it holds considerable application potential in the domain of leaf disease image augmentation and offers a promising new direction for expanding datasets of disease images for other crops.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Intelligent Q&A Method for Crop Diseases and Pests Using LLM Augmented by Adaptive Hybrid Retrieval
    YANG Jun, YANG Wanxia, YANG Sen, HE Liang, ZHANG Di
    Smart Agriculture    2026, 8 (1): 52-61.   DOI: 10.12133/j.smartag.SA202506026
    Abstract1824)   HTML50)    PDF(pc) (1647KB)(145)       Save

    [Objective] Extracting valuable knowledge from vast amounts of dispersed, heterogeneous, and unstructured agricultural big data, correlating and structuring it, and enhancing large models to form intelligent question-answering systems enables the effective delivery of services to all in agriculture. This approach can rapidly advance the scientific and precision-based development of agricultural production. Existing agricultural Q&A systems lack enough semantic understanding of complex symptoms, while general-purpose large language models (LLMs) produce factual hallucinations due to incomplete training data coverage. The research aims to address the issues of insufficient scale and low quality in the construction of knowledge bases in the agricultural field. [Methods] First, disease and pest data were collected along for five typical crops: wheat, rice, corn, potatoes, and cotton. Using manual verification methods, outliers were precisely identified and removed, ultimately yielding 87 901 unstructured data entries. Then, a few-shot learning model was employed to extract entities defined in the pattern layer, and these entities were aligned with the semantic vectors of Bert and LLM prompt engineering, ultimately yielding a triplet knowledge base of 916 239 entries for knowledge retrieval. A knowledge retrieval-augmented LLM approach for intelligent Q&A on crop diseases and pests was proposed, specifically the adaptive hybrid retrieval-augmented generation (AHR-RAG) approach. Firstly, an overlapping mechanism was introduced during fixed-length segmentation to mitigate semantic fragmentation. Simultaneously, vector semantic similarity was used to match highly related text blocks with the topic for optimization and storage. Then, single-hop and multi-hop retrieval were designed based on the complexity of the problem. Single-hop retrieval used the BM25 algorithm to match information extracted from the query with document content in the Elasticsearch index, feeding the results into the LLM to enhance answer generation. Multi-hop retrieval first converted user queries into structured conditions and semantic vector representations. Results retrieved from different knowledge bases were then fused using reciprocal rank fusion (RRF) and fed into the LLM. [Results and Discussions] The proposed method was experimentally compared with multiple baseline approaches, including different query types and complexity queries. The results demonstrated that the proposed method achieved accuracy and F1 improvements of 0.193 and 0.170, respectively, on the Qwen1.5-7B-Chat model. Compared to the improved methods Self-RAG and Adaptive-RAG, AHR-RAG maintained low response times while achieving F1 improvements of 0.05 and 0.021, respectively, with an accuracy as high as 0.896. For multi-type question-answering tasks, compared to the Naive-RAG method that relied solely on prior knowledge, the AHR-RAG approach achieved accuracy improvements of 0.231, 0.123, and 0.157 for comparison, judgment and selection query types, respectively. For parsing complex semantics, AHR-RAG also demonstrated significant advantages. In single-hop queries, its accuracy reached 0.921, representing a 0.029 improvement over Adaptive-RAG. In multi-hop query scenarios, its accuracy reached 0.748, achieving gains of 0.082 and 0.059 over Self-RAG and Adaptive-RAG respectively. In retrieval-augmented generation, AHR-RAG achieved a 0.013 increase in accuracy and a 0.009 improvement in F1 by optimizing prompt strategies, compared to directly feeding retrieval results to the model for output. [Conclusions] This research demonstrates strong adaptability to diverse query types and excels at reasoning complex queries such as multi-hop searches. It delivers significant advantages in answer generation accuracy, relevance, and comprehensiveness, producing responses with enhanced logical coherence and richer content. Future work will explore the integration of multimodal knowledge bases.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Lightweight Apple Instance Segmentation Algorithm Based on SSW-YOLOv11n for Complex Orchard Environments
    HAN Wenkai, LI Tao, FENG Qingchun, CHEN Liping
    Smart Agriculture    2025, 7 (5): 114-123.   DOI: 10.12133/j.smartag.SA202505002
    Abstract1816)   HTML69)    PDF(pc) (3074KB)(108)       Save

    [Objective] In complex orchard environments, accurate fruit detection and segmentation are critical for autonomous apple-picking robots. Environmental factors severely degrade fruit visibility, challenging instance segmentation models across diverse field conditions. Apple-picking robots operate on embedded edge-computing platforms with stringent constraints on processing power, memory, and energy consumption. Limited computational resources preclude high-complexity deep-learning architectures, requiring segmentation models to balance real-time throughput and resource efficiency. This study introduces SSW-YOLOv11n, a lightweight instance segmentation model derived from YOLOv11n and tailored to orchard environments. SSW-YOLOv11n maintains high mask accuracy under adverse conditions—variable lighting, irregular occlusion, and background clutter—while delivering accelerated inference on resource-limited edge devices through three core design enhancements. [Methods] The SSW-YOLOv11n model first introduced GSConv and VoVGSCSP modules into its neck network, thereby constructing a highly compact yet computationally efficient "Slim-Neck" architecture. By integrating GSConv—an operation that employs grouped spatial convolutions and channel-shuffle techniques—and VoVGSCSP—a cross-stage partial module optimized for balanced depth and width—the model substantially reduced its overall floating-point operations while concurrently enhancing the richness of its feature representations. This optimized neck design facilitated more effective multi-scale information fusion, ensuring that semantic features corresponding to target regions were extracted comprehensively, all without compromising the model's lightweight nature. Subsequently, the authors embedded the SimAM self-attention mechanism at multiple output interfaces between the backbone and neck subnets. SimAM leveraged a parameter-free energy-based weighting strategy to dynamically amplify critical feature responses and suppress irrelevant background activations, thereby augmenting the model's sensitivity to fruit targets amid complex, cluttered orchard scenes. Finally, the original bounding-box regression loss was replaced with Wise-IoU, which incorporated a dynamic weighting scheme based on both center-point distance and geometric discrepancy factors. This modification further refined the regression process, improving localization precision and stability under variable environmental conditions. Collectively, these three innovations synergistically endowed the model with superior instance-segmentation performance and deployment adaptability, offering a transferable design paradigm for implementing deep-learning-based vision systems on resource-constrained agricultural robots. [Results and Discussions] Experimental results demonstrated that SSW-YOLOv11n achieved Box mAP50 and Mask mAP50 of 76.3% and 76.7%, respectively, representing improvements of 1.7 and 2.4 percentage points over the baseline YOLOv11n model. The proposed model reduced computational complexity from 10.4 to 9.1 GFLOPs (12.5% reduction) and achieved a model weight of 4.55 MB compared to 5.89 MB for the baseline (22.8% reduction), demonstrating significant efficiency gains. These results indicate that the synergistic integration of lightweight architecture design and attention mechanisms effectively addresses the trade-off between model complexity and segmentation accuracy. Comparative experiments showed that SSW-YOLOv11n outperformed Mask R-CNN, SOLO, YOLACT, and YOLOv11n with Mask mAP50 improvements of 23.2, 20.3, 21.4, and 2.4 percentage points, respectively, evidencing substantial advantages in segmentation precision within unstructured orchard environments. The superior performance over traditional methods suggests that the proposed approach successfully adapts deep learning architectures to agricultural scenarios with complex environmental conditions. Edge deployment testing on NVIDIA Jetson TX2 platform achieved 29.8 FPS inference rate, representing an 18.7% improvement over YOLOv11n (25.1 FPS), validating the model's real-time performance and suitability for resource-constrained agricultural robotics applications. [Conclusions] SSW-YOLOv11n effectively enhanced fruit-target segmentation accuracy while reducing computational overhead, thus providing a robust technical foundation for the practical application of autonomous apple-picking robots. By addressing the dual imperatives of high-precision perception and efficient inference within constrained hardware contexts, the proposed approach advanced the state of the art in intelligent agricultural robotics and offered a scalable solution for large-scale orchard automation.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Intelligent Inspection Path Planning Algorithm for Large-Scale Cattle Farms
    CHEN Ruotong, LIU Jifang, ZHANG Zhiyong, MA Nan, WEI Peigang, WANG Yi, YANG Yantao
    Smart Agriculture    2026, 8 (1): 178-191.   DOI: 10.12133/j.smartag.SA202504004
    Abstract1788)   HTML20)    PDF(pc) (4660KB)(96)       Save

    [Objective] Timely detection and early warning of livestock health issues are critical for green and efficient management within large-scale cattle farms. Traditional manual inspections are time-consuming, labor-intensive, and prone to missed or erroneous detections. Robotic inspections offer significant advantages including all-weather operation, high precision, high efficiency, and low cost. However, existing path planning approaches predominantly focus on dynamic obstacle avoidance and fixed target point inspection path, often failing to address two key challenges in dynamic large-scale farm environments: global traversal of individual large livestock (e.g., beef cattle, dairy cows) and accessibility of local areas compromised by dynamic obstacles. This study aims to overcome the limitations of existing robotic inspection systems in large-scale cattle farms, specifically addressing the lack of comprehensive inspection capability for dynamic individuals, excessive path redundancy, and insufficient proactive obstacle avoidance capability. [Methods] A global-local optimization algorithm was proposed for large-scale cattle farm intelligent inspection path planning, which integrated the traveling salesman problem (TSP), A* and dynamic window approach (DWA), and solved the problems of global multi-objective individual traversal, path redundancy and local passability with proactive obstacle avoidance in dynamic cattle farm scenarios. ​​For global traversal optimization, a global path planning algorithm was introduced which combined ​​improved TSP​​ and ​​optimized A*. Specifically, the inspection status list tracking breeding sheds and individual cattle was maintained to enhance the TSP's Nearest Neighbor Algorithm, dynamically updating targets to avoid re-visits. A dynamic priority mechanism optimized multi-objective inspection, determining the optimal visitation sequence across barns and dynamic paths within barns. The data structure of the A* algorithm was optimized, a diagonal distance heuristic function was introduced to replace Manhattan distance, which more accurately reflected the movement cost in eight directions. The path obtained by the A* algorithm through greedy strategy was simplified, and Bresenham's line algorithm was used to check whether there were obstacles in the straight line field of view. If there were no obstacles, redundant inflection points were removed to construct an efficient moving path between sheds. For local passability optimization, an enhanced DWA-based local path was proposed for planning algorithm. The dynamic safety threshold of obstacle size was introduced to improve the DWA. When the inspection robot judged that the size of the obstacle in the local accessible area was too large and the robot was difficult to pass, it would actively avoid or detour in advance to ensure the safe avoidance of large obstacles in narrow passages. The improved DWA also increased the task progress potential field​​, drived the robot to move to the breeding shed to be visited with the attractive force field model, balanced the local obstacle avoidance and global inspection efficiency, and realized the real-time judgment of local area passability caused by dynamic obstacles and proactive obstacle avoidance in advance. [Results and Discussions] The optimized A* algorithm's data structures significantly improved search efficiency. The diagonal distance heuristic and greedy strategy substantially enhanced path smoothness. Compared to the traditional A*, the improved A* achieved average reductions of 90.06% in planning time, 85.13% in path turns, and 1.83% in path length. The global inspection algorithm combining improved TSP and optimized A* achieved 100% average coverage of individual cattle. Inspection path length and time were reduced by 17.99% and 20.85%, respectively, compared to the classic ant colony optimization (ACO) algorithm, demonstrating superior efficiency in dynamic multi-objective inspection scenarios. The improved DWA successfully enabled proactive judgment of local path passability based on obstacle size. By adjusting the robot's linear velocity, angular velocity, and attitude angle in real time, the algorithm achieved robust proactive obstacle avoidance. The inspection robot would reduce the linear velocity in advance when encountering obstacles, and realize proactive obstacle avoidance by adjusting the attitude angle. Simulation experiments confirmed that robots equipped with the improved DWA effectively navigated around unknown static and dynamic obstacles while maintaining global path-tracking capability. [Conclusions] The global inspection algorithm combining improved TSP and optimized A*, utilizing dynamic inspection status lists and path optimization techniques, achieved global inspection coverage of individual cattle and could significantly improve inspection quality and efficiency. The local inspection algorithm based on improved DWA, incorporating obstacle size dynamic safety threshold and task progress, achieved real-time judgment of local passability and proactive obstacle avoidance, ensuring safe robot navigation in complex environments. The global-local co-optimization framework demonstrated adaptability to the dynamic farm environment, enabling the timely completion of individual traversal tasks, and providing a robust solution for intelligent inspection in large-scale cattle operations. Future work involves integrating the proposed path planning algorithm with simultaneous localization and mapping (SLAM), cattle identification, distance detection systems on inspection robot platforms, and conducting extensive field tests within operational cattle farms. Exploring multi-robot collaborative inspection frameworks and incorporating the Vision-and-Language Navigation model to enhance environmental perception and anomaly-handling capabilities are promising directions for adapting to the complexities of even larger-scale farming scenarios.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Object Detection Method of Maize Ears Within Canopy Based on CornYOLO
    GAO Guangfu, WANG Qilei, SONG Liwen, FENG Haikuan, SHI Lei, YANG Hao, LIU Yang, YUE Jibo
    Smart Agriculture    2026, 8 (1): 167-177.   DOI: 10.12133/j.smartag.SA202509005
    Abstract1782)   HTML25)    PDF(pc) (2701KB)(70)       Save

    [Objective] As a major grain crop, maize plays a critical role in global food security. The ears of maize serves as a key phenotypic trait, providing essential information on the plant's physiological and agronomic status. Its morphological characteristics, size, and color effectively reflect the plant's growth status and potential yield. Therefore, accurately acquiring images of maize ears in the field across different growth stages is crucial for breeding research and yield prediction. Traditional field detection of maize ears relies heavily on manual labor, which is not only inefficient and labor-intensive but also struggles to meet the high-throughput demands of modern precision breeding programs. There is an urgent need for efficient, automated detection technologies that can operate reliably under real-world field conditions. To address the requirement for efficient acquisition of maize ears phenotypic traits in field breeding work, the objective of this research is to develop a robust object detection solution suitable for large-scale field environments. An improved CornYOLO model based on the YOLO11n (You Only Look Once) architecture was designed to enhance the detection accuracy and efficiency of maize ears in complex field environments. [Methods] Image data were acquired using an unmanned ground vehicle (UGV) equipped with a high-resolution panoramic camera, which traversed multiple experimental plots under varying lighting and growth conditions. A dataset containing 1 152 annotated samples was constructed, covering diverse ear morphologies and occlusion scenarios. Dynamic data augmentation techniques were applied during training to enhance the model's generalization capability. Three key enhancements were introduced to the YOLO11n detection framework. First, a cross stage partial network with dynamic pointwise spatial attention (C2PDA) module was designed to replace the cross stage partial with pointwise spatial attention (C2PSA) module in the YOLO11 backbone network. This module enhanced spatial discriminability and channel sensitivity in feature representation through the collaborative integration of a dynamic channel weighting mechanism and position-aware modeling. It significantly improves the model's performance in identifying maize ears under challenging field conditions such as occlusion of stems and leaves and multi-scale target distribution. Second, the spatial pyramid pooling-fast (SPPF) module in the original model was replaced with an feature refinement module (FRM ) to optimize multi-scale feature fusion. The FRM functions via directional feature decomposition and an adaptive attention mechanism. It captures fine-grained spatial structural information through horizontal and vertical bidirectional pooling and combines spatial-channel cooperative attention for dynamic feature calibration, thereby improving recognition accuracy across varying ear sizes and complex backgrounds. Finally, the unified intersection over union (UIoU) loss function was introduced to optimize bounding box regression accuracy. UIoU is an innovative loss function that emphasizes weight allocation among prediction boxes of different qualities. It adaptively adjusted the weight of each prediction box's loss term based on the IoU value or its monotonic function, assigning higher weights to lower-quality predictions to prioritize their optimization, while reducing weights for high-quality boxes to prevent over-optimization. [Results and Discussions] Experimental results demonstrate that CornYOLO achieved a mAP@50 of 89.3% on the validation set, with the F1-Score increasing by 2.5 percentage points. Compared to widely used lightweight models including YOLOv3-tiny, YOLOv5n, YOLOv8n, YOLOv10n, real-time detection transformer (RT-DETR) and YOLO13n, CornYOLO showed significantly superior detection performance in complex field environments, with mAP@50 improvements of 2.2, 1.9, 1.8, 5.7, 12.6 and 2.4 percentage points, respectively. These results fully validate that CornYOLO can efficiently and accurately extract maize ear images under field conditions, providing a technical foundation for precise phenotypic evaluation and yield prediction. Furthermore, ablation studies were conducted: Introducing the C2PDA module improved the model's mAP@50 by 0.5 percentage points and the F1-Score by 0.5 percentage points. However, after incorporating the FRM module, which successfully enhanced multi-scale detection performance and increased the F1-Score by 1.5 percentage points, the integration of these two modules resulted in the generation of a small number of low-quality detection boxes. The original loss function was inefficient in optimizing such boxes, resulting in no improvement in mAP@50 after the modification. To address this issue, the UIoU loss function was introduced. By dynamically adjusting weight assignments based on prediction quality, it significantly improved the regression performance for low-quality detection boxes, thereby enhancing the localization accuracy and convergence stability of the model in dense target scenarios. The final CornYOLO model exhibited excellent overall performance: Compared to the original YOLO11n, the F1-Score increased by 2.5 percentage points and mAP@50 improved by 1.1 percentage points. The experimental results fully demonstrate that CornYOLO effectively enhances the detection capability for maize ears in complex field environments compared to the baseline YOLO11n model. [Conclusions] The CornYOLO model proposed in this study incorporates three key components: C2PDA, FRM, and UIoU, which enhances model convergence and localization performance in dense and occluded scenes, enables the model to effectively and precisely identify maize ears under practical conditions, thereby providing reliable technical support for phenotypic analysis and yield prediction in maize breeding. Future work will focus on extending the model to other crop types and further optimizing inference efficiency for real-time deployment on mobile platforms.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Detection Method of Apple Alternaria Leaf Spot Based on Deep-Semi-NMF
    FU Zhuojun, HU Zheng, DENG Yangjun, LONG Chenfeng, ZHU Xinghui
    Smart Agriculture    2024, 6 (6): 144-154.   DOI: 10.12133/j.smartag.SA202409001
    Abstract1759)   HTML42)    PDF(pc) (1901KB)(289)       Save

    [Objective] Apple Alternaria leaf spot can easily lead to premature defoliation of apple tree leaves, thereby affecting the quality and yield of apples. Consequently, accurately detecting of the disease has become a critical issue in the precise prevention and control of apple tree diseases. Due to factors such as backlighting, traditional image segmentation-based methods for detecting disease spots struggle to accurately identify the boundaries of diseased areas against complex backgrounds. There is an urgent need to develop new methods for detecting apple Alternaria leaf spot, which can assist in the precise prevention and control of apple tree diseases. [Methods] A novel detection method named Deep Semi-Non-negative Matrix Factorization-based Mahalanobis Distance Anomaly Detection (DSNMFMAD) was proposed, which combines Deep Semi-Non-negative Matrix Factorization (DSNMF) with Mahalanobis distance for robust anomaly detection in complex image backgrounds. The proposed method began by utilizing DSNMF to extract low-rank background components and sparse anomaly features from the apple Alternaria leaf spot images. This enabled effective separation of the background and anomalies, mitigating interference from complex background noise while preserving the non-negativity constraints inherent in the data. Subsequently, Mahalanobis distance was employed, based on the Singular Value Decomposition (SVD) feature subspace, to construct a lesion detector. The detector identified lesions by calculating the anomaly degree of each pixel in the anomalous regions. The apple tree leaf disease dataset used was provided by PaddlePaddle AI-Studio. Each image in the dataset has a resolution of 512×512 pixels, in RGB color format, and was in JPEG format. The dataset was captured in both laboratory and natural environments. Under laboratory conditions, 190 images of apple leaves with spot-induced leaf drop were used, while 237 images were collected under natural conditions. Furthermore, the dataset was augmented with geometric transformations and random changes in brightness, contrast, and hue, resulting in 1 145 images under laboratory conditions and 1 419 images under natural conditions. These images reflect various real-world scenarios, capturing apple leaves at different stages of maturity, in diverse lighting conditions, angles, and noise environments. This diversed dataset ensured that the proposed method could be tested under a wide range of practical conditions, providing a comprehensive evaluation of its effectiveness in detecting apple Alternaria leaf spot. [Results and Discussions] DSNMFMAD demonstrated outstanding performance under both laboratory and natural conditions. A comparative analysis was conducted with several other detection methods, including GRX (Reed-Xiaoli detector), LRX (Local Reed-Xiaoli detector), CRD (Collaborative-Representation-Based Detector), LSMAD (LRaSMD-Based Mahalanobis Distance Detector), and the deep learning model Unet. The results demonstrated that DSNMFMAD exhibited superior performance in the laboratory environment. The results demonstrated that DSNMFMAD attained a recognition accuracy of 99.8% and a detection speed of 0.087 2 s/image. The accuracy of DSNMFMAD was found to exceed that of GRX, LRX, CRD, LSMAD, and Unet by 0.2%, 37.9%, 10.3%, 0.4%, and 24.5%, respectively. Additionally, the DSNMFMAD exhibited a substantially superior detection speed in comparison to LRX, CRD, LSMAD, and Unet, with an improvement of 8.864, 107.185, 0.309, and 1.565 s, respectively. In a natural environment, where a dataset of 1 419 images of apple Alternaria leaf spot was analysed, DSNMFMAD demonstrated an 87.8% recognition accuracy, with an average detection speed of 0.091 0 s per image. In this case, its accuracy outperformed that of GRX, LRX, CRD, LSMAD, and Unet by 2.5%, 32.7%, 5%, 14.8%, and 3.5%, respectively. Furthermore, the detection speed was faster than that of LRX, CRD, LSMAD, and Unet by 2.898, 132.017, 0.224, and 1.825 s, respectively. [Conclusions] The DSNMFMAD proposed in this study was capable of effectively extracting anomalous parts of an image through DSNMF and accurately detecting the location of apple Alternaria leaf spot using a constructed lesion detector. This method achieved higher detection accuracy compared to the benchmark methods, even under complex background conditions, demonstrating excellent performance in lesion detection. This advancement could provide a valuable technical reference for the detection and prevention of apple Alternaria leaf spot.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Prediction and Mapping of Soil Total Nitrogen Using GF-5 Image Based on Machine Learning Optimization Modeling
    LIU Liqi, WEI Guangyuan, ZHOU Ping
    Smart Agriculture    2024, 6 (5): 61-73.   DOI: 10.12133/j.smartag.SA202405011
    Abstract1748)   HTML58)    PDF(pc) (3325KB)(1108)       Save

    [Objective] Nitrogen in soil is an absolutely crucial element for plant growth. Insufficient nitrogen supply can severely affect crop yield and quality, while excessive use of nitrogen fertilizers can lead to significant environmental issues such as water eutrophication and groundwater pollution. Therefore, large-scale, rapid detection of soil nitrogen content and precise fertilization are of great importance for smart agriculture. In this study, the hyperspectral data from the GF-5 satellite was emploied, and the various machine learning algorithms introduced to establish a prediction model for soil total nitrogen (TN) content and a distribution map of soil TN content was generated in the study area, aiming to provide scientific evidence for intelligent monitoring in smart agriculture. [Method] The study area was the Jian Sanjiang Reclamation Area in Fujin city, Heilongjiang province. Fieldwork involved the careful collection of 171 soil samples, obtaining soil spectral data, chemical analysis data of soil TN content, and the GF-5 hyperspectral data. Among these samples, 140 were randomly selected as the modeling sample set for calibration, and the remaining 31 samples were used as the test sample set. Three machine learning algorithms were introduced: Partial least squares regression (PLSR), backpropagation neural network (BPNN), and support vector machine (SVM) driven by a polynomial kernel function (Poly). Three distinct soil TN inversion models were constructed using these algorithms. To optimize model performance, ten-fold cross-validation was employed to determine the optimal parameters for each model. Additionally, multiple scatter correction (MSC) was applied to obtain band characteristic values, thus enhancing the model's prediction capability. Model performance was evaluated using three indicators: Coefficient of determination (R²), root mean square error (RMSE), and relative prediction deviation (RPD), to assess the prediction accuracy of different models. [Results and Discussions] MSC-Poly-SVM model exhibited the best prediction performance on the test sample set, with an R² of 0.863, an RMSE of 0.203, and an RPD of 2.147. This model was used to perform soil TN content inversion mapping using GF-5 satellite hyperspectral data. In accordance with the stringent requirements of land quality geochemical evaluation, the GF-5 hyperspectral land organic nitrogen parameter distribution map was drawn based on the "Determination of Land Quality Geochemical Evaluation". The results revealed that 86.1% of the land in the Jian Sanjiang study area had a total nitrogen content of more than 2.0 g/kg, primarily concentrated in first and second-grade plots, while third and fourth-grade plots accounted for only 11.83% of the total area. The study area exhibited sufficient soil nitrogen reserves, with high TN background values mainly concentrated along the riverbanks in the central part, distributed in a northeast-east direction. Specifically, in terms of soil spectral preprocessing, the median filtering method performed best in terms of smoothness and maintaining spectral characteristics. The spectra extracted from GF-5 imagery were generally quite similar to ground-measured spectral data, despite some noise, which had a minimal overall impact. [Conclusions] This study demonstrates the clear feasibility of using GF-5 satellite hyperspectral remote sensing data and machine learning algorithm for large-scale quantitative detection and visualization analysis of soil TN content. The soil TN content distribution map generated based on GF-5 hyperspectral remote sensing data is detailed and consistent with results from other methods, providing technical support for future large-scale quantitative detection of soil nutrient status and rational fertilization.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Bi-Intentional Modeling and Knowledge Graph Diffusion for Rice Variety Selection and Breeding Recommendation
    QIAO Lei, CHEN Lei, YUAN Yuan
    Smart Agriculture    2025, 7 (2): 73-80.   DOI: 10.12133/j.smartag.SA202412025
    Abstract1735)   HTML39)    PDF(pc) (1070KB)(687)       Save

    [Objective] Selection of rice varieties requires consideration of several factors, such as yield, fertility, disease resistance and resistance to downfall. In order to meet the user's rice variety selection needs, help users quickly access to the rice varieties they need, improve efficiency, and further promote the informatization and intelligence of rice breeding work, the bi-intentional modeling and knowledge graph diffusion model, an advanced method was proposed. [Methods] The research work was mainly carried out at two levels: Data and methodology. At the data level, considering the current lack of relevant data support for rice variety selection and breeding recommendation, a certain amount of recommendation dataset was constructed. The rice variety selection recommendation dataset consisted of two parts: Interaction data and knowledge graph. For the interaction data, the rice varieties that had been planted in the region were collected on a region-by-region basis, and then a batch of users was simulated and generated from the region. The corresponding rice varieties were assigned to the generated users according to the random sampling method to construct the user-item interaction data. For the knowledge graph, detailed text descriptions of rice varieties were first collected, and then information was extracted from them to construct data in ternary format from multiple varietal characteristics, such as selection unit, varietal category, disease resistance, and cold tolerance. At the methodological level, a model of bi-intentional modeling and knowledge graph diffusion (BMKGD) was proposed. The intent factor in the interaction behavior and the denoising process of the knowledge graph were both taken into account by the BMKGD model. Intentions were usually considered from two perspectives: individual independence and conformity. A dual intent space was chosen to be built by the model to represent both perspectives. For the problem of noisy data in the knowledge graph, denoising was carried out by combining the idea of the diffusion model. Random noise was introduced to destroy the original structure when the knowledge graph was initialized, and the original structure was restored through iterative learning. The denoising was completed in this process. After that, cross-view contrastive learning was carried out in both views. [Results and Discussions] The method proposed achieved optimal performance in the rice variety selection dataset, with recall and normalized discounted cumulative gain (NDCG) values improved by 2.9% and 3.7% compared to the suboptimal model. The performance improvement validated the effectiveness of the method to some extent, indicating that the BMKGD model was more suitable for rice variety recommendation. The Recall value of the BMKGD model on the rice variety selection dataset was 0.327 6, meeting the basic requirements of the recommendation system. The analysis revealed that the collaborative signals in the interaction data played a major role, while the quality of the constructed knowledge graph still had some room for improvement. The module variants with key components removed all exhibited a decrease in performance compared to the original model, which validated the effectiveness of the modules. The performance degradation of the model variants with each component removed varied, indicating that different components played different roles. The performance drop of the model variant with the cross-view contrastive learning module removed was small, indicating that there was some room for improvement in the module to fully utilize the collaborative relationship between the two views. Conclusions The BMKGD model proposed in this paper achieves good performance on the rice variety selection dataset and accomplishes the recommendation task well. It shows that the model can be used to support the rice variety selection and breeding work and help users to select suitable rice varieties.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Detection of Amylose in Fresh Corn Ears Based on Near-Infrared Spectroscopy
    XUE Zhicheng, ZHANG Yongli, ZHANG Jianxing, CHEN Fei, HUAN Kewei, ZHAO Baishun
    Smart Agriculture    2025, 7 (4): 132-140.   DOI: 10.12133/j.smartag.SA202505030
    Abstract1731)   HTML10)    PDF(pc) (1172KB)(43)       Save

    [Objective] Fresh corn is increasingly an important choice in the daily diet of consumers due to its rich nutrition and sweet taste. With the improvement of living standards, people's quality requirements for fresh corn continue to improve, among which amylose content is a key indicator affecting the taste and flavor of corn, at present, the industry mainly uses chemical detection methods to determine amylose content, which is not only time-consuming and laborious, destroys samples, but also difficult to meet the needs of rapid detection in modern agricultural production and food processing. Therefore, the development of an efficient, accurate and non-destructive rapid detection technology for amylose has become a key issue in the field of agricultural product quality control. [Methods] In this study, a non-destructive detection model for amylose content in ears of fresh corn based on near-infrared spectroscopy technology was established. Taking Jinguan 597 fresh corn as the research object, the near-infrared spectroscopic detection system independently built by the laboratory was used to collect diffuse reflectance spectral data in the middle area of the complete corn ear to ensure that the detection process did not damage the integrity of the sample. At the same time, the physical and chemical values of amylose content in samples were determined with reference, and a standard database was established. In the data preprocessing stage, the Mahalanobis Distance method was used to screen the outliers of the original spectral data, and the abnormal samples caused by operating errors or sample defects were eliminated, and finally 90 representative fresh corn samples were retained for modeling analysis. In order to optimize the model performance, the effects of five mainstream spectral pretreatment methods were compared: standard normal variable (SNV) transform to eliminate the influence of optical path difference, multiplicative scatter correction (MSC) to reduce particle scattering interference, SavitZky-Golay smoothing (SGS) to remove random noise, first-order derivative (FD) to enhance spectral characteristic peaks, and detrending (DT) to eliminate baseline drift. Based on the partial least squares regression (PLSR) algorithm, a full-band amylose prediction model was constructed, and the robustness of the model was evaluated by cross-validation. In order to further improve the efficiency of model operation, the characteristic wavelengths with the strongest correlation with amylose content were selected from the whole spectrum by innovatively combining two variable selection methods, competitive adaptive reweighted sampling (CARS) and continuous successive projections algorithm (SPA), and a simplified characteristic band prediction model was established. [Results and Discussions] The results demonstrated that among the various combined models incorporating different preprocessing and feature wavelength selection methods, the "SNV-CARS-PLSR" model, which integrated SNV preprocessing with CARS feature extraction, exhibited superior performance. This model significantly outperformed alternative modeling approaches in predictive capability. The model achieved the following performance metrics: a calibration coefficient of determination (R2C) of 0.826, root mean square error of calibration (RMSEC) of 1.399, prediction coefficient of determination (R2P) of 0.820, root mean square error of prediction (RMSEP) of 1.081, and residual predictive deviation (RPD) of 2.426. Comparative analysis revealed that the "SNV-CARS-PLSR" model showed a 14.0% improvement in R2P compared to the full-band PLSR model with SNV preprocessing alone. This enhancement was primarily attributed to the CARS algorithm's effective identification of key feature wavelengths. Through its adaptive weighting and iterative optimization process, CARS successfully extracted 22 characteristic wavelengths that were strongly correlated with amylose content from the original 157 wavelength points in the full spectrum. This selective extraction process effectively eliminated redundant spectral information and noise interference, thereby significantly improving the model's predictive accuracy. [Conclusions] Combined SNV preprocessing with CARS feature selection, the study successfully established a rapid, non-destructive prediction model for amylose content in fresh maize ears utilizing near-infrared spectroscopy technology. The developed methodology demonstrated significant advantages, including rapid analysis capability and complete non destructiveness of samples. The reseach could provide technical support for rapid, non-destructive detection of amylose in fresh maize ears.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Recognition of Sugarcane Leaf Diseases in Complex Backgrounds Based on Deep Network Ensembles
    MA Weiwei, CHEN Yue, WANG Yongmei
    Smart Agriculture    2025, 7 (1): 136-145.   DOI: 10.12133/j.smartag.SA202411026
    Abstract1725)   HTML59)    PDF(pc) (1385KB)(293)       Save

    [Objective] Sugarcane is an important cash crop, and its health status affects crop yields. However, under natural environmental conditions, the identification of sugarcane leaf diseases is a challenging problem. There are various issues such as disease spots on sugarcane leaves being blocked and interference from lighting, which make it extremely difficult to comprehensively obtain disease information, thus significantly increasing the difficulty of disease identification. Early image recognition algorithms cannot accurately extract disease features and are prone to misjudgment and missed judgment in practical applications. To solve the problem of identifying sugarcane leaf diseases under natural conditions and break through the limitations of traditional methods, a novel identification model, XEffDa was proposed in this research. [Methods] The XEffDa model proposed implemented a series of improvement measures based on the ensemble learning framework, aiming to significantly improve the accuracy of classifying and identifying sugarcane leaf diseases. Firstly, the images in the sugarcane leaf disease dataset under natural conditions were pre-processed. Real-time data augmentation techniques were used to expand the scale of the dataset. Meanwhile, HSV image segmentation and edge-processing techniques were adopted to effectively remove redundant backgrounds and interference factors in the images. Considering that sugarcane leaf disease images were fine-grained images, in order to fully extract the semantic information of the images, the transfer learning strategy was employed. The pre-trained models of EfficientNetB0, Xception, and DenseNet201 were loaded respectively, and with the help of the pre-trained weight parameters based on the ImageNet dataset, the top layers of the models were frozen. The performance of the validation set was monitored through the Bayesian optimization method, and the parameters of the top-layer structure were replaced, thus achieving a good balance between optimizing the number of model parameters and the overall performance. In the top-layer structure, the improved ElasticNet regularization and Dropout layer were integrated. These two mechanisms cooperated with each other to double-suppress overfitting and significantly enhance the generalization ability of the model. During the training process, the MSprop optimizer was selected and combined with the sparse categorical cross - entropy loss function to better adapt to the multi-classification problem of sugarcane disease identification. After each model completed training independently, an exponential weight-allocation strategy was used to organically integrate the prediction features of each model and accurately map them to the final disease categories. To comprehensively evaluate the model performance, the accuracy indicator was continuously monitored, and an early-stopping mechanism was introduced to avoid overfitting and further strengthen the generalization ability of the model. Through the implementation of this series of refined optimization and integration strategies, the XEffDa model for sugarcane leaf diseases was finally successfully constructed. [Results and Discussions] The results of the confusion matrix showed that the XEffDa model performed very evenly across various disease categories, and all indicators achieved excellent results. Especially in the identification of red rot disease, its F1-Score was as high as 99.09%. This result was not only higher than that of other single models (such as EfficientNetB0 and Xception) but also superior to the combination of EfficientNetB0 and other deep networks (such as DenseNet121 and DenseNet201). This indicated that the XEffDa model significantly improved the ability to extract and classify features of complex pathological images by integrating the advantages of different network architectures. The comparison experiments of different models showed that the recognition accuracy of the XEffDa model reached 97.62%. Compared with the single models of EfficientNetB0 and Xception, as well as the combined models of EfficientNetB0 and other deep networks, the recognition accuracy increased by 9.96, 6.04, 8.09, 4.19, and 1.78 percentage points, respectively. The fusion experiments further showed that the accuracy, precision, recall, and F1-Score of the network improved by ElasticNet regularization increased by 3.76, 3.76, 3.67, and 3.72 percentage points respectively compared with the backbone network. The results of the maximum-probability scatter plot showed that the proportion of the maximum prediction probability value not lower than 0.5 was as high as 99.4%. [Conclusions] The XEffDa model demonstrated stronger robustness and stability. In the identification task of small sugarcane leaf disease datasets, it showed good generalization ability. This model can provide a powerful reference for the accurate prevention and control of sugarcane crop leaf diseases in practical scenarios, and it has positive significance for promoting the intelligent and precise management of sugarcane production.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Pruning Point Recognition and Localization for Spindle-Shaped Apple Trees During Dormant Season Using an Improved U-Net Model
    LIU Long, WANG Ning, WANG Jiacheng, CAO Yuheng, ZHANG Kai, KANG Feng, WANG Yaxiong
    Smart Agriculture    2025, 7 (3): 120-130.   DOI: 10.12133/j.smartag.SA202501022
    Abstract1702)   HTML49)    PDF(pc) (2725KB)(181)       Save

    [Objective] To address the current issues of intelligent pruning robots, such as insufficient recognition accuracy of fruit tree branches and inaccurate localization of pruning points in complex field environments, a deep learning method based on the fusion of images and point clouds was proposed in this research. The method enables non-contact segmentation of dormant high-spindle apple tree branches and measurement of phenotypic parameter, which also achieving automatic identification and precise localization of pruning points. [Methods] Localized RGB-D data were collected from apple trees using a Realsense D435i camera, a device capable of accurate depth measurements within the range of 0.3~3.0 m. Data acquisition took place between early and mid-January 2024, from 9:00 AM to 4:00 PM daily. To maintain uniformity, the camera was mounted on a stand at a distance of 0.4~0.5 m from the main stems of the apple trees. Following data collection, trunks and branches were manually annotated using Labelme software. The OpenCV library was also employed for data augmentation, which helped prevent overfitting during model training. To improve segmentation accuracy of tree trunks and branches in RGB images, an enhanced U-Net model was introduced. This model utilized VGG16 (Visual Geometry Group 16) as its backbone feature extraction network and incorporated the convolutional block attention module (CBAM) at the up-sampling stage. Based on the segmentation results, a multimodal data processing pipeline was established. First, segmented branch mask maps were derived from skeleton lines extracted using OpenCV's algorithm. The first-level branch connection points were identified based on their positions relative to the trunk. Subsequently, potential pruning points were then searched within local neighborhoods through coordinate translation. An edge detection algorithm was applied to locate the nearest edge pixels relative to these potential pruning points. By extending the diameter line of branch pixel points in the images and integrating with depth information, the actual diameter of the branches could be estimated. Additionally, branch spacing was calculated using vertical coordinates differences of potential pruning points in the pixel coordinate system, alongside depth information. Meanwhile, trunk point cloud data were acquired by merging the trunk mask maps with the depth maps. Preprocessing of the point cloud enabled the estimation of the average trunk diameter in the local view through cylindrical fitting using the randomized sampling consistency (RANSAC) algorithm. Finally, an intelligent pruning decision-making algorithm was developed by investigating of orchardists' pruning experience, analyzing relevant literature, and integrating phenotypic parameter acquisition methods, thus achieving accurate prediction of apple tree pruning points. [Results and Discussions] The improved U-Net model proposed achieved a mean pixel accuracy (mPA) of 95.52% for branch segmentation, representing a 2.74 percent point improvement over the original architecture. Corresponding increases were observed in mean intersection over union (mIoU) and precision metrics. Comparative evaluations against DeepLabV3+, PSPNet, and the baseline U-Net were conducted under both backlight and front-light illumination conditions. The improved model demonstrated superior segmentation performance and robustness across all tested scenarios. Ablation experiments indicated that replacing the original feature extractor with VGG16 yielded a 1.52 percent point mPA improvement, accompanied by simultaneous gains in mIoU and precision. The integration of the CBAM at the up sampling stage further augmented the model's capacity to resolve fine branch structures. Phenotypic parameter estimation using segmented branch masks combined with depth maps showed strong correlations with manual measurements. Specifically, the coefficient of determination (R2) values for primary branch diameter, branch spacing, and trunk diameter were 0.96, 0.95, and 0.91, respectively. The mean absolute errors (MAE) were recorded as 1.33, 13.96, and 5.11 mm, surpassing the accuracy of visual assessments by human pruning operators. The intelligent pruning decision system achieved an 87.88% correct identification rate for pruning points, with an average processing time of 4.2 s per viewpoint. These results confirm the practical feasibility and operational efficiency of the proposed method in real-world agricultural settings. [Conclusions] An efficient and accurate method for identifying pruning points on apple trees was proposed, which integrates image and point cloud data through deep learning. The results indicate that this method could provide significant support for the application of intelligent pruning robots in modern agriculture. It not only offers high feasibility but also exhibits outstanding efficiency and accuracy in practical applications, thus laying a solid foundation for the advancement of agricultural automation.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    LightTassel-YOLO: A Real-Time Detection Method for Maize Tassels Based on UAV Remote Sensing
    CAO Yuying, LIU Yinchuan, GAO Xinyue, JIA Yinjiang, DONG Shoutian
    Smart Agriculture    2025, 7 (6): 96-110.   DOI: 10.12133/j.smartag.SA202505021
    Abstract1701)   HTML54)    PDF(pc) (4491KB)(98)       Save

    [Objective] The accurate identification of maize tassels is critical for the production of hybrid seed. Existing object detection models in complex farmland scenarios face limitations such as restricted data diversity, insufficient feature extraction, high computational load, and low detection efficiency. To address these challenges, a real-time field maize tassel detection model, LightTassel-YOLO (You Only Look Once) based on an improved YOLOv11n is proposed. The model is designed to quickly and accurately identify maize tassels, enabling efficient operation of detasseling unmanned aerial vehicles (UAVs) and reducing the impact of manual intervention. [Methods] Data was continuously collected during the tasseling stage of maize from 2023 to 2024 using UAVs, establishing a large-scale, high-quality maize tassel dataset that covered different maize tasseling stages, multiple varieties, varying altitudes, and diverse meteorological conditions. First, EfficientViT (Efficient vision transformer) was applied as the backbone network to enhance the ability to perceive information across multi-scale features. Second, the C2PSA-CPCA (Convolutional block with parallel spatial attention with channel prior convolutional attention) module was designed to dynamically assign attention weights to the channel and spatial dimensions of feature maps, effectively enhancing the network's capability to extract target features while reducing computational complexity. Finally, the C3k2-SCConv module was constructed to facilitate representative feature learning and achieve low-cost spatial feature reconstruction, thereby improving the model's detection accuracy. [Results and Discussions] The results demonstrated that LightTassel-YOLO provided a reliable method for maize tassel detection. The final model achieved an accuracy of 92.6%, a recall of 89.1%, and an AP@0.5 of 94.7%, representing improvements of 2.5, 3.8 and 4.0 percentage points over the baseline model YOLOv11n, respectively. The model had only 3.23 M parameters and a computational cost of 6.7 GFLOPs. In addition, LightTassel-YOLO was compared with mainstream object detection algorithms such as Faster R-CNN, SSD, and multiple versions of the YOLO series. The results demonstrated that the proposed method outperformed these algorithms in overall performance and exhibits excellent adaptability in typical field scenarios. [Conclusions] The proposed method provides an effective theoretical framework for precise maize tassel monitoring and holds significant potential for advancing intelligent field management practices.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Multi-Scale Tea Leaf Disease Detection Method Based on Improved YOLOv11n
    XIAO Ruihong, TAN Lixin, WANG Rifeng, SONG Min, HU Chengxi
    Smart Agriculture    2026, 8 (1): 62-71.   DOI: 10.12133/j.smartag.SA202509014
    Abstract1698)   HTML53)    PDF(pc) (1532KB)(65)       Save

    [Objective] Preventing and containing leaf diseases is a critical component of tea production, and accurate identification and localization of symptoms are essential for modern, automated plantation management. Field inspection in tea gardens poses distinctive challenges for vision-based detection algorithms: targets appeared at widely varying scales and morphologies under complex backgrounds and unfixed acquisition distances, which easily misled detectors. Models trained on standardized datasets with uniform distance and background often underperform, leading to false alarms and missed detections. To support method development under realistic constraints, YOLO-SADMFA (You Only Look Once-Switchable Atrous Dynamic Multi-scale Frequency-aware Adaptive), a detector based on the YOLOv11n backbone was proposed. The architecture aims to preserve fine details during repeated re-sampling (down- and up-sampling), strengthen modeling of lesions at varying scales, and refine multi-scale feature fusion. [Methods] The proposed architecture incorporated additional convolutional, feature extraction, upsampling, and detection head stages to better handle multi-scale representations, and a DMF-Upsample (Dynamic Multi-scale Frequency-aware Upsample) module that performed upsampling through multi-scale feature analysis and dynamic frequency adjustment fusion was introduced. This module enabled efficient multi-scale feature integration while effectively mitigating information loss during up- and down-sampling. Concretely, the DMF-Upsample analyzed multi-frequency responses from adjacent pyramid levels and fused them with dynamically learned frequency-selective weights, which preserved high-frequency lesion boundaries and textures while retaining low-frequency contextual structure such as leaf contours and global shading. A lightweight gating mechanism estimates per-location and per-channel coefficients to regulate the contribution of different bands, and a residual bypass preserved identity information to further reduce aliasing and oversmoothing introduced by repeated resampling. Furthermore, the baseline C3k2 block was replaced with a switchable atrous convolution (SAConv) module, which enhanced multi-scale feature capture by combining outputs from different dilation rates and incorporates a weight locking mechanism to improve model stability and performance. In practice, the SAConv aggregated parallel atrous branched at multiple dilation factors through learned coefficients under weight locking, which expanded the effective receptive field without sacrificing spatial resolution and suppressed gridding artifacts, while incurring modest parameter overhead. Lastly, an adaptive spatial feature fusion (ASFF) mechanism was integrated into the detection head, forming an ASFF-Head that learned spatially varying fusion weights across different feature scales, effectively filters conflicting information, and strengthens the model's robustness and overall detection accuracy. Together, these components formed a deeper yet efficient multi-scale pathway suited to complex field scenes. [Results and Discussions] Compared with the original YOLOv11n model, YOLO-SADMFA improved precision, recall, and mAP by 4.4, 8.4, and 3.7 percentage points, respectively, indicating more reliable identification and localization across diverse field scenes. The detector was particularly effective for multi-scale targets where the lesion area occupied approximately 10%-65% of the image, reflecting the variability introduced by unfixed acquisition distance during tea garden patrols. Under low illumination and in complex backgrounds with occlusions and clutter, it maintained stable performance, reduced both missed detections and false alarms, and effectively distinguished disease categories with similar morphology and color. On edge computing devices, it sustained about 161 f/s, which met real-time requirements for mobile inspection robots and portable systems. These outcomes demonstrated strengthened robustness to background interference and improved sensitivity at extreme scales, which was consistent with practical demands where the acquisition distance was not fixed. From an ablation perspective, DMF-Upsample preserved high-frequency lesion boundaries while retaining low-frequency structural context after resampling, SAConv expanded receptive fields through multi-dilation aggregation under a weight-locking mechanism, and the ASFF-Head mitigated conflicts among feature pyramids. Their combination yielded cumulative gains in stability and accuracy. Qualitative analyses further supported the quantitative results: Boundary localization improved for small, speckled lesions, large blotches were captured with fewer spurious edges, and distractors such as veins, shadows, and soil textures were less frequently misclassified, confirming the benefits of dynamic multi-scale frequency-aware fusion and adaptive spatial weighting in real field conditions. [Conclusions] The proposed YOLO-SADMFA effectively addressed the multi-scale disease detection challenge in complex tea garden environments, where acquisition distance was not fixed, lesion morphology and color were diverse, and cluttered backgrounds easily caused misjudgments and omissions. It significantly improved detection accuracy and robustness relative to the original YOLOv11n model across a wide range of target scales, and it maintained stable performance under low illumination and complex backgrounds typical of field inspections. It provided reliable technical support for automated tea leaf disease inspection systems by enabling accurate localization and identification of lesions in real operating conditions and by sustaining real-time inference on edge devices suitable for patrol-style deployment.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Dynamic Prediction Method for Carbon Emissions of Cold Chain Distribution Vehicle under Multi-Source Information Fusion
    YANG Lin, LIU Shuangyin, XU Longqin, HE Min, SHENG Qingfeng, HAN Jiawei
    Smart Agriculture    2024, 6 (4): 138-148.   DOI: 10.12133/j.smartag.SA202403020
    Abstract1680)   HTML25)    PDF(pc) (2240KB)(886)       Save

    [Objective] The dynamic prediction of carbon emission from cold chain distribution is an important basis for the accurate assessment of carbon emission and its green credit grade. Facing the fact that the carbon emission of vehicles is affected by multiple factors, such as road condition information, driving characteristics, refrigeration parameters, etc., a dynamic prediction model of carbon emission was proposed from refrigerated vehicles that integrates multi-source information. [Methods] The backbone feature extraction network, neck feature fusion network and loss function of YOLOv8s was firstly improved. The full-dimensional dynamic convolution was introduced into the backbone feature extraction network, and the multidimensional attention mechanism was introduced to capture the contextual key information to improve the model feature extraction capability. A progressive feature pyramid network was introduced into the feature extraction network, which reduced the loss of key information by fusing features layer by layer and improved the feature fusion efficiency. The road condition information recognition model based on improved YOLOv8s was constructed to characterize the road condition information in terms of the number of road vehicles and the percentage of pixel area. Pearson's correlation coefficient was used to compare and analyze the correlation between carbon emissions of refrigerated vehicles and different influencing factors, and to verify the necessity and criticality of the selection of input parameters of the carbon emission prediction model. Then the iTransformer temporal prediction model was improved, and the external attention mechanism was introduced to enhance the feature extraction ability of iTransformer model and reduce the computational complexity. The dynamic prediction model of carbon emission of refrigerated vehicles based on the improved iTransformer was constructed by taking the road condition information, driving characteristics (speed, acceleration), cargo weight, and refrigeration parameters (temperature, power) as inputs. Finally, the model was compared and analyzed with other models to verify the robustness of the road condition information and the prediction accuracy of the vehicle carbon emission dynamic prediction model, respectively. [Results and Discussions] The results of correlation analysis showed that the vehicle driving parameters were the main factor affecting the intensity of vehicle carbon emissions, with a correlation of 0.841. The second factor was cargo weight, with a correlation of 0.807, which had a strong positive correlation. Compared with the vehicle refrigeration parameters, the road condition information had a stronger correlation between vehicle carbon emissions, the correlation between refrigeration parameters and the vehicle carbon emissions impact factor were above 0.67. In order to further ensure the accuracy of the vehicle carbon emissions prediction model, The paper was selected as the input parameters for the carbon emissions prediction model. The improved YOLOv8s road information recognition model achieved 98.1%, 95.5%, and 98.4% in precision, recall, and average recognition accuracy, which were 1.2%, 3.7%, and 0.2% higher than YOLOv8s, respectively, with the number of parameters and the amount of computation being reduced by 12.5% and 31.4%, and the speed of detection being increased by 5.4%. This was due to the cross-dimensional feature learning through full-dimensional dynamic convolution, which fully captured the key information and improved the feature extraction capability of the model, and through the progressive feature pyramid network after fusing the information between different classes through gradual step-by-step fusion, which fully retained the important feature information and improved the recognition accuracy of the model. The predictive performance of the improved iTransformer carbon emission prediction model was better than other time series prediction models, and its prediction curve was closest to the real carbon emission curve with the best fitting effect. The introduction of the external attention mechanism significantly improved the prediction accuracy, and its MSE, MAE, RMSE and R2 were 0.026 1 %VOL, 0.079 1 %VOL, 0.161 5 %VOL and 0.940 0, respectively, which were 0.4%, 15.3%, 8.7% and 1.3% lower, respectively, when compared with iTransformer. As the degree of road congestion increased, the prediction accuracy of the constructed carbon emission prediction model increased. [Conclusions] The carbon emission prediction model for cold chain distribution under multi-source information fusion proposed in this study can realize accurate prediction of carbon emission from refrigerated vehicles, provide theoretical basis for rationally formulating carbon emission reduction strategies and promoting the development of low-carbon cold chain distribution.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Underwater Insitu Weight Estimation Method for Chinese Mitten Crab Based on Binocular Vision and Improved YOLOv11-pose
    LI Aoqiang, DAI Hangyu, GUO Ya
    Smart Agriculture    2026, 8 (1): 192-202.   DOI: 10.12133/j.smartag.SA202505019
    Abstract1679)   HTML56)    PDF(pc) (4043KB)(92)       Save

    [Objective] With the accelerated development of large-scale and intelligent aquaculture, accurate estimation of the body weight of individual Chinese mitten crabs is critical for tasks such as precise feeding, disease prevention, and optimization of harvest decisions. Traditional methods of manually catching and weighing crabs are time-consuming, labor-intensive, and can cause stress or injury to the crabs, while also failing to provide real-time monitoring. To address the challenges posed by turbid water conditions in aquaculture, which lead to poor image quality and difficulty in feature extraction, a method is proposed for estimating Chinese mitten crab weight that combines binocular vision with deep learning–based keypoint detection. This approach achieves high-precision detection of anatomical keypoints on the crab, providing new technical support for precision aquaculture and intelligent management. [Methods] Based on a lightweight YOLOv11 framework, in its C3K2 module, MBConv depthwise-separable convolutions were incorporated to significantly reduce computational complexity and improve feature extraction efficiency. An EffectiveSE channel attention mechanism was introduced to adaptively emphasize important channel-wise features. To further enhance cross-scale information fusion, a spatial dynamic feature fusion module (SDFM) was added. The SDFM adaptively and weightedly fused local spatial attention with global channel attention, enabling detailed extraction of crab shell edges and anatomical keypoints. The improved YOLOv11-ES model could simultaneously output the crab's bounding box, the positions of four anatomical keypoints, and the crab's sex classification in a single forward pass. In the 3D reconstruction stage, calibrated stereo camera parameters were used, and a sparse keypoint matching strategy guided by the crab's sex and spatial geometric constraints was employed. High-confidence keypoint pairs were selected from the left and right views, and the true 3D coordinates of the crab's carapace length and width were computed by triangulation. Finally, the obtained carapace length, width, and sex label data were fed into a two-layer back-propagation (BP) neural network to perform a regression prediction of the individual crab's weight. [Results and Discussion] To validate the effectiveness and robustness of the proposed method, a dataset of Chinese mitten crab images with annotated keypoints was constructed under varying water turbidity and lighting conditions, and both ablation and comparative experiments were conducted. The YOLOv11-ES achieved a mean average precision at intersection over union (IOU) threshold of 0.5 (mAP@50) of 97.2% on the test set, which was 4.4 percentage points higher than the original YOLOv11 model. The keypoint detection component reached an mAP@50 of 96.7%, which was 3.6 percentage points higher than that of the original YOLOv11 model. In comparative experiments, YOLOv11-ES also demonstrated significant advantages over other models in the same series. Moreover, in a full-system evaluation using images of 30 individual crabs, the mean absolute percentage error (MAPE) for carapace width measurements was only 2.68%, and for carapace length it was 1.48%. The Pearson correlation coefficients between the measured and manually obtained true values for both carapace length and width exceeded 0.977, indicating high accuracy in the 3D reconstruction and minimal measurement error. Experiments analyzing the influence of image quality on measurement accuracy showed that when the underwater image quality measure (UIQM) reached at least 1.5, the combined MAPE of carapace length and width errors could be kept below 5%. When UIQM reached at least 2.2, the MAPE dropped to about 1.9%. These results confirmed the robustness of the method against variations in water turbidity and lighting conditions. For weight regression prediction, the BP network trained on carapace length, width, and sex features achieved a mean absolute error (MAE) of 2.39 g and a MAPE of 7.1% on an independent test set, demonstrating high-precision estimation of individual crab weight. [Conclusions] The proposed method, which combines an improved YOLOv11 object detection network, binocular sparse keypoint matching, and a two-layer BP regression network, enabled high-precision, low-error, real-time, non-contact estimation of Chinese mitten crab weight in complex turbid aquatic environments. This approach featured a lightweight model, high computational efficiency, excellent measurement accuracy, and strong adaptability to varying environmental conditions. It provided key technical parameters for intelligent Chinese mitten crab farming. In the future, this approach could be extended to other aquaculture species and complex farming scenarios. Combined with transfer learning and online adaptive calibration techniques, its generalization capability could be further improved and integrated with intelligent monitoring platforms to achieve large-scale, all-weather underwater crab weight estimation, contributing to the sustainable development of smart aquaculture.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Greenhouse Temperature and Humidity Prediction Method Based on Adaptive Kalman Filter and GWO-LSTM-Attention
    CAI Yuqin, LIU Daming, XU Qin, LI Boyang, LIU Bojie
    Smart Agriculture    2026, 8 (1): 148-155.   DOI: 10.12133/j.smartag.SA202506033
    Abstract1649)   HTML19)    PDF(pc) (1482KB)(59)       Save

    [Objective] Acquiring valid data is a critical part for establishing accurate greenhouse prediction models. However, simple averaging and weighted averaging are commonly used to process multi-sensor data in current research, but these methods are often ineffective against sensor noise interference. Additionally, greenhouse temperature and humidity exhibit strong coupling characteristics that necessitate coordinated control strategies. Prevailing studies predominantly train separate models for temperature and humidity prediction, which risks generating physically inconsistent results (e.g., simultaneous high temperature and high humidity), using it as the basis for control may lack reliability. Furthermore, the multi-dimensional environmental factor data in greenhouses has the characteristics of large volume and high computational cost. In the training process of the traditional LSTM model, parameters are manually adjusted based on human experience. When dealing with high-dimensional data, the model's convergence is slow and it is prone to getting stuck in local optima. [Methods] To address multi-point data fusion challenges, the traditional Kalman filtering algorithm was improved by dynamically adjusting the process noise covariance (Q) and observation noise covariance (R), while adaptively assigning weights to multiple sensors based on the innovation. This adaptation was achieved by monitoring the innovation sequence—the difference between observed and predicted measurements. Furthermore, the algorithm utilized the innovation covariance to assign adaptive weights to multiple sensors. Sensors with consistently smaller innovations which indicated higher reliability, were assigned greater weights. This mechanism enabled the system to swiftly identify and mitigate the impact of abnormal sensor readings, thereby ensuring robust and accurate fusion of multi-sensor data and providing a reliable foundation for subsequent model training. To address the strong coupling between temperature and humidity and their collaborative control requirements, a multi-output LSTM-attention model was developed for joint temperature-humidity prediction within a unified architecture. This model employed an attention mechanism to adaptively weight critical environmental factors, thereby resolving physical constraint violations inherent in univariate forecasting approaches. The multi-dimensional nature of greenhouse environmental data often leads to high computational costs during model training. In traditional practices, the hyperparameters of LSTM models were often manually tuned based on experience, a process that was not only inefficient but also prone to suboptimal convergence and local optima traps, especially with high-dimensional data. To overcome this limitation, the grey wolf optimizer (GWO) was integrated to automatically perform hyperparameter optimization search and efficiently search for the optimal combination of key hyperparameters, such as the number of hidden units, learning rate, and dropout rate. [Results and Discussions] The adaptive Kalman filtering algorithm proposed achieved mean absolute deviations (MAD) of 1.59 ℃ and 8.64% for multi-point temperature and humidity fusion, respectively. Compared to the traditional Kalman filter algorithm, these represented reductions of 1.24% and 8.57%. The algorithm enabled swift identification of abnormal sensors and effectively mitigated their impact. When utilizing the fusion results of this algorithm as the model training dataset, the R2 values for temperature and humidity predictions reached 98.2% and 99.3%, respectively. This constituted an increase of 4.7 and 4.3 percentage points compared to results obtained using the Kalman filter, demonstrating that the algorithm provided a highly reliable data foundation for model training. Furthermore, the GWO-LSTM-Attention model trained on this data yielded root mean square errors (RMSE) of 0.776 8 and 2.056 4 for temperature and humidity prediction, respectively. Compared to the LSTM and LSTM-Attention time-series prediction models, the temperature RMSE was reduced by 15.6% and 6.6%, while the humidity RMSE saw reductions of 29.2% and 5.7%. This reflects the role of the GWO algorithm in enhancing model generalization capability and convergence efficiency. [Conclusions] The proposed adaptive Kalman fusion algorithm effectively integrates multi-sensor data, demonstrating robustness in handling sensor noise, outliers, and non-stationary environmental fluctuations. For predicting multiple greenhouse environmental factors, the developed GWO-LSTM-Attention model provides reliable forecasts across diverse time horizons. This study can provide a highly accurate prediction tool for greenhouse environment control. The combined prediction results could directly support the coordinated control of ventilation and irrigation equipment in the future, thereby reducing energy consumption.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    U-Net Greenhouse Sweet Cherry Image Segmentation Method Integrating PDE Plant Temporal Image Contrastive Learning and GCN Skip Connections
    HU Lingyan, GUO Ruiya, GUO Zhanjun, XU Guohui, GAI Rongli, WANG Zumin, ZHANG Yumeng, JU Bowen, NIE Xiaoyu
    Smart Agriculture    2025, 7 (3): 131-142.   DOI: 10.12133/j.smartag.SA202502008
    Abstract1646)   HTML22)    PDF(pc) (2118KB)(49)       Save

    [Objective] Within the field of plant phenotyping feature extraction, the accurate delineation of small targets boundaries and the adequate recovery of spatial details during upsampling operations have long been recognized as significant obstacles hindering progress. To address these limitations, an improved U-Net architecture designed for greenhouse sweet cherry image segmentation. [Methods] Taking temporal phenotypic images of sweet cherries as the research subject, the U-Net segmentation model was employed to delineate the specific organ regions of the plant. This architecture was referred to as the U-Net integrating self-supervised contrastive learning method for plant time-series images with priori distance embedding (PDE) pre-training and graph convolutional networks (GCN ) skip connection for greenhouse sweet cherry image segmentation. To accelerate model convergence, the pre-trained weights derived from the PDE plant temporal image contrastive learning method were transferred to. Concurrently, the incorporation of a GCN local feature fusion layer was incorporated as a skip connection to optimize feature fusion, thereby providing robust technical support for image segmentation task. The PDE plant temporal image contrastive learning method pre-training required the construction of image pairs corresponding to different phenological periods. A classification distance loss function, which incorporated prior knowledge, was employed to construct an Encoder with adjusted parameters. Pre-trained weights obtained from the PDE plant temporal image contrastive learning method were effectively transferred and and applied to the semantic segmentation task, enabling the network to accurately learn semantic information and detailed textures of various sweet cherry organs. The Encoder module performs multi-scale feature extraction by convolutional and pooling layers. This process enabled the hierarchical processing of the semantic information embedded in the input image to construct representations that progress transitions from low-level texture features to high-level semantic features. This allows consistent extraction of semantic features from images across various scales and abstraction of underlying information, enhancing feature discriminability and optimizing modeling of complex targets. The Decoder module was employed to conduct up sampling operations, which facilitated the integration of features from diverse scales and the restoration of the original image resolution. This enabled the results to effectively reconstruct spatial details and significantly improve the efficiency of model optimization. At the interface between the Encoder and Decoder modules, a GCN layer designed for local feature fusion was strategically integrated as a skip connection, enabling the network to better capture and learn the local features in multi-scale images. [Results and Discussions] Utilizing a set of evaluation metrics including accuracy, precision, recall, and F1-Score, an in-depth and rigorous assessment of the model's performance capabilities was conducted. The research findings revealed that the improved U-Net model achieved superior performance in semantic segmentation of sweet cherry images, with an accuracy of up to 0.955 0. Ablation experiments results further revealed that the proposed method attained a precision of 0.932 8, a recall of 0.927 4, and an F1-Score of 0.912 8. The accuracy of improved U-Net is higher by 0.069 9, 0.028 8, and 0.042 compared to the original U-Net, U-Net with PDE plant temporal image contrastive learning method, and U-Net with GCN skip connections, respectively. Meanwhile the F1-Score is 0.078 3, 0.033 8, and 0.043 8 higher respectively. In comparative experiments against DeepLabV3, Swin Transformer and Segment Anything Model segmentation methods, the proposed model surpassed the above models by 0.022 2, 0.027 6 and 0.042 2 in accuracy; 0.063 7, 0.147 1 and 0.107 7 in precision; 0.035 2, 0.065 4 and 0.050 8 in recall; and 0.076 8, 0.127 5 and 0.103 4 in F1-Score. [Conclusions] The incorporation of the PDE plant temporal image contrastive learning method and the GCN techniques was utilized to develop an advanced U-Net architecture that is specifically designed and optimized for the analysis of sweat cherry plant phenotyping. The results demonstrate that the proposed method is capable of effectively addressing the issues of boundary blurring and detail loss associated with small targets in complex orchard scenarios. It enables the precise segmentation of the primary organs and background regions in sweet cherry images, thereby enhancing the segmentation accuracy of the original model. This improvement provides a solid foundation for subsequent crop modeling research and holds significant practical importance for the advancement of agricultural intelligence.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Advances and Prospects in Body-Size Measurement of Sheep: From 2D Vision to 3D Reconstruction and 2D-3D Fusion
    DAI Weijiao, LIANG Yudongchen, ZHOU Yong, YAO Chao, ZHANG Cheng, SONG Yongjian, LI Guoliang, TIAN Fang
    Smart Agriculture    2026, 8 (1): 120-147.   DOI: 10.12133/j.smartag.SA202507028
    Abstract1615)   HTML60)    PDF(pc) (4740KB)(79)       Save

    [Significance] In alignment with the national germplasm security strategy, current research efforts are accelerating the adoption of precision breeding in sheep. Within the whole-genome selection, accurate phenotyping of body morphometrics is critical for assessing growth performance and breeding value. Traditional manual measurements are inefficient, prone to human error, and may cause stress to sheep, limiting their suitability for precision sheep management. By summarizing the applications of sheep body size measurement technologies and analyzing their development directions, this paper provides theoretical references and practical guidance for the research and application of non contact sheep body size measurement. [Progress] This review synthesizes progress across three principal methodological paradigms: two-dimensional (2D) image-based techniques, three-dimensional (3D) point cloud-based approaches, and integrated 2D-3D fusion systems. 2D methods, employing either handcrafted geometric features or deep learning-based keypoint detector algorithms, are cost-effective and operationally simple but sensitive to variation in imaging conditions and unable to capture critical circumference metrics. 3D point-cloud approaches enable precise reconstruction of full animal morphology, supporting comprehensive body-size acquisition with higher accuracy, yet face challenges including high hardware costs, complex data workflows, and sensitivity to posture variability. Hybrid 2D-3D fusion systems combine semantic richness from RGB imagery with geometric completeness from point clouds. Having been effectively validated in other livestock specise, e.g., cattle and pigs, these fusion systems have demonstrated excellent performance, providing important technical references and practical insights for sheep body size measurement. [Conclusions and Prospects] Firstly, future research should focus on constructing large-scale, high-quality datasets for sheep body size measurement that encompass diverse breeds, growth stages, and environmental conditions, thereby enhancing model robustness and generalization. Secondly, the development of lightweight artificial intelligence models is essential. Techniques such as model compression, quantization, and algorithmic optimization can substantially reduce computational complexity and storage requirements, facilitating deployment in resource-constrained environments. Thirdly, the 3D point cloud processing pipeline should be streamlined to improve the efficiency of data acquisition, filtering, registration, and segmentation, while promoting the integration of low-cost, high-resilience vision systems into practical farming scenarios. Fourthly, specific emphasis should be placed on improving the accuracy of curved-dimensional measurements, such as chest circumference, abdominal circumference, and shank circumference, through advances in pose standardization, refined 3D segmentation strategies, and multi-modal data fusion. Finally, the cross-fertilization of sheep body size measurement technologies with analogous methods for other livestock species offers a promising pathway for mutual learning and collaborative innovation, accelerating the industrialization of automated sheep morphometric systems and supporting the development of intelligent, data-driven pasture management practices.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Agricultural Drought Monitoring in Arid Irrigated Areas Based on TVDI Combined with ICEEMDAN-ARIMA Model
    WEI Yuxin, LI Qiao, TAO Hongfei, LU Chunlei, LUO Xu, MAHEMUJIANG Aihemaiti, JIANG Youwei
    Smart Agriculture    2025, 7 (2): 117-131.   DOI: 10.12133/j.smartag.SA202502005
    Abstract1590)   HTML27)    PDF(pc) (3498KB)(183)       Save

    [Objective] Drought, one of the most frequent natural disasters globally, is characterized by its extensive impact area, prolonged duration, and significant harm. Large scale irrigation areas, as important pillars of China's agricultural economy, often have their benefits severely restricted by drought disasters. Therefore, quickly and accurately grasping the regional drought situation is of great significance. It can not only effectively improve the utilization efficiency of water resources and reduce agricultural production losses but also promote the sustainable development of regional agriculture. [Methods] The Santun river irrigation area in Xinjiang, an arid - zone irrigation area, was taken as an research object. Based on Landsat TM/ETM+/OLI_TIRS series data, the temperature vegetation drought index (TVDI) and the vegetation temperature condition index (VTCI) were calculated. Using in situ the soil water content of the 0-10 cm soil layer in the study area measured by the Smart Soil Moisture Monitor, an applicability analysis of the drought monitoring effects of TVDI and VTCI was carried out to select the remote sensing monitoring index suitable for drought research in the study area. Based on the selected drought monitoring index, methods such as linear trend analysis and Theil - Sen + Mann - Kendall trend test were used to explore the temporal and spatial distribution characteristics and change trends of drought in the study area from 2005 to 2022. Meanwhile, with the help of machine learning algorithms, an ICEEMDAN - ARIMA combined model was constructed to predict the drought situation in the study area in spring, summer, and autumn of 2023. The prediction performance of the ICEEMDAN - ARIMA combined model was evaluated using root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). [Results and Discussions] The research results show that there were varying degrees of linear correlations between the two drought indices, TVDI and VTCI, inverted from remote sensing data, and the soil water content of the 0-10 cm surface soil layer in the Santun river irrigation area of Xinjiang. The coefficient of determination between TVDI and the measured soil water content was greater than 0.51 in all periods, with an overall fitting coefficient of 0.57, and the slopes of the fitting equations were all negative, indicating a significant negative correlation. In contrast, the highest coefficient of determination of VTCI was only 0.33, and its overall monitoring effect was significantly weaker than that of TVDI. In terms of temporal and spatial distribution, the drought situation in the study area showed a slow-increasing trend from 2005 to 2022. The growth rate of TVDI was 0.01/10 a, and it had strong spatial heterogeneity, specifically manifested as the spatial distribution characteristic that the southern and southwestern regions of the irrigation area were drier than the northern and northeastern regions. The results of the drought trend analysis indicated that from 2005 to 2022, the distribution of Sen change rate data in the study area conforms to the normal distribution (P < 0.01), and the Sen slopes of more than 72.83% of the regions were greater than zero. At the same time, according to the classification criteria of the Sen + Mann - Kendall trend test, six types of drought change trends were divided. The area proportions of the extremely significant mitigation, significant mitigation, slight mitigation, extremely significant drying, significant drying, and slight drying categories were 0.73%, 1.78%, 24.31%, 5.33%, 9.43%, and 58.42%, respectively. The area proportions of the slight drying and slight mitigation categories were the largest, accounting for a total of 82.73% of the total area of the study area. The ICEEMDAN - ARIMA combined model constructed with the help of machine learning algorithms achieved good results in predicting the drought situation in the study area in 2023. The average value of R2 reached 0.962, demonstrating high robustness and good prediction performance. [Conclusions] The research results systematically characterizes the characteristics of agricultural drought changes in the Santun river irrigation area of Xinjiang over a long - time series, and reveals that the ICEEMDAN - ARIMA combined model has good prediction accuracy in agricultural drought prediction research. This study can provide important references for the construction of drought early warning and forecasting systems, water resource management, and the sustainable development of agriculture in arid-zone irrigation areas.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Analysis of the Spatial Temporal Evolution Pattern and Influencing Factors of Grain Production in Sichuan Province of China
    ZHENG Ling, MA Qianran, JIANG Tao, LIU Xiaojing, MOU Jiahui, WANG Canhui, LAN Yu
    Smart Agriculture    2025, 7 (2): 13-25.   DOI: 10.12133/j.smartag.SA202411013
    Abstract1580)   HTML43)    PDF(pc) (3213KB)(197)       Save

    [Objective] Sichuan province, recognized as a strategic core region for China's food security, exhibits spatiotemporal dynamics in grain production that have significant implications for regional resource allocation and national food strategies. Previous studies have primarily focused on spatial dimension of grain production, treating temporal and spatial characteristics separately. This approach neglected the non-stationary effects of time and failed to integrate the evolution patterns of time and space in a coherent manner. Consequently, the interrelationship between the temporal evolution and spatial distribution of grain production was not fully elucidated. A spatiotemporal integrated analysis framework along with a method for extracting spatiotemporal features was proposed in this study. The objective is to elucidate the spatial pattern temporal variations in Sichuan province, thereby providing a scientific basis for regional food security management. [Methods] The study was based on county-level panel data of Sichuan province spanning the years 2000 to 2019. Multiple spatiotemporal analysis techniques were employed to comprehensively examine the evolution of grain production and to identify its driving mechanisms. Initially, standard deviation ellipse analysis and the centroid migration trajectory model were applied to assess the spatial distribution of major grain-producing areas and their temporal migration trends. This analysis enabled the identification of spatial agglomeration patterns and the direction of change in grain production. Subsequently, a three-dimensional spatiotemporal framework was constructed based on the space-time cube model. This framework integrated both temporal and spatial information. Hotspot analysis and the local Moran's I statistic were then utilized to systematically identify the distribution of cold and hot spots as well as spatial clustering patterns in county-level grain output. This approach revealed the spatiotemporal hotspots, clustering characteristics, and the evolving trends of grain production over time. Finally, a spatiotemporal geographically weighted regression model was employed to quantitatively assess the influence of various factors on grain production. These factors included natural elements (such as topography, climate, and soil properties), agricultural factors (such as the total sown area, mechanization level, and irrigation conditions), economic factors (such as per capita gross domestic product and rural per capita disposable income), and human factors (such as rural population and nighttime light intensity). The analysis elucidated the spatial heterogeneity and evolution of the principal driving forces affecting grain production in the province. [Results and Discussions] A high-yield core area was established on the eastern Sichuan plain, with its spatial distribution exhibiting a pronounced northeast-southwest orientation. The production centroid consistently remained near Lezhi County, although it experienced significant shifts during the periods 2000-2001 and 2009-2010. In contrast, the grain production levels in the western Sichuan plateau and the central hilly regions were relatively low. Over the past two decades, the province demonstrated seven distinct patterns in the distribution of cold and hot spots and three clustering patterns in grain production. Specifically, grain output on the Chengdu Plain continuously increased, the decline in production on the western plateau decelerated, and production in the central region consistently decreased. Approximately 64.77% of the province exhibited potential for increased production, particularly in the western region, where improvements in natural conditions and the gradual enhancement of agricultural infrastructure contributed to significant yield growth potential. Conversely, roughly 16.93% of the areas, characterized by complex topography and limited resources, faced potential yield reductions due to resource scarcity and restrictive cultivation conditions. The analysis further revealed that agricultural factors served as the dominant determinants influencing the spatiotemporal characteristics of grain production. In this regard, the total sown area and the area of cultivated land acted as positive contributors. Natural factors, including slope, soil pH, and annual sunshine duration, exerted negative effects. Although human and economic factors had relatively minor influences, indicators such as population density and nighttime light intensity also played a moderating role in regional grain production. The maintenance of agricultural land area proved crucial in safeguarding and enhancing grain yields, while improvements in natural resource conditions further bolstered production capacity. These findings underscored the inherent spatiotemporal disparities in grain production within Sichuan province and revealed the impact of agricultural resource allocation, environmental conditions, and policy support on the heterogeneity of spatial production changes. [Conclusions] The proposed spatiotemporal integrated analysis framework provided a novel perspective for elucidating the dynamic evolution and driving mechanisms of grain production in Sichuan province. The findings demonstrated that the grain production pattern exhibited complex characteristics, including regional concentration, dynamic spatiotemporal evolution, and the interplay of multiple factors. Based on these results, future policies should emphasize the construction of high-standard farmland, the promotion of precision agriculture technologies, and the rational adjustment of agricultural resource allocation. Such measures are intended to enhance agricultural production efficiency and to improve the regional eco-agricultural system. Ultimately, these recommendations aim to furnish both theoretical support and practical guidance for the establishment of a stable and efficient grain production system and for advancing the development of Sichuan province as a key granary.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Frontiers and Future Trends in Data Sensing Technologies for Opto-Intelligent Agriculture: From Optical Sensors to Intelligent Decision Systems
    CHEN Chengcheng, WU Jiaping, YU Helong
    Smart Agriculture    2025, 7 (5): 1-16.   DOI: 10.12133/j.smartag.SA202507049
    Abstract1561)   HTML78)    PDF(pc) (2483KB)(126)       Save

    [Significance] Opto-intelligent agriculture represents an emerging paradigm that deeply integrates optical sensing and intelligent decision-making within agricultural systems, aiming to transform production from experience-based management to data-driven precision cultivation. The core of this paradigm lies in exploiting the dual role of light: As an information carrier, it enables non-destructive sensing of crop physiological states through hyperspectral imaging, fluorescence, and other optical sensors; As a regulatory factor, it allows feedback-based manipulation of the light environment to precisely regulate crop growth. This establishes a closed-loop framework of "perception-decision-execution", which substantially enhances water and fertilizer use efficiency, enables early warning of pests and diseases, and supports quality-oriented production. Nevertheless, the transition of this technology from laboratory research to large-scale field application remains challenged by unstable signals under complex environments, weak model generalization, high equipment costs, a shortage of interdisciplinary talent, and insufficient policy support and promotion mechanisms. This paper systematically reviews the technological architecture, practical achievements, and intrinsic limitations of opto-intelligent agriculture, with the objective of providing theoretical guidance and practical directions for future development. [Progress] Opto-intelligent agriculture is evolving from isolated technological advances toward full-chain integration, characterized by significant progress in optical sensing, intelligent decision-making, and precision execution. At the optical sensing level, technological approaches have expanded from traditional spectral imaging to multi-scale, synergistic sensing networks. Hyperspectral imaging captures subtle spectral variations during the early stages of crop stress, chlorophyll fluorescence imaging enables ultra-early diagnosis of both biotic and abiotic stresses, LiDAR provides accurate three-dimensional phenotypic data, and emerging quantum-dot sensors have enhanced detection sensitivity down to the molecular scale. In terms of intelligent decision-making, recent advances focus on the deep integration of mechanistic and data-driven models, which compensates for the limited adaptability of purely mechanistic models while improving the interpretability of purely data-based ones. Through multi-source data fusion, the system jointly analyzes optical, environmental, and soil parameters to generate globally optimal strategies that balance yield, quality, and resource efficiency. At the execution stage, systems have developed into real-time feedback control loops. Dynamic light-spectrum LED systems and intelligent variable-spray drones transform decision outputs into precise actions, while continuous monitoring enables adaptive self-optimization. This mature technological chain has delivered measurable outcomes across the agricultural value chain, integrated solutions demonstrate even greater potential. Collectively, the achievements signify the transition of opto-intelligent agriculture from conceptual exploration to practical implementation. [Conclusions and Prospects] By synergizing optical perception with intelligent decision-making, opto-intelligent agriculture is driving a fundamental transformation in agricultural production. To achieve the transition from merely usable to genuinely effective, a comprehensive advancement framework integrating technology, equipment, talent, and policy must be established. Technologically, efforts should focus on enhancing sensing stability under open-field conditions, developing lightweight and interpretable models, and promoting the domestic development of core components. From a talent perspective, interdisciplinary education and agricultural technology training must be strengthened. From a policy standpoint, improving subsidy mechanisms, digital infrastructure, and innovation-oriented dissemination systems will be essential. Looking forward, through integration with emerging technologies such as 6G communication and digital twin systems, opto-intelligent agriculture is poised to become a cornerstone for ensuring both food security and ecological sustainability.

    Table and Figures | Reference | Related Articles | Metrics | Comments0
    Remote Sensing Extraction Method of Rice-Crayfish Fields Based on Dual-Branch and Multi-Scale Attention
    ZHANG Yun, ZHANG Lumin, XU Guangtao, HAO Jiahui
    Smart Agriculture    2025, 7 (6): 185-195.   DOI: 10.12133/j.smartag.SA202507032
    Abstract1529)   HTML13)    PDF(pc) (3231KB)(67)       Save

    [Objective] Rice-crayfish co-culture represents a highly efficient ecological agricultural system that simultaneously provides substantial economic returns and ecological benefits. Accurately obtaining spatial distribution information on rice-crayfish fields is of great importance for promoting the optimal allocation of agricultural resources, supporting ecological protection, and facilitating sustainable agricultural development. In regions characterized by complex terrain, fragmented plots, and diverse planting structures, traditional extraction approaches are often influenced by spectral confusion and indistinct field boundaries, making it difficult to achieve high-precision identification of rice-crayfish fields. The aim of this research is to develop a deep learning model that integrates multi-temporal and multi-scale feature information to improve the accuracy of remote sensing identification of rice-crayfish fields. [Methods] Multi-temporal GF-2 satellite imagery was employed as the primary data source, and a deep learning-based extraction method named the dual-branch attention pyramid network (DBAP-Net) was developed. The proposed model was established upon the U-Net framework and designed with a dual-branch encoder architecture to extract temporal features from different phenological stages, thereby fully capturing the spectral variations of rice-crayfish fields between the paddy flooding and rice-growing periods. The convolutional block attention module (CBAM) was embedded in each encoder layer and in the skip connections to adaptively adjust feature weights along both the channel and spatial dimensions, enhancing the network's capacity to emphasize critical spatial structures of rice-crayfish fields while effectively suppressing background noise and redundant information. During the feature fusion stage, an atrous spatial pyramid pooling (ASPP) module was incorporated to aggregate contextual information from multiple receptive fields through multi-scale atrous convolutions, improving the model's capability for multi-scale spatial information representation. [Results and Discussions] A quantitative performance evaluation of each DBAP-Net component was conducted through ablation experiments. The results demonstrated that the introduction of a dual-branch structure improved overall accuracy (OA), F1-Score, intersection over union (IoU), and Matthews correlation coefficient (MCC) by 0.48, 0.57, 0.94, and 0.99 percentage points, respectively. Incorporating the CBAM module further enhanced these metrics by 0.52, 0.85, 1.40, and 1.20 percentage points, while the addition of the ASPP module yielded further increases of 0.59, 1.09, 1.81, and 1.49 percentage points, respectively. The DBAP-Net model achieved the highest comprehensive performance, with an OA of 94.45%, F1-Score of 91.79%, IoU of 84.82%, and MCC of 87.60%. These values represented respective improvements of 1.83, 2.55, 4.25, and 3.98 percentage points compared with the baseline U-Net model. These findings indicated that each enhancement module made a substantial contribution to improving both feature representation and spatial boundary delineation. DBAP-Net was further compared with five representative semantic segmentation networks, U-Net, PSPNet, DeepLabV3+, SegFormer, and TransUNet, to comprehensively evaluate its generalization and segmentation performance. The results demonstrated that DBAP-Net consistently achieved higher overall accuracy, precision, F1-Score, and IoU than all other comparison models. Specifically, compared with U-Net, PSPNet, and DeepLabV3+, the F1-Scores increased by 2.55, 2.98, and 2.75 percentage points, while the IoU values improved by 4.25, 4.96, and 4.57 percentage points, respectively. In comparison with the more recent models, SegFormer and TransUNet, DBAP-Net's F1-Score was higher by 3.09 and 1.67 percentage points, and its IoU was enhanced by 5.12 and 2.81 percentage points. Visualization of the segmentation results further revealed that DBAP-Net produced clear segmentation boundaries with complete fields, significantly reducing misclassification and omission rates. In contrast, other models exhibited varying degrees of boundary blurring and fragmentation. When applied across the entire study area, DBAP-Net demonstrated strong robustness and stability. The model achieved an overall accuracy of 96.00%, with a Kappa coefficient of 0.920. The producer's accuracy and user's accuracy were 95.13% and 97.38%, respectively. Compared with traditional approaches such as the seasonal water-difference method, random forest classification, and temporal index thresholding, DBAP-Net significantly improved both extraction precision and spatial completeness, particularly under conditions of complex terrain and fragmented agricultural landscapes. [Conclusions] DBAP-Net, by integrating multi-temporal spectral and multi-scale spatial information, significantly improves the accuracy and completeness of remote sensing extraction of rice-crayfish fields from high-resolution remote sensing imagery. The model provides a reliable and adaptable technical framework for fine-scale monitoring, precise mapping, and sustainable management of rice-crayfish co-culture systems, offering valuable methodological support for agricultural resource assessment and ecological protection.

    Table and Figures | Reference | Related Articles | Metrics | Comments0