Welcome to Smart Agriculture 中文

#### Most Down Articles

 Published in last 1 year | In last 2 years| In last 3 years| All| Most Downloaded in Recent Month | Most Downloaded in Recent Year| All
 Select Advances in diagnosis of crop diseases, pests and weeds by UAV remote sensing | Open Access Lan Yubin, Deng Xiaoling, Zeng Guoliang Smart Agriculture    2019, 1 (2): 1-19.   doi:10.12133/j.smartag.2019.1.2.201904-SA003 Abstract （3389）   HTML （5881）    PDF （1165KB）（4799）       Rapid acquisition and analysis of crop information is the precondition and basis for carrying out precision agricultural practice. Variable spraying and agricultural operation management based on the actual degree of crop diseases, pests and weeds can reduce the cost of agricultural production, optimize crop cultivation, improve crop yield and quality, and thus achieve precise agricultural management. In recent years, with the rapid development of UAV industry, UAV agricultural remote sensing technologies have played an important role in monitoring crop diseases, insects and weeds because of high spatial resolution, strong timeliness and low cost. Firstly, this research introduces the basic idea and system composition of precision agricultural aviation, and the status of UAV remote sensing in precision agricultural aviation. Then, the common UAV remote sensing imaging and interpreting methods were discussed, and the progress of UAV agricultural remote sensing technologies in detecting crop diseases, pests and weeds were respectively expounded. Finally, the challenges in the development of UAV agricultural remote sensing technologies nowadays were summarized, and the future development directions of UAV agricultural remote sensing were prospected. This research can provide theoretical references and technical supports for the development of UAV remote sensing technology in the field of precision agricultural aviation.
 Select State-of-the-art and recommended developmental strategic objectivs of smart agriculture | Open Access Zhao Chunjiang Smart Agriculture    2019, 1 (1): 1-7.   doi:10.12133/j.smartag.2019.1.1.201812-SA005 Abstract （6274）   HTML （16586）    PDF （433KB）（4668）       With the wide applications of modern information technology in agriculture, agricultural intelligent technology revolution with manifestation of smart agriculture is coming. Smart agriculture is an advanced stage in the development of agricultural informatization from digitalization to networking to intelligence, it forms a new way of agricultural production, i.e., taking information and knowledge as the core elements, and integrating modern information technology such as internet, internet of things (IoT), big data, cloud computing, artificial intelligence, intelligent equipment, and so on, to realize agricultural information perception, quantitative decision-making, intelligent control, precise input, and personalized service. Smart agriculture is a milestone in the development of agriculture and has become the development trend of modern agriculture in the world. In this article, the policies, measures, and programs for encouraging the development of smart agriculture issued by Japan, the European Union, the United Kingdom, Canada, the United States, and other countries and regions were summarized, the development history from 1.0 version to 4.0 version of agriculture and development status of smart agriculture in China were also analyzed: remarkable results has achieved, at the end of 2017, the proportion of internet access in administrative villages reached 96%, 204,000 villages established the AgroSciences Information Agency, the retail sales of rural networks reached RMB 1.25 trillion Yuan, 426 cost-effective agricultural IoT products and technologies have been formed by the implementation of IoT pilot project. Behind the rapid development, smart agriculture in China still faces the problems of lack of basic research and technology accumulation, technologies such as sensors for agriculture, animal and plant models with intelligent decision-making, intelligent and precise operation equipment are the main short-boards. The pilot construction projects for the application of smart agriculture have been carried out all over the country, however, the role of display was greater than the actual effect. In order to solving the problems and achieving development demand, the strategic objectives of breaking through the core technologies, realizing the three major changes of "machine replacing manpower", "computer replacing human brain", and "independent technology replacing imports", improving the agricultural production level of intelligence and management network, accelerating the popularization of information services, and reducing application cost, providing farmers with personalized and precise information services that are affordable, and well-used, greatly improving agricultural production efficiency, and guiding the development of modern agriculture were proposed. Based on the analysis above, finally, eight key tasks including developing agricultural sensors, large-load agricultural UAV (unmanned aerial vehicle) protection systems, smart tractors, agricultural robots, agricultural big data, agricultural artificial intelligence, integrated applications and smart agricultural industry, and five policy recommendations including strengthening government support, formulating relevant subsidy policies, strengthening technical standards, and opening data sharing for the future development of smart agriculture in China were proposed.
 Select Recent Advances and Future Outlook for Artificial Intelligence in Aquaculture | Open Access LI Daoliang, LIU Chang Smart Agriculture    2020, 2 (3): 1-20.   doi:10.12133/j.smartag.2020.2.3.202004-SA007 Online available: 21 October 2020 Abstract （2831）   HTML （6886）    PDF （2843KB）（3128）       The production of China's aquaculture has changed from extensive model to intensive model, the production structure is continuously adjusting and upgrading, and the production level has been continuously improved. However, as an important part of China's agricultural production, aquaculture plays an important role in promoting the development of China's agricultural economy. Low labor productivity, production efficiency and resource utilization, low-quality aquatic products, and the lack of safety guarantees have severely limited the rapid development of China's aquaculture industry. Using modern information technology and intelligent devices to realize precise, automated, and intelligent aquaculture, improving fishery productivity and resource utilization is the main way to solve the above contradictions. Artificial intelligence technology in aquaculture is to use the computer technology to realize the production process of aquaculture, monitor the growth of underwater organisms, judge, discuss and analyze problems, and then perform feeding, disease treatment, and breeding. In order to understand the development status and technical characteristics of artificial intelligence technology in aquaculture, in this article, five main aspects of aquaculture, i.e., life information acquisition, aquatic product growth regulation and decision-making, fish disease prediction and diagnosis, aquaculture environment perception and regulation, and aquaculture underwater robots, combined with the practical problems in aquaculture, were mainly focused on. The application principles and necessity of artificial intelligence technology in each aspect were explained. Commonly used technical methods were point out and the classic application cases were deeply analyzed. The main problems, bottlenecks and challenges in the current development of artificial intelligence technology in aquaculture were analyzed, including turbid water, multiple interference factors, corrosion of equipment, and movement of underwater animals, etc., and reasonable research directions for these potential challenges were pointed out. In addition, the main strategic strategies to promote the transformation of aquaculture were also proposed. The development of aquaculture is inseparable from artificial intelligence technology, this review can provide references to accelerate the advancement of digitalization, precision and intelligent aquaculture.
 Select Technical demands for agricultural remote sensing satellites in China | Open Access Chen Zhongxin, Hao Pengyu, Liu Jia, An Meng, Han Bo Smart Agriculture    2019, 1 (1): 32-42.   doi:10.12133/j.smartag.2019.1.1.201901-SA003 Abstract （2330）   HTML （2813）    PDF （572KB）（2078）       With the development of China's modern agriculture, information agriculture and smart agriculture, and the implementation of national rural revitalization strategy, there are very strong demands for timely and effective retrieving information for agricultural environment, production conditions, status, and procedure. Because of the inherent characteristics of agriculture, satellite remote sensing is one of the critical techniques in agricultural information acquisition. Based on the analysis of the applications of agricultural remote sensing satellites abroad and in China, the authors analyzed the technical demand and engineering demand of China's remote sensing satellites development according to the demand of modern agricultural development, in order to provide suggestions for the construction agricultural remote sensing satellite system in the national digital agriculture system. In developed economies, remote sensing satellites that can be used for agricultural applications have formed constellations or systems for integrative observation. Their designs of payloads and sensors onboard remote sensing satellites have taken full account of the demand for agricultural applications. Their technical innovation and information retrieval capability have been greatly enhanced in agricultural applications of satellite remote sensing. In contrast with that in the advanced foreign countries, the agricultural satellite remote sensing applications in China have quite a few problems and shortcomings. We rely mainly multi-spectral remote sensing systems, which leads to inadequate observation elements in agricultural remote sensing applications. Limited by the performance of remote sensing sensors and the inadequate ability of remote sensing satellite ground application system, there is a certain gap between quantitative remote sensing monitoring means in China and foreign developed countries. Based on a comprehensive analysis of the current and future demands of agricultural remote sensing applications in China, this paper suggests the agricultural requirements for the application capability and equipment of remote sensing satellites. It is suggested that a constellation system of agricultural satellites flying in a tandem sequence should be constructed. The constellation has multi-spectral, hyperspectral, infrared and microwave sensors, which can acquire the comprehensive features of the same objects in the same temporal phase, and thus obtain the data with high spatial-temporal consistency and consistency of solar illumination conditions. The precision of multi-source data fusion can comprehensively provide multi-scale remote sensing products with different bands, different polarization, active/passive, microwave/optical fusion. With help of this advanced agricultural remote sensing satellite system and national spatial infrastructure in China, it will enhance the capability to promote the rapid development of agricultural remote sensing technology and the integration of three-dimensional space-air-ground based digital agriculture in China.
 Select Advances in the development and applications of intelligent equipment and feeding technology for livestock production | Open Access Zhao Yiguang, Yang Liang, Zheng Shanshan, Xiong Benhai Smart Agriculture    2019, 1 (1): 20-31.   doi:10.12133/j.smartag.2019.1.1.201812-SA017 Abstract （1885）   HTML （769）    PDF （990KB）（1975）       Intelligent equipment for livestock production is one of the components of intelligent agricultural machinery equipment, and is the focus of technology development in international agricultural equipment industry. This paper reviewed the current situation and development trend of intelligent equipment for livestock production systems nationally and internationally, including electronic feeding stations, animal farming robots, and many supporting intelligent facilities within the animal house. The features and performance characteristics of the equipment were discussed. The development of intelligent equipment for livestock production systems mainly focused on pigs and dairy cows including electronic sow feeding station, lactating sow precision feeding system, electronic cattle feeding station, automatic cattle feeding system, cattle feed pusher and dairy cow milking robot. The development and application of intelligent livestock equipment such as the electronic feeding stations and feeding robots, have significantly increased the production efficiency and saved labor cost in both pig and dairy farms. In addition, it also contributed to improve both of the animal and farmer welfare. However, there is still considerable room to get the application of intelligent livestock equipment improved in practice. For example, the animals have to be trained to get used to the intelligent facilities. On the other hand, the intelligent facilities are also required to identify individual animal or animal organ more accurately in order to further increase the production efficiency. Therefore, the key features in the further development of intelligent livestock equipment would be smarter, more convenient, more reliable, and more economical. At the meantime, it should be a highly integrated and coordinated intelligent system including intelligent facilities, well trained staff, good animal welfare, and comfortable environment. Therefore, the industrial application of the intelligent livestock equipment should be integrated with the local farming practice and fitted with the layout of animal houses in order to increase the efficiency of the equipment, and consequently, to improve animal welfare. The systematical combination of intelligent facilities and animal physiology, animal growth, and animal behavior could contribute to the dynamic interactions between the equipment and animal. Finally, it was concluded that the development of intelligent equipment should be coordinated with the theory of animal production, the function of animal products and the innovation of farming practice. And it also should be continuously updated to promote the transformation and upgrading of animal husbandry industry.
 Select Developmental analysis and application examples for agricultural models | Open Access Cao Hongxin, Ge Daokuo, Zhang Wenyu, Zhang Weixin, Cao Jing, Liang Wanjie, Xuan Shouli, Liu Yan, Wu Qian, Sun Chuanliang, Zhang Lingling, Xia Ji‘an, Liu Yongxia, Chen Yuli, Yue Yanbin, Zhang Zhiyou, Wan Qian, Pan Yue, Han Xujie, Wu Fei Smart Agriculture    2020, 2 (1): 147-162.   doi:10.12133/j.smartag.2020.2.1.202002-SA006 Abstract （1545）   HTML （1004）    PDF （2217KB）（1952）       Agricultural models, agricultural artificial intelligent, and data analysis technology, etc., exist in whole processes of information perceiving, transmission, processing and control for smart agriculture， thus they are the core technology of smart agriculture. To furtherly make the substances and functions of agricultural models clear, facilitate its further research and application, drive smart agriculture development with healthy, steady, and sustainable, methods of systematic analysis, comparison, and chart for relationship, etc. were used in this research. The definition, classification, functions of the agricultural models were theoretically analyzed. The relationships between the agricultural models and the elements and processes of the smart agriculture were expounded, which made the functions of agricultural models clear, provided some agricultural models examples applied in the smart agriculture. The important studies and application progresses of agricultural models were reviewed. The comparison results of agricultural models showed that the 4 levels of agricultural biological elements, 6 scales of agricultural environmental elements, 6 administrative levels of agricultural technological and economic elements, and the relevant approaches for modeling agricultural system need to be considered. The research and application of multi-space scales on environment elements in the agricultural models would have the larger potential. The combination of agricultural models with molecular genetics, perceiving, and artificial intelligence, the collaboration among public and private researchers, and food security challenges have been an important power for further development of agricultural models, linking agricultural models with various agricultural system modeling, databases, harmonious and open data, and decision-making support systems (DSS) would be focus on. The research and application of the agricultural models in China have formed crop model series with Chinese characteristics, joined in the world trends of the Agricultural Model Intercomparison and Improvement Project (AgMIP), the smart agriculture, and so on. They should be speedy graspe chances and accelerate development. The agricultural models is a quantitative express of relationships within or among the agricultural system elements. An important method with epistemological values of quantifying and synthesizing agricultural sciences, and will play an indispensible role in data achieving and processing for the smart agriculture combining perceiving techniques, and become a significant bridge and bond.
 Select Key technology analysis and research progress of UAV intelligent plant protection | Open Access Xu Min, Zhang Ruirui, Chen Liping, Tang Qing, Xu Gang Smart Agriculture    2019, 1 (2): 20-33.   doi:10.12133/j.smartag.2019.1.2.201812-SA025 Abstract （1677）   HTML （2295）    PDF （1405KB）（1928）       UAV plant protection operation faces very complicated environmental conditions. On one hand, its ultra low altitude operations are vulnerable to ground structures and basic hydropower facilities; on the other hand, the effectiveness of plant protection operation is strong, and it is necessary to spray the pesticides to the specific parts of crops at the prescribed time so as to ensure good pesticide application effect. At present, UAV plant protection technology mainly refers to the existing mature technology and flight platform in general aviation field to basically "fly and spray". However, the lack of penetrating research and theoretical guidance on environmental perception in farmland operation, the movement mechanism of droplets under the rotor airflow, and the penetrability of the droplet to different crops canopy lead to low penetration rate of the UAV plant protection operation, easy drifting, frequent accidents, large damage probability and low comprehensive operational efficiency. Benefiting from the breakthroughs in artificial intelligence, parallel computing technology and intelligent hardware, the UAV plant protection technology is developing in the direction of intellectualization, systematization and precision. The real-time perception of the environment under non established conditions, intelligent job decision method based on intelligent recognition of crop diseases and pests, the control of the toward-target pesticide spraying control based on the variable of wind field droplet deposition model and the data based job evaluation system have gradually become the key technology of the UAV intelligent plant protection. The manuscript analyzed and summarized the research status and technical achievements in the field of UAV intelligent plant protection from the field information perception, the modeling and optimization control of accurate pesticide application, the evaluation and monitoring of the operation effect. Based on the existing research, the research also predicted the development trend of the key technologies of intelligent UAV plant protection in the future. The clustering method of hyper-spectral image acquisition and computational intelligence based deep learning recognition will become the key technology for real-time and efficient acquisition of crop target information in plant protection work, which greatly improves the accuracy of remote sensing information inversion recognition; machine vision and multi machine cooperative sensing technology can acquire dynamic information of field operation at multiple levels and time; the high precision droplet spectrum control technology independently controlled by nozzle design and the precision variable spraying control technology based on the wind field model can further improve the droplet deposition effect and reduce the liquid drifting; the breakthrough of high accuracy mesh solution technology will change the prediction mode of droplet drift from artificial experience judgment to computer simulation and numerical deduction; the job path planning technology will greatly improve the efficiency of multi machine and multi area operation and reduce the distance of invalid operation; the job quality evaluation based on the real-time data of the sensor and the operation supervision system of large data technology will replace people to effectively control the process of the UAV plant protection operation, achieve data and transparency of plant protection, and ensure the process is observable and controllable.
 Select Research progress and developmental recommendations on precision spraying technology and equipment in China | Open Access He Xiongkui Smart Agriculture    2020, 2 (1): 133-146.   doi:10.12133/j.smartag.2020.2.1.201907-SA002 Abstract （1533）   HTML （4456）    PDF （871KB）（1765）       Chemical plant protection, which refers to using plant protection machinery sprays chemical pesticides, is the most important technology for pest and disease control at present, an important technical guarantee for food security, and also is essential for safeguarding agricultural production. Pesticide, spray technology and plant protection machinery are called the three pillars of chemical plant protection, which having been becoming a hot research topic in the world. Efficient, precise and intelligent spray technology and equipment can provide guarantee for the improvement of pesticide efficacy and utilization. With the issues of agricultural product safety and environmental protection getting more and more attention from the public, the research and development direction of Chinese plant protection field will gradually turn to intelligent and precision spraying technology and equipment. Since 2010 year, the great development potential and application value of intelligent and precision spraying technologies and equipment have been widely recognized worldwide. In this article, the main precision spraying technologies were reviewed, the research status, typical representative and application progress of plant protection equipment in different working scenarios were classified and summarized. The challenges in the development of precision spraying were analyzed, the countermeasures and suggestions were put forward. This research can provide new methods and new ideas not only for implementation of China's pesticide reduction plan, the promotion of intelligent plant protection equipment and precision spraying technology, but for the development of modern agriculture.
 Select Corn plant disease recognition based on migration learning and convolutional neural network | Open Access Chen Guifen, Zhao Shan, Cao Liying, Fu Siwei, Zhou Jiaxin Smart Agriculture    2019, 1 (2): 34-44.   doi:10.12133/j.smartag.2019.1.2.201812-SA007 Abstract （1413）   HTML （646）    PDF （4817KB）（1736）       Corn is one of the most important food crops in China, and the occurrence of disease will result in serious yield reduction. Therefore, the diagnosis and treatment of corn disease is an important link in corn production. Under the background of big data, massive image data are generated. The traditional image recognition method has a low accuracy in identifying corn plant diseases, which is far from meeting the needs. With the development of artificial intelligence and deep learning, convolutional neural network, as a common algorithm in deep learning, is widely used to deal with machine vision problems. It can automatically identify and extract image features. However, in image classification, CNN still has problems such as small sample size, high sample similarity and long training convergence time. CNN has the limitations of expression ability and lack of feedback mechanism, and data enhancement and transfer learning can solve the corresponding problems. Therefore, this research proposed an optimization algorithm for corn plant disease recognition based on the convolution neural network recognition model combining data enhancement and transfer learning. Firstly, the algorithm preprocessed the data through the data enhancement method to expand the data set, so as to improve the generalization and accuracy of the model. Then, the CNN model based on transfer learning was constructed. The Inception V3 model was adopted through transfer learning to extract the image characteristics of the disease while keeping the parameters unchanged. In this way, the training process of the convolutional neural network was accelerated and the over-fitting degree of the network was reduced. The extracted image features were used as input of the CNN to train the network, and finally the recognition results were obtained. Finally, the model was applied to the pictures of corn diseases collected from the farmland to accurately identify five kinds of corn diseases. Identification test results showed that using data to enhance the CNN optimization algorithm and the migration study on the average recognition accuracy main diseases of com (spot, southern leaf blight, gray leaf spot, smut, gall smut) reached 96.6%, which compared with single CNN, has greatly improved the precision and identification precision by 25.6% on average. The average processing time of each image was 0.28 s, shortens nearly 10 times than a single convolution neural network. The experimental results show that the algorithm is more accurate and faster than the traditional CNN, which provides a new method for identification of corn plant diseases.
 Select Framework and recommendation for constructing the SAGI digital agriculture system | Open Access Wu Wenbin, Shi Yun, Zhou Qingbo, Yang Peng, Liu Haiqi, Wang Fei, Liu Jia, Wang Limin, Zhang Baohui Smart Agriculture    2019, 1 (2): 64-72.   doi:10.12133/j.smartag.2019.1.2.201812-SA021 Abstract （1134）   HTML （1307）    PDF （665KB）（1719）       The human society is entering the era of big data and data is becoming one of the key production elements. It is thus critical to develop the China's data-driving digital agriculture system, which would greatly promote the construction of digital China, stimulate the agriculture high-quality development and improve the agricultural competitiveness at the global market. To achieve this goal, strong integration of information is needed from multi-sources, multi-sensors, and multi-scales. This research, from the perspective of agricultural information science, describes the new framework of satellite, aerial, and ground integrated (SAGI) digital agriculture system for comprehensive agricultural monitoring, modeling, and management. The SAGI system differs from traditional digital agriculture systems and includes 5 important functionalities which are resource survey, production controlling, disaster monitoring, market early-warning and decision supporting. To make the system running in operation, it is necessary to first build an observation system, which integrates the satellite, aerial, and ground in-situ observation systems to capture more sophisticated, accurate and reliable data at different scales. The system is extremely needed for China, a large country with a great geographic difference, diverse agricultural cultivation and multiple agricultural traditions. This observing system helps to form the agricultural big data for subsequent data analysis and data mining. Secondly, using the big data collected, 4 key digitalization and monitoring tasks targeting at resource property right, production process, natural disaster and market status should be implemented so as to transform the data to knowledge. In this process, some diagnosis algorithms and models are developed to understand the growth and health of crops and animals, as well as their interaction with the agro-environment. With the above support, a management system covering the full range of agricultural production, processing, selling, management and services should be established to provide the rapid and reliable information support to decision-making as well to the local farming management, thereby guaranteeing agricultural sustainability and national food security. Thirdly, some key fields for future science and technology innovation to support the applications of the SAGI system should to be enhanced such as the standardization designing, innovation in technologies and instruments, system integration and platform development. Finally, considering the complicated and integrative characteristics of this SAG system, this research also proposed some recommendations such as holistic planning, science-technology innovation, resource sharing, multi-stakeholders participation, and expansion of application fields, so as to drive this idea to the reality.
 Select Information sensing and environment control of precision facility livestock and poultry farming | Open Access Teng Guanghui Smart Agriculture    2019, 1 (3): 1-12.   doi:10.12133/j.smartag.2019.1.3.201905-SA006 Abstract （1918）   HTML （2510）    PDF （2880KB）（1659）       The fine breeding of livestock and poultry facilities is the frontier of the development of modern animal husbandry. The core of the fine breeding of livestock and poultry facilities lies in the deep integration of the "Internet of Things+" with traditional farming facilities. In recent years, with the withdrawal of more and more individual family-based breeding models, the management methods of livestock and poultry farms in China have gradually moved towards intensification, large scale,and automated facilitation. The traditional family-style livestock and poultry management experience is falling behind and gradually withdrawing from the historical stage. The refined farming of livestock and poultry facilities based on the individual animal management and quality assurance of farmed animals and animal welfare requirements have become the latest development trend of livestock and poultry farming industry. The rapid development of digital and network technology will provide new opportunities for the organic combination of animal husbandry production, animal welfare, information management and sustainable utilization of natural resources. Economic benefit, animal health and welfare, refinement of production process management and product quality are three key factors that affect the sustainable development of animal husbandry. In this paper, based on expounding the importance of the information sensing and the environmental regulation and control of the fine breeding livestock and poultry facilities, a cutting-edge technology of the information sensing and the environmental regulation and control of the livestock and poultry facilities was introduced; problems and challenges to be faced with were analyzed; and it was concluded that the smart sensor technology would become the base driving force for progress of livestock and fine poultry breeding facilities, taking account of the welfare of livestock and animal performance of animal anthropomorphizing intelligent control technology and strategy is facing significant challenges. In the field of pig farming, the core direction is mechanized production mode, which is light simplification, feed hygiene and animal health. In the field of cattle farming, the main direction is the automation of the whole chain of forage and the safety of its enclosure facilities. In the field of milking technology, the frontier of technological innovation is to further improve milking efficiency and quality, milking process, low disturbance milk metering, and cow individual milk production prediction. In the field of poultry production, similar to cattle farming, more attention is paid to the improvement of engineering processes such as bedding, environment and drinking water. Finally the paper put forward suggestions on how to implement the key technologies of fine farming of livestock and poultry facilities in China, with purpose of providing theoretical reference and technical support for the transformation, upgrading sustainable development of livestock and poultry breeding industry.
 Select Method for identifying crop disease based on CNN and transfer learning | Open Access Li Miao, Wang Jingxian, Li Hualong, Hu Zelin, Yang XuanJiang, Huang Xiaoping, Zeng Weihui, Zhang Jian, Fang Sisi Smart Agriculture    2019, 1 (3): 46-55.   doi:10.12133/j.smartag.2019.1.3.201903-SA005 Abstract （1795）   HTML （2226）    PDF （2845KB）（1611）       The internet is a huge resource base and a rich knowledge base. Aiming at the problem of small agricultural samples, the utilization technology of network resources was studied in the research, which would provide an idea and method for the research and application of crop disease identification and diagnosis. The knowledge transfer and deep learning methods to carry out research and experiments on public data sets (ImageNet, PlantVillage) and laboratory small sample disease data (AES-IMAGE) were introduced: first the batch normalization algorithm was applied to the AlexNet and VGG of Convolutional Neural Network (CNN) models to improve the over-fitting problem of the network; second the transfer learning strategy using parameter fine-tuning: The PlantVillage large-scale plant disease dataset was used to obtain the pre-trained model. On the improved network (AlexNet, VGG model), the pre-trained model was adjusted by our small sample dataset AES-IMAGE to obtain the disease identification model of cucumber and rice; third the transfer learning strategy was used for the bottleneck feature extraction: using the ImageNet big dataset to obtain the network parameters, CNN model (Inception-v3 and Mobilenet) was used as feature extractor to extract disease features. This method requires only a quick identification of the disease on the CPU and does not require a lot of training time, which can quickly complete the process of disease identification on the CPU. The experimental results show that: first in the transfer learning strategy of parameter fine-tuning: the highest accuracy rate was 98.33%, by using the VGG network parameter fine-tuning strategy; second in the transfer learning strategy of bottleneck feature extraction, using the Mobilenet model for bottleneck layer feature extraction and identification could obtain 96.8% validation accuracy. The results indicate that the combination of CNN and transfer learning is effective for the identification of small sample crop diseases.
 Select Progress and prospects of crop diseases and pests monitoring by remote sensing | Open Access Huang Wenjiang, Shi Yue, Dong Yingying, Ye Huichun, Wu Mingquan, Cui Bei, Liu Linyi Smart Agriculture    2019, 1 (4): 1-11.   doi:10.12133/j.smartag.2019.1.4.201905-SA005 Abstract （2360）   HTML （7011）    PDF （566KB）（1554）       Global change and natural disturbances have already caused a severe co-epidemic of crop pests and diseases, such as aphids, fusarium, rust, and powdery mildew. These threats may result in serious deterioration of grain yield and quality. Traditionally, crop pests and diseases are monitored by visual inspection of individual plants, which is time-consuming and inefficient. Besides, the distribution of different infected wheat patches are hard to identify through manual scouting. However, the spatial scale difference of remote sensing observation directly affects the remote sensing diagnosis mechanism and monitoring method of pests and diseases. The differences in pest and disease characterization and monitoring mechanisms promote the development of the remote sensing-based monitoring technology at different spatial scales, and the complementarity of multi-spatial data sources (remote sensing, meteorology, plant protection, etc.) increase the chance of the precision monitoring of the occurrence and development of pest and disease. As a non-destructive way of collecting ground information, remote sensing technologies have been proved to be feasible in crop pests and diseases monitoring and forecasting. Meanwhile, many crop diseases and pests monitoring and alarming systems have been developed to manage and control agricultural practices. Based on the description of physiological mechanism that crop diseases and pests stressed spectral response, some effective spectral wavelengths, remote sensing monitoring technologies, and crop pests and disease monitoring and forecasting system were summarized and sorted in this paper. In addition, challenge problems of key technology on monitoring crop diseases and pests with remote sensing was also pointed out, and some possible solutions and tendencies were also provided. This article detailed revealed the researches on the remote sensing based monitoring methods on detection and classification of crop pests and diseases with the challenges of regional-scale, multi-source, and multi-temporal data. In addition, we also reviewed the remote sensing monitoring of pests and diseases that meet the characteristics of different remote sensing spatial scale data and precise plant protection and control needs. Finally, we investigated the current development of the pest and disease monitoring systems which integrated the research and application of the existing crop pest and disease monitoring and early warning model. In summary, this review will prove a new perspective for sustainable agriculture from the current researches, thus, new technology for earth observation and habitat monitoring will not only directly benefit crop production through better pest and disease management but through the biophysical controls on pest and disease emergence. Application of UAVs, image processing to insect/disease detection and control should be directly transferable to other pests and diseases, with feedbacks into UAV and EO capabilities for the mapping and management of these agricultural risks. Similarly, these vision systems open other possibilities for farm robotics such as mechanical rather than manual pesticide usage for below crop canopy pest surveying.
 Select Application analysis and suggestions of modern information technology in agriculture: Thoughts on Internet enterprises entering agriculture | Open Access Kong Fantao, Zhu Mengshuai, Sun Tan Smart Agriculture    2019, 1 (4): 31-41.   doi:10.12133/j.smartag.2019.1.4.201906-SA012 Abstract （2196）   HTML （9913）    PDF （964KB）（1456）       With the rapid development of information technology and the steady growth of the agricultural and rural economy, agricultural information technology has attracted more and more attention, and the trend of capital and technology playing important roles in the agricultural field has gradually formed. In recent years, large Internet enterprises have begun to enter the agricultural industry and smart agriculture has developed strongly. This paper analyzed the status and technical application characteristics of large-scale Internet companies engaged in agriculture; explained the reasons why the current technology and capital entered the agricultural field in large numbers, especially in the context of the world science and technology revolution and China's economic and social status, analyzed the key areas and problems of the combination of technology, capital and agricultural industry; analyzed the application boundary, application prospects of information technology in the agricultural field. In view of the digital development and application of new technology in agricultural and rural areas, this paper put forward some policy suggestions. Firstly, strengthen policy guidance and support to prevent market speculation risks; secondly, built a system and mechanism for the convergence and integration of Internet enterprises and agricultural industries; thirdly, focus on cutting-edge key technologies and strengthen efforts to promote scientific and technological innovation; finally speed up the dynamic follow-up of technology achievement transformation, strengthen supervision and do a good job in leading and demonstration drive. The key priority is to focus on the world’s cutting-edge technology and key application technology, strengthen the dominant position of technological innovation of enterprises, and combine with the specific practice of production, circulation and consumption of China’s agricultural industry to fully promote the innovation and application of China’s agricultural information technology. And the main research contents included summarize the successful examples carefully, doing a good job in publicity and guidance, and promoting the typical leads vigorously so that they can be copied, popularized and applied; for the failure cases, learn from the insufficient lessons to prevent the recurrence of similar cases; for the advanced practical technology formed by Internet enterprises, promote technology sharing and information sharing on the premise of protecting intellectual property rights and turn it into a new driving force for the development of agricultural modernization. Only by applying the latest achievement of modern information technology to the practice of agricultural production and becoming the representative of agricultural productivity, can we truly contribute to the development of modern agriculture and rural areas in China and the wing of information.
 Select Research progress and prospect on non-destructive detection and quality grading technology of apple | Open Access Cao Yudong, Qi Weiyan, Li Xian, Li Zhemin Smart Agriculture    2019, 1 (3): 29-45.   doi:10.12133/j.smartag.2019.1.3.201906-SA011 Abstract （1315）   HTML （1040）    PDF （1394KB）（1374）       China has high total apple output, but the export volume is low. The high-end apple market is mostly occupied by imported apples. The main reason of this situation is the lack of technologies and equipments for fruit quality classification, and the degree of automation after picking stands low. The apples enter the consumer market without simple roughing processing, and the quality of the apple is unstable, which greatly reduces its market competitiveness. In this paper, the status quo of non-destructive detection and grading technology of apple quality was analyzed, then the development was forecasted. Apple non-destructive detection technology mainly includes spectrum, electrical characteristics, CT, chromatography, electronic nose and computer vision technology. According to the functional characteristics, advantages and disadvantages of various technologies, it is proposed to develop apple odor detection method based on new sensor technology; adopting multi-feature grading method based on machine vision, the combination of apple quality non-destructive testing technology and grading technology can promote the improvement of apple's industrial competitiveness. Overall, the needs of apple quality non-destructive detection and grading technology development in China are urgent. Detections with new technologies such as nanotechnology, biotechnology and artificial intelligence methods of sensor technology and products in apple non-destructive, quality grading detection and multi-technology have great potential. A real-time, efficient, high-precision grading systems in apple quality which integrates electricity, light, gas and computer vision may be an important development direction for improving apple's quality and enhancing the competitiveness of the apple industry.
 Select Research and prospect of solar insecticidal lamps Internet of Things | Open Access Li Kailiang, Shu Lei, Huang Kai, Sun Yuanhao, Yang Fan, Zhang Yu, Huo Zhiqiang, Wang Yanfei, Wang Xinyi, Lu Qiaoling, Zhang Yacheng Smart Agriculture    2019, 1 (3): 13-28.   doi:10.12133/j.smartag.2019.1.3.201905-SA001 Abstract （1691）   HTML （719）    PDF （3195KB）（1364）       Along with the increasing awareness of environmental protection and growing demand for green and pollution-free agricultural products, it has a great need to explore new ways to apply greener pest control methods in agricultural production. Researching on Solar Insecticidal Lamps (SILs) has continuously received incremental attentions from both the academia and industry, which brings a new mode for the preventing and controlling of agricultural migratory pests with phototaxis feature, and now is becoming to a hot research topic. Towards the fast development of "precision agriculture" and "smart agriculture" as well as the increasing demands for agricultural informatization, Wireless Sensor Networks (WSNs) have been widely used for agricultural information collection and intelligent control of agricultural equipment. WSNs are suitable for large-scale deployment and regional monitoring, which can be easily combined with SIL nodes. Based on the combination, a new type of agricultural Internet of things - Solar Insecticidal Lamps Internet of Things (SIL-IoTs) was proposed and the technology of WSNs for the prevention and control of phototactic migratory pests in agricultural applications were surveyed. Firstly, the state-of-art insecticidal lamps applications was reviewed and their characteristics deployment manners and working lifetime in the production of crops (e.g., forest, fruits, rice, vegetables) were summarized. Secondly, the characteristics of existing GSM/3G/4G-enabled SIL nodes and their latest research status on SIL-IoTs were summarized. Furthermore, the research status was analyzed concerning the energy harvesting mode and deployment characteristics of SIL, which are solar energy SIL harvesting mode for energy saving and the heuristic mode for node deployment, respectively. Finally, towards the fast-developed vision of smart agriculture, in which various emerging IT and automation technologies are maturely applied, SIL-IoTs can be considered as a new and important component to contribute to the green agricultural pest monitoring and control. To further enhance SIL-IoTs' capability and enrich SIL-IoTs' function, four open research issues on SIL-IoTs were proposed, i.e., 1) optimized deployment scheme of SIL-IoTs with multiple constrains, 2) optimized and adaptive energy management strategy for ensuring normal working hours of SIL node, 3) lack of algorithms for pests outbreak area localization, and 4) interference on data transmission because of dense high voltage discharge during severe pest disaster. To sum up, SIL-IoTs is one of the representative applications of "precision agriculture" and "smart agriculture" based on WSNs, which is a new model on prevention and control of pests. The combination of both optimized deployment algorithms of SIL-IoTs nodes and artificial intelligence techniques will provide a theoretical basis for SIL-based applications in terms of optimized deployment and energy management. Intelligent pest information collection, alarm, and node' senergy management via SIL-IoTs will facilitate decisions-makings for precise agricultural applications in prevention and control of pests.
 Select Development and performance evaluation of a multi-rotor unmanned aircraft system for agricultural monitoring | Open Access Zhu Jiangpeng, Cen Haiyan, He Liwen, He Yong Smart Agriculture    2019, 1 (1): 43-52.   doi:10.12133/j.smartag.2019.1.1.201812-SA011 Abstract （1227）   HTML （650）    PDF （1255KB）（1343）       In modern agriculture production, to obtain real-time, accurate and comprehensive information of the farmlands is necessary for farmers. Unmanned Aircraft System (UAS) is one of the most popular platforms for agricultural information monitoring, especially the multi-rotor aircraft due to its simplicity of operation. It is easy to control the speed and altitude of multi-rotor aircraft, even at low altitude. The above features enable multi-rotor UAS to acquire high-resolution images at low altitudes by integrating different imaging sensors. The aim of this work was to develop an octocopter UAS for agricultural information monitoring. In order to obtain the high-resolution aerial images of the entire experimental field, the Sony Nex-7 camera was attached to the aircraft. According to the real-time position of the aircraft got from global position system (GPS) and inertial measurement unit (IMU), the flight control system of the aircraft will send signals to control the camera to capture images at desired locations. Besides, position and orientation system (POS) and an illuminance sensor were loaded on the aircraft to get the location, shooting angle and ambient illumination information of each image. The system can be used to collect the remote sensing data of a field, and the performance was comprehensively evaluated in the field of oilseed rape experimental station in Zhuji, Zhejiang Province, China. The result shows that the system can keep the camera optical axis perpendicular to the ground during the operation. Because the effective communication was established between the mission equipment and the flight control system, the UAS can accurately acquire the images at the pre-defined locations, which improved the operation efficiency of the system. The images collected by the system can be mosaicked into an image of the whole field. In summary, the system can satisfy the demand for the agricultural information collection.
 Select Research Status and Development Direction of Design and Control Technology of Fruit and Vegetable Picking Robot System | Open Access WU Jianqiao, FAN Shengzhe, GONG Liang, YUAN Jin, ZHOU Qiang, LIU Chengliang Smart Agriculture    2020, 2 (4): 17-40.   doi:10.12133/j.smartag.2020.2.4.202011-SA004 Abstract （1685）   HTML （3887）    PDF （2346KB）（1321）       Vegetable and fruit harvesting is the most difficult production process to achieve mechanized operations. High-efficiency and low-loss picking is also a worldwide problem in the field of agricultural robot research and development, resulting in few production and application equipment currently on the market. In response to the demand for picking vegetables and fruits, to improve the time-consuming, labor-intensive, low-efficiency, and low-automation problems of manual picking, scholars have designed a series of automated picking equipment in the recent 30 years, which has promoted the development of agricultural robot technology. In the research and development of fresh vegetable and fruit picking equipment, firstly, the harvesting object and harvesting scene should be determined according to the growth position, shape and weight of the crop, the complexity of the scene, the degree of automation required, through complexity estimation, mechanical characteristics analysis, pose modeling and other methods clarify the design requirements of agricultural robots. Secondly, as the core executor of the entire picking action, the design of the end effector of the picking robot is particularly important. In this article, the structure of the end effector was classified, the design process and method of the end effectors were summarized, the common end effector driving methods and cutting methods were expounded, and the fruit collection mechanism was summarized. Furthermore, the overall control scheme of the picking robot, recognition and positioning method, adaptive control scheme of obstacle avoidance method, quality classification method, human-computer interaction and multi-machine cooperation scheme were summarized. Finally, in order to evaluate the performance of the picking robot overall, the indicators of average picking efficiency, long-term picking efficiency, harvest quality, picking maturity rate and missed picking rate were proposed. The overall development trend was pointed that picking robots would develop toward generalization of picking target scenes, diversified structures, full automation, intelligence, and clustering were put forward in the end.
 Select Advances and Progress of Agricultural Machinery and Sensing Technology Fusion | Open Access CHEN Xuegeng, WEN Haojun, ZHANG Weirong, PAN Fochu, ZHAO Yan Smart Agriculture    2020, 2 (4): 1-16.   doi:10.12133/j.smartag.2020.2.4.202002-SA003 Abstract （2471）   HTML （7397）    PDF （2650KB）（1275）       Agricultural machinery and equipment are important foundations for transforming agricultural development methods and promoting sustainable agricultural development, as well as are the key areas and core supports for promoting agricultural modernization. In order to clarify the development ideas of agricultural machinery informatization and find the key development directions, and vigorously promote the development of agricultural machinery intelligentization, the development status of foreign agricultural machinery and sensing technology fusion were analyzed in this article, and five major development characteristics: 1) development towarding digitalization, automation and informationization, 2) applying sensing technology to the design and manufacturing of agricultural machinery equipment, 3) rapidly developing of animal husbandry machinery sensing technology, 4) focusing on resource conservation and environmental protection, and sensing technology promoting sustainable agricultural development, and 5) towarding intelligent control, automatic operation and driving comfort development were summarized. Among them, some advanced intelligent agricultural machinery were introduced, including the German Krone BiGX700 self-propelled silage harvester, an automatic weeding and fertilization robot developed by the Queensland University of Technology in Australia—Agbot II, and John Deere CP690 self-propelled baler Cotton machine, etc. After that, the new characteristics of the development of agricultural mechanization in China were summarize, and the viewpoint was pointed out that although the current development of agricultural mechanization in China had achieved remarkable results, there were still problems such as low intelligence and informatization of agricultural machinery, and insufficient fusion of agricultural machinery and informatization. Then the prospects for the development of China's agricultural machinery and sensing technology fusion were put forward, including 1) promoting the development of intelligent perception technology and navigation technology research, 2) promoting the intelligentization of agricultural machinery and equipment, and building an agricultural intelligent operation system, 3) promoting the research of agricultural machinery autonomous operation technology and the construction of unmanned farms, and 4) strengthening the technical standard formulation of agricultural machinery informatization and the training of compound talents. The fusion of agricultural machinery and sensing technology can realize the effective and diversified fusion of agricultural mechanization and sensing technology, maximize the guiding effect of informatization, improve the efficiency of agricultural production in China, and promote the development of digital agriculture and modern agriculture.
 Select Airborne remote sensing systems for precision agriculture applications | Open Access Yang Chenghai Smart Agriculture    2020, 2 (1): 1-22.   doi:10.12133/j.smartag.2020.2.1.201909-SA004 Abstract （1838）   HTML （7083）    PDF （1726KB）（1265）       Remote sensing has been used as an important data acquisition tool for precision agriculture for decades. Based on their height above the earth, remote sensing platforms mainly include satellites, manned aircraft, unmanned aircraft systems (UAS) and ground-based vehicles. A vast majority of sensors carried on these platforms are imaging sensors, though other sensors such as lidars can be mounted. In recent years, advances in satellite imaging sensors have greatly narrowed the gaps in spatial, spectral and temporal resolutions with aircraft-based sensors. More recently, the availability of UAS as a low-cost remote sensing platform has significantly filled the gap between manned aircraft and ground-based platforms. Nevertheless, manned aircraft remain to be a major remote sensing platform and offer some advantages over satellites or UAS. Compared with UAS, manned aircraft have flexible flight height, fast speed, large payload capacity, long flight time, few flight restrictions and great weather tolerance. The first section of the article provided an overview of the types of remote sensors and the three major remote sensing platforms (i.e., satellites, manned aircraft and UAS). The next two sections focused on manned aircraft-based airborne imaging systems that have been used for precision agriculture, including those consisting of consumer-grade cameras mounted on agricultural aircraft. Numerous custom-made and commercial airborne imaging systems were reviewed, including multispectral, hyperspectral and thermal cameras. Five application examples were provided in the fourth section to illustrate how different types of remote sensing imagery have been used for crop growth assessment and crop pest management for practical precision agriculture applications. Finally, some challenges and future efforts on the use of different platforms and imaging systems for precision agriculture were briefly discussed.
 Select Framework design and application prospect of agricultural product information blockchain | Open Access Liang Hao, Liu Sichen, Zhang Yinuo, Lv Ke Smart Agriculture    2019, 1 (1): 67-75.   doi:10.12133/j.smartag.2019.1.1.201812-SA020 Abstract （1518）   HTML （1904）    PDF （1064KB）（1200）       Agriculture of China is a typical agricultural system of small producer and large market. Producers are too scattered. Agricultural foundation remains weak in the vast rural areas, especially poverty-stricken areas. All of the above have built up a hedge for the high input of information industry and been a serious impediment to agricultural informationalization. As the underlying technology of electronic tokens, blockchain has become the current research hotspot, and been applied in finance, logistics, electronic commerce, information traceability and so on. Blockchain is a distributed storage and computation system, which is decentralized, so it is highly compatible with the distributed economic system. It will be a comprehensive solution to the agricultural status that is "scattered, small and weak". The book China Blockchain Technology and Application Development Whitepaper 2016 gives guidance suggestions for the application of blockchain in different industries including agriculture. This article is proposed by combining the specific status of Chinese agriculture and the technical characteristics of the block chain. Blockchain will play a very important rule in information gathering, resource integrating, profits sharing and backtracking information. Framework of blockchain for agricultural product with 7 levels of information gathering layer, data layer, network layer, consensus layer, excitation layer, contract layer and application layer was designed based on generalized blockchain according to actual situation of agriculture in China. The function of information gathering layer and data layer weve used to storage encrypted information that is acquired by IoT node in a distributed way. The Network layer was designed with a semi-distributed topological structure based on the original Peer-to-Peer distributed network structure in the blockchain by adding the supper notes. In the consensus layer, the DPOS was implied install of POW, therefore, there is no need for intensive computing. Due to the use of smart contact in the contract layer, transactions can be completed automatically in the absence of intermediaries. Furthermore, members of the Blockchain Union can also get repay by participating in the consensus with the smart contracts. The application layer was designed to provide the interface for application of government, bank, enterprise, producer and consumers. This framework can provide flexible mechanism of distributed storage, complete information consensus system, reliable information tamper-proof function and practical incentive reward measures. Subsequently, the above functions have been explained in the agricultural products quality safety traceability and application for the agricultural product market information transparency in more detail. However, the application of block chain in the field of agriculture is still in the stage of exploration, the technology is far from mature, and still need to be perfected in the process of application gradually.
 Select Original innovation of key technologies leading healthy development of smart agricultural | Open Access Gao Wanlin, Zhang Ganghong, Zhang Guofeng, Huang Feng, Wu Dehua, Tao Sha, Wang Minjuan Smart Agriculture    2019, 1 (1): 8-19.   doi:10.12133/j.smartag.2019.1.1.201812-SA015 Abstract （1798）   HTML （2113）    PDF （824KB）（1173）       Smart agricultural is a new form of agriculture that makes full use of human wisdom to develop agriculture. It is a new stage, new model and new pattern of agricultural development. The development of agricultural information technology is an inevitable requirement for smart agricultural. The new generation of core information technology, such as agricultural big data, cloud computing, Internet of things, artificial intelligence, can enable the innovative development of smart agricultural. It can provide new technologies, new methods and new solutions for the healthy development of smart agricultural. Agricultural informationization standardization is the premise to guide the progress and innovation of agricultural science and technology. It can lead the progress of agricultural science and technology and standardize the process of agricultural production. It is an urgent need for the development of smart agricultural. Agricultural Internet of things and agricultural application-specific chip are the core technologies and equipment for the development of smart agricultural. The application demand of agricultural Internet of things can promote the development of agricultural application-specific chip technology. The technological innovation of agricultural application-specific chip will promote the technological upgrading of agricultural Internet of things. Agricultural big data and cloud computing are powerful technical support for massive and complex agricultural information processing. The computing requirements of big data algorithms can promote the innovation and development of cloud computing technology. The improvement of cloud computing capability is more convenient for the application of big data algorithms and applications. Agricultural information security and blockchain are the key to guarantee the security of agricultural information, agricultural product quality certification system and agricultural. Agricultural artificial intelligence is the inevitable choice to improve agricultural labor productivity, reduce resource consumption, and efficient production. The innovation and application of artificial intelligence algorithm is an effective measure to realize smart agricultural. Agricultural plasma technology provides a new technological means for smart agricultural to produce more safer and more reassuring green organic agricultural products. It can be used in different stages of agricultural production, includes before, during and after production, to protect the healthy development of the whole agricultural production chain. The original innovation and autonomous control of the key technologies of smart agricultural will surely lead the healthy development of smart agricultural.
 Select Development and Application of an Intelligent Remote Management Platform for Agricultural Machinery | Open Access ZHU Dengsheng​, FANG Hui​, HU Shaoming​, WANG Wenquan​, ZHOU Yansuo​, WANG Hongyan​, LIU Fei​, HE Yong​ Smart Agriculture    2020, 2 (2): 67-81.   doi:10.12133/j.smartag.2020.2.2.202004-SA006 Abstract （1010）   HTML （1158）    PDF （2701KB）（1158）       In order to solve problems such as the lack of real-time data in agricultural machinery management, the difficulty in real-time machine operation supervision and the asymmetry of machine service information, an intelligent remote management platform was developed in this research. Firstly, five design principles of a specialized remote agricultural machinery management system: specialization, standardization, cloud platform, modularity and openness were proposed. Based on these principles, a customizable general-purpose intelligent remote management system for agricultural machinery based on intelligent sensing technology, Internet of Things technology, positioning technology, remote sensing technology and geographic information system was designed. Practical modules, including agricultural machinery information-based and location-based services using WebGIS, real-time monitoring and management of machinery operation, basic information management of farmland, basic information management of crops in the field, dispatching management of machinery, subsidy management of machinery, order management of machinery operation were designed and implemented in the platform for users of government agencies, agricultural machinery corporations, machine operators, and farmers. Besides, some key technologies of the platform under the current technical background, including the calculation method of the working area with low-precision GNSS positioning receivers, the analysis of anomality data during the processing of GNSS positioning data, the machine scheduling algorithm development, the integration of sensors were focused， analyzed and implementd. The idea of building the machinery management platform with each individual field as the building block was developed. It can be predicted that the agricultural machinery operation management platform would gradually change from simple operation management to field-level comprehensive management. The research and development of this platform can not only solve current machinery management problems, but also provide basic functions for development of similar machinery management platforms.
 Select Research on key technologies of crop growth process simulation model and morphological 3D visualization | Open Access Zhu Yeping, Li Shijuan, Li Shuqin Smart Agriculture    2019, 1 (1): 53-66.   doi:10.12133/j.smartag.2019.1.1.201901-SA005 Abstract （1438）   HTML （1651）    PDF （2416KB）（1149）       According to the demand of digitized analysis and visualization representation of crop yield formation and variety adaptability analysis, aiming at improving the timeliness, coordination and sense of reality of crop simulation model, key technologies of crop growth process simulation model and morphological 3D visualization were studied in this research. The internet of things technology was applied to collect the field data. The multi-agent technology was used to study the co-simulation method and design crop model framework. Winter wheat (Triticum aestivum L.) was taken as an example to conducted filed test, the 3D morphology visualization system was developed and validated. Taking three wheat varieties, Hengguan35 (Hg35), Jimai22 (Jm22) and Heng4399 (H4399) as research objects, logistic equation was constructed to simulate the change of leaf length, maximum leaf width, leaf height and plant height. Parametric modeling method and 3D graphics library (OpenGL) were used to build wheat organ geometry model so as to draw wheat morphological structure model. The R2 values of leaf length, maximum leaf width, leaf height and plant height were between 0.772-0.999, indicating that the model has high fitting degree. F values (between 10.153-4359.236) of regression equation and Sig. values (under 0.05) show that the model has good significance. Taking wheat as example, this research combined wheat growth model and structure model effectively in order to realize the 3D morphology visualization of crop growth processes under different conditions, it will provide references for developing the crop simulation visualization system, the method and related technologies are suitable for other field crops such as corn and rice, etc.
 Select Development of precision service system for intelligent agriculture field crop production based on BeiDou system | Open Access Wu Caicong, Fang Xiangming Smart Agriculture    2019, 1 (4): 83-90.   doi:10.12133/j.smartag.2019.1.4.201911-SA001 Abstract （1102）   HTML （1086）    PDF （1195KB）（1087）       Precision navigation technology of agricultural machinery is being applied on a large scale for field crop production in China. The technology can reduce labor cost, improve working quality, and extend working time. However, the precision application technology of agricultural machinery and precision management technology of agricultural production are still slow in development. The technology, equipment, and service system of precision agriculture have not been completely developed yet in China. There is still a lack of scientific and technical means to achieve the main objectives of cost saving, efficiency improvement, energy saving, and environmental protection in crop production. With the integration of material, energy, and information, intelligent agricultural machinery system is being developed to provide a safer, more efficient, and more scientific solution for agricultural production. In view of the characteristics of intelligent agricultural machinery system, the characteristics of socialized service of agricultural machinery in China, and the status quo of agricultural financial subsidies, this paper puts forward an idea that to develop a socialized precision service system of agricultural machinery, in order to achieve cost saving, efficiency improvement, energy saving, and environmental protection for crop production. The system includes the core participants in agricultural machinery production operations, such as agricultural production organizations, agricultural machinery service organizations, related agriculture management authorities, and the third-party data management service organization. The key technologies for the system include the intelligent gateway technology of agricultural machinery, the variable controlling and measurement technology of fertilizer and chemical, the big data management service technology, and the technology of professional application service platform. During the field operation, the agricultural machinery can control the application of fertilizer or chemical according the prescription map and send the data of position and flow to the database belongs to the third-party organization designated by the government. Therefore, the construction of this system can be used as a basis for the social services and the granting of subsidies. The government can set related standards of application of fertilizer or chemical, and pay the subsidies for the machinery operation according to the operating area when the farmers achieve the standards, which may encourage the farmers to adopt the advanced technology to save fertilizer and chemical. The study provides solutions and technical means to achieve the goal of reducing both fertilizer and chemicals, to adjust of the state’s relevant agricultural subsidy policies, and to promote the comprehensive application of China’s precision agricultural technology.
 Select Design and implementation of intelligent terminal service system for greenhouse vegetables based on cloud service:A case study of Heilongjiang province | Open Access Zhang Haifeng, Li Yang, Zhang Yu, Song Lijuan, Tang Lixin, Bi Hongwen Smart Agriculture    2019, 1 (3): 87-99.   doi:10.12133/j.smartag.2019.1.3.201906-SA002 Abstract （1172）   HTML （1366）    PDF （5851KB）（1050）       The greenhouse vegetable industry play an important strategic role in the adjustment of agricultural transformation mode and the reform of supply side in Heilongjiang Province. Facility horticulture in Heilongjiang Province develops rapidly in recent years, technical support is in great demand, but the experts' technology support for facility horticulture is far from enough. Experts' on-site guidance costs much time and money in the countryside, while the service efficiency is very low. To solve this urgent problem, the architecture of "greenhouse vegetable intelligent terminal system based on cloud service" and the key technologies of implementation (low-cost IoT, distributed real-time operating architecture, virtual expert service, neural network image recognition and mobile terminal service) were put forward. Based on expert services, supplemented by data mining technology, IoT devices were used as expert's remote perception means, smart phones as user terminals, cloud service for integrating knowledge, resources and Internet of Things data to provide vegetable experts and greenhouse vegetable users with high information acquisition, storage, analysis,decision-making capabilities and effective solutions. Experts could view vegetable production status in greenhouses remotely through the Internet, get image and growth environment data, then provide remote guidance to vegetable farmers through the system, expert knowledge would be stored, mined and reused by the system. The Internet of Things system could automatically send out early warning information by judging the air temperature, humidity, illumination intensity and soil moisture in greenhouse. The application of knowledge map and neural network technology would reduce the workload of experts and increase concurrent processing capability of services at the same time. At present, part of this research has been applied in different user groups such as agricultural research departments, enterprises, vegetable cooperatives and farmers in Heilongjiang Province. The system can provide experts with remote inquiry means of greenhouse vegetable production environment, and has the characteristics of simple deployment and low cost. It is suitable for various greenhouse vegetable scenarios, including fruit and edible fungi. In order to popularize this technology in greenhouse vegetable production in China, and achieve an efficient experts' technical support, this research also proposed technical solutions of a large-scale application scenario through cloud computing in future.
 Select Design and application of data acquisition and analysis system for CropSense | Open Access Wang Jiaojiao, Xu Bo, Wang Congcong, Yang Guijun, Yang Zhong, Mei Xin, Yang Xiaodong Smart Agriculture    2019, 1 (4): 91-104.   doi:10.12133/j.smartag.2019.1.4.201910-SA002 Abstract （908）   HTML （1759）    PDF （1549KB）（1003）       In view of the demand of small and medium-sized farms for rapid monitoring and accurate diagnosis of crop growth, the National Engineering Research Center for Information Technology in Agriculture (NERCITA) designed a crop growth monitoring device which named CropSense. It is a portable crop health analysis instrument based on dual-channel high-throughput spectral signals which derived from the incident and reflected light intensity of the crop canopy at red and near-infrared bands. This paper designed and implemented a data collecting and analyzing system for CropSense. It consisted of a mobile application for collecting data of CropSense and a server-side system for data and model management. The system implemented data collecting, processing, analyzing and management completely. The system calculated normalized differential vegetation index (NDVI) based on the two-channels spectral sampling data from CropSense which connected smart phone by Bluetooth, then generated crop growth parameters about nitrogen content, chlorophyll content and Leaf Area Index with the built-in spectral inversion model in the server. Meanwhile, it calculated vegetation coverage, density and color content by images captured from the camera of smart phone. When we finished the sampling program, it generated growth parameter thematic maps by Kriging interpolation based on all sampling data of the selected fields. Considering the target yield of the plot, it could provide expert advice visually. Users could get diagnostic information and professional guiding scheme of crop plots immediately after collecting data by touch a button. Now the device and system have been applied in some experimental farms of research institutes. This paper detailed application of the system in XiaoTangShan farm of NERCITA. Compared with the traditional corn flare period samples and fertilize schemes, users could avoid errors caused by manual recording. Besides, with the same corn yield, the fertilization amount has reduced 16.67% when using the generation of the variable fertilization scheme by this system. The result showed that the system could get the crop growth status efficiently and produced reasonable fertilization. The system collected and analyzed crop growth efficiently and conveniently. It is suitable for various farmers without expertise to obtain the information of the crop growth timely and can guide them to operate more effectively and economically in the field. The system saved data to web server through the Internet which improved the shortcoming of poor sharing in the traditional data exporting mode. This system is practical and promising, and it will be widely applied in the explosion of family farms in China.
 Select Development of an automatic steering test bench for tractors | Open Access Du Juan, Li Min, Jin Chengqian, Yin Xiang Smart Agriculture    2019, 1 (2): 85-93.   doi:10.12133/j.smartag.2019.1.2.201903-SA002 Abstract （831）   HTML （324）    PDF （1055KB）（953）       In recent years, the technology of automatic tractor navigation based on satellite positioning has greatly improved the efficiency and accuracy of tractor field work. Automatic steering contributes is one of the key technologies to realize the automation and intelligentization of agricultural mechanization. It costs much time to install and test automatic steering systems for tractors in the field due to complicated conditions. An automatic steering test bench was developed to reduce time consumed in the field by conducting simulation tests on accuracy and reliability. The developed automatic steering system can be applied to the tractor after obtaining satisfactory results on the test bench, which will greatly shorten the development cycle and improve the precision of the system. In this study, a 120-horsepower tractor front axle was selected. Through the design and calculation of mechanical structure, hydraulic system and electrical control system, the tractor automatic steering test bench was built. The mechanical body consist of a tractor front axle assembly, a loading device and a mechanical frame. The hydraulic interface was reserved for post-installation of automatic steering devices. Two inertial measurement units were used to test the steering system performance by recording the rotation angle of front wheels and the steering wheel. The steering wheel had a steering clearance of 16.48° and an average wheel delay time of 0.14s. In the general range and small angle range, there is a small deviation between the actual corner and the theoretical corner. Responsibility and stability met requirements for agricultural machinery steering. Experimental results show that the test bench has stable performance in terms of status detection, steering control and measurement analysis, which could meet requirements for verifying working parameters of automatic steering devices. The research provides an efficient and reliable test bench for commissioning and performance testing of agricultural machinery automatic steering.
 Select Perspectives and experiences on the development and innovation of agricultural aviation and precision agriculture from the Mississippi Delta and recommendations for China | Open Access Huang Yanbo Smart Agriculture    2019, 1 (4): 12-30.   doi:10.12133/j.smartag.2019.1.4.201909-SA003 Abstract （1289）   HTML （2066）    PDF （1240KB）（848）       Crop production management has advanced into the stage of smart agriculture, which is driven by state-of-the-art agricultural information technology, intelligent equipment and massive data resources. Smart agriculture inherits ideas from precision agriculture and brings agricultural production and management from mechanization and informalization to intelligentization with automatization. Precision agriculture has been developed from strategic monitoring operations in the 1980s to tactical monitoring and control operations in the 2010s. In its development, agricultural aviation has played a key role in serving systems for spray application of crop protection and production materials for precision agriculture with the guidance of global navigation through geospatial prescription mapping derived from remotely-sensed data. With the development of modernized agriculture, agricultural aviation is even more important for advancing precision agricultural practices with more efficient soil and plant health sensing and more prompt and effective system actuation and action. This paper overviews the status of agricultural aviation for precision agriculture to move toward smart agriculture, especially in the Mississippi Delta region, one of the most important agricultural areas in the U.S. The research and development by scientists associated with the Mississippi Delta region are reported. The issues, challenges and opportunities are identified and discussed for further research and development of agricultural aviation technology for next-generation precision agriculture and smart agriculture.
 Select Multi-blockchain application technology for agricultural products transaction | Open Access Liang Hao, Liu Sichen, Zhang Yinuo, Lv Ke Smart Agriculture    2019, 1 (4): 72-82.   doi:10.12133/j.smartag.2019.1.4.201907-SA001 Abstract （951）   HTML （879）    PDF （1340KB）（827）       Agriculture of China is a typical agricultural system of small producer and large market, producers are too scattered. Agricultural foundation remains weak in the vast rural areas, especially poverty-stricken areas. Blockchain technology has good complementarity and applicability with China's agricultural products trading system, because of its distributed storage, transaction information transparency and product information traceability. However, the agricultural product trading system has characteristics of product diversity, commercial process complexity, user group widespread, decentralized, privacy protection and so on. It is difficult to apply the traditional blockchain technology directly to China's agricultural products trading information network. In view of the above problems, the design idea of alliance chain was adopted, and the technology of multi-chain agricultural product transaction information, which includes transaction information blockchain, user information blockchain and agricultural products information blockchain was put forward. The product information blockchain provided the detailed information of agricultural products and guarante that the traceability and non-tamperability of the information. The blockchain node access mechanism was introduced in the user information chain to provide real-name voucher registration and management functions for the agricultural product trading platform. The transaction information blockchain recorded the results of all transaction smart contracts, and through the addition of channel technology, different transaction information could be isolated from each other, which could meet the privacy protection of transaction information and user data and the rapid processing of transaction data. The profit of the transaction was automatically divided by the smart contract, which improved the efficiency of execution and reduces the transaction cost. Finally, a transparent, efficient and applicable blockchain framework for agricultural product transactions was established.
 Select Energy optimization strategy for wireless sensor networks in large-scale farmland habitat monitoring | Open Access Zhang Xiaohan, Yin Changchuan, Wu Huarui Smart Agriculture    2019, 1 (2): 55-63.   doi:10.12133/j.smartag.2019.1.2.201812-SA024 Abstract （747）   HTML （295）    PDF （1207KB）（822）       Wireless sensor network (WSN) has been widely deployed in precision agriculture to improve the crop production. However, we still face many challenges for large-scale farmland habitat monitoring, the energy shortage for battery-powered sensor nodes, the complicated propagation environment for wireless signals during different growing-up periods of the crops, the optimization of the coverage of the sensor nodes, etc. In order to guarantee the holeless coverage of the sensor nodes during the whole life of the crops, the WSNs are typically deployed with high density. Therefore, some of the sensors in the network are redundant in certain growing-up periods of the crops. And also the data collected by each sensor node may have strong temporal correlation. Recently, compressive sensing (CS) has received much attention due to its capability of reconstructing sparse signals with the number of measurements much lower than that of the Nyquist sampling rate. With the rapid progress of CS based sparse representation, matrix completion (MC) theory was proposed very recently. According to the MC theory, a low-rank matrix can be accurately rebuilt with a few number of entries in the matrix. Matrix completion provides the advantage of sampling small set of data at sensor nodes without requiring excessive computational and traffic loads, which meets the requirement of energy-efficient data gathering and transmitting in WSNs. In this research, by considering the characteristics that the sensor nodes are redundant in some growing-up periods of the crops and the data collected by sensor-nodes usually share a strong spatial and temporal correlation among them in WSNs for large-scale farmland habitat monitoring, we put forward a MC based two-step energy saving optimization algorithm to reduce both the energy consumption of the data acquisition and data transmission process in WSNs and achieved the purpose of prolonging the network lifetime. Firstly, through the measurement of the sensor node's data information, we found the non-redundant nodes by considering the spatial correlation of the data from the sensor nodes. We would close the data acquisition units of the remaining redundant nodes and make them only transmit data as relay nodes. Secondly, we took advantage of the partial sampling scheme in matrix completion to further reduce the quantity of data. Thereby, we could reduce the energy consumption on both data collection and transmission process of the wireless sensor network. The experiment results show that the proposed algorithm reduces 83% working nodes in the network, and therefore reducing the energy cost of the network.
 Select Evaluation of fish feeding intensity in aquaculture based on near-infrared machine vision | Open Access Zhou Chao, Xu Daming, Lin Kai, Chen Lan, Zhang Song, Sun Chuanheng, Yang Xinting Smart Agriculture    2019, 1 (1): 76-84.   doi:10.12133/j.smartag.2019.1.1.201812-SA016 Abstract （1452）   HTML （431）    PDF （1290KB）（812）       In aquaculture, feeding intensity can directly reflect the appetite of fish, which is of great significance for guiding feeding and productive practice. However, most of the existing fish feeding intensity evaluation methods have problems of low observation efficiency and low objectivity. In this study, a fish feeding intensity evaluation method based on near-infrared machine vision was proposed to achieve an automatic objective evaluation of fish appetite. Firstly, a near-infrared image acquisition system was built by using near-infrared industrial camera. After a series of image processing steps, the gray level co-occurrence matrix was used to extract the texture feature variable information of the image, including contrast, energy, correlation, inverse gap and entropy. Then the data set were constructed by using these five feature variables as input vectors, and the support vector machine classifier was trained. Among them, the optimal penalty coefficient c and kernel function parameter g were selected by grid search. Finally, the trained images were used to classify the feeding images of fish. And ultimately, the evaluation of fish feeding intensity was realized. The results show that the accuracy of the evaluation could reach 87.78%. In addition, this method does not need to consider the impact of reflections, sprays and other factors on image processing results, so it has strong adaptability and can be used for automatic and objective evaluation of fish appetite, thus provide theoretical basis and methodological support for subsequent feeding decisions.
 Select Research Status and Prospect on Height Estimation of Field Crop Using Near-Field Remote Sensing Technology | Open Access ZHANG Jian, XIE Tianjin, YANG Wanneng, ZHOU Guangsheng Smart Agriculture    2021, 3 (1): 1-15.   doi:10.12133/j.smartag.2021.3.1.202102-SA033 Abstract （1460）   HTML （281）    PDF （1983KB）（785）       Plant height is a key indicator to dynamically measure crop health and overall growth status, which is widely used to estimate the biological yield and final grain yield of crops. The traditional manual measurement method is subjective, inefficient, and time-consuming. And the plant height obtained by sampling cannot evaluate the height of the whole field. In the last decade, remote sensing technology has developed rapidly in agriculture, which makes it possible to collect crop height information with high accuracy, high frequency, and high efficiency. This paper firstly reviewed the literature on obtaining plant height by using remote sensing technology for understanding the research progress of height estimation in the field. Unmanned aerial vehicle (UAV) platform with visible-light camera and light detection and ranging (LiDAR) were the most frequently used methods. And main research crops included wheat, corn, rice, and other staple food crops. Moreover, crop height measurement was mainly based on near-field remote sensing platforms such as ground, UAV, and airborne. Secondly, the basic principles, advantages, and limitations of different platforms and sensors for obtaining plant height were analyzed. The altimetry process and the key techniques of LiDAR and visible-light camera were discussed emphatically, which included extraction of crop canopy and soil elevation information, and feature matching of the imaging method. Then, the applications using plant height data, including the inversion of biomass, lodging identification, yield prediction, and breeding of crops were summarized. However, the commonly used empirical model has some problems such large measured data, unclear physical significance, and poor universality. Finally, the problems and challenges of near-field remote sensing technology in plant height acquisition were proposed. Selecting appropriate data to meet the needs of cost and accuracy, improving the measurement accuracy, and matching the plant height estimation of remote sensing with the agricultural application need to be considered. In addition, we prospected the future development was prospected from four aspects of 1) platform and sensor, 2) bare soil detection and interpolation algorithm, 3) plant height application research, and 4) the measurement difference of plant height between agronomy and remote sensing, which can provide references for future research and method application of near-field remote sensing height measurement.
 Select Development and Testing of Intelligent Sensing and Precision Proportioning System of Water and Fertilizer Concentration | Open Access JIN Zhou​, ZHANG Junqing​, GUO Hongyan, HU Yimin​, CHEN Xiangyu​, HUANG He​, WANG Hongyan​ Smart Agriculture    2020, 2 (2): 82-93.   doi:10.12133/j.smartag.2020.2.2.202003-SA012 Abstract （778）   HTML （1405）    PDF （2031KB）（746）       Water and fertilizer integration technology can effectively improve nutrient utilization efficiency. However, the existing water and fertilizer machines have some shortcomings, such as huge cost, single fertilizer injection, need for cleaning water and so on, which hinder the development of water and fertilizer integration technology. Aiming at the problems of precise and low-cost compounding of compound fertilizer at the local farm, the water and fertilizer integrated intelligent irrigation and fertilization system were taken as the research object. In this research, new concept of an intelligent sensing system was proposed， and accurate proportioning system of water and fertilizer concentration was constructed and implemented. Firstly, a fast on-line method of intelligent sensing model of water and fertilizer was established based on a series of concentration gradient compound fertilizer solutions. The conductivity values of these formulated solutions were tested by contactless conductivity detection electrodes. Subsequently, the data analysis algorithms were discussed and compared to fit regression model. Based on the intelligent sensing model of water and fertilizer , the framework structure of in-situ intelligent sensing and accurate proportioning system of water and fertilizer concentration was designed, and the working principle of the system was also explained. The system proposed includs a first-level water and fertilizer concentration intelligent perception model building subsystem and a second-level water and fertilizer accurate proportioning subsystem. The first-level subsystem was designed as a portable device, which mainly included a precise pump for quantitative dosing, a large-range online conductivity sensor, a plastic bucket and supporting control and model building software. The second-level subsystem was designed as a dynamic and precise fertilizer distribution device. The effectiveness of the system was verified by three types of water intelligent fertilizer application so as to guide the in-situ water and fertilizer concentration ratio. The testing results showed that the second-order polynomial fitting curve under regularization conditions was the best model to express the relationship between the conductivity and the concentration of water and fertilizer, and the correlation coefficients R2 was higher than 0.999. Combined with the proportion of each index of compound fertilizer, the concentration of each index of compound fertilizer that the user cares about can be obtained according to this model. The results of three types of water intelligent fertilizer application showed that the conductivity of natural water had an effect on the water and fertilizer system, and the relative deviation was more than 0.1. The online water and fertilizer perception and ratio system proposed in this research realized the elimination of the interference of the local water conductivity on the accuracy of the ratio of water and fertilizer, and the accurate calculation of compound fertilizer was achieved through model calculation. This system has a simple structure and accurate ratio, low cost， and can be easily combined with the existing water and fertilizer integrated machine or artificial fertilizer system. The system could be widely used in facility agriculture, orchard cultivation and field cash crop cultivation, et al.
 Select Regionalization research of summer corn planting in North China Plain based on multi-source data | Open Access Diao Xingliang, Yang Zaijie, Li Qifeng, Yu Jingxin, Zheng Wengang, Shi Leigang Smart Agriculture    2019, 1 (2): 73-84.   doi:10.12133/j.smartag.2019.1.2.201901-SA002 Abstract （902）   HTML （425）    PDF （1101KB）（736）       Accurate identification of agricultural production environment information and agricultural production characteristics, comprehensive classification of meteorological, soil and crop multi-source data, are the bases for improving the efficiency of agricultural resource utilization and optimizing the structure of agricultural cultivation. Based on the meteorological data of nearly 20 years and the statistics of com yield, this study first constructed a database of spatial and temporal distribution characteristics of climate resources and com production in North China Plain, and there were significant spatiotemporal changes in rainfall, activity accumulated temperature, sunshine hours, solar radiation and corn yield. By using the method of fine crop planting regionalization, the summer com planting areas in the North China plain were divided into 5 categories: the extremely unsuitable area, the unsuitable area, the less suitable area, the suitable area, and the most suitable area, the proportions of each type of area in the total area is about 10%, 11%, 25%, 30%, 24%, respectively, further through using the Environmental Category attribution analysis method, each large class was divided into 5 subcategories, the probability was greater than 75% the relatively stable region accounts for about 63% of the total area, the fluctuation area of less than 75% is about the stable spatial and temporal distribution of 37%; the extremely unsuitable area, the unsuitable area and the less suitable area, these three kinds of spatial and temporal distributions were relatively stable, the belonging degree was 100%, accounting for 87.67%, 70.41% and 84.28%, respectively, the fluctuation zone mainly occurs between the extremely suitable zone and the suitable zone, and between the suitable zone and the relatively suitable zone. The fine zoning of summer com in North China Plain has important guiding significance for improving the utilization efficiency of local resources and optimizing the layout of com industry.
 Select Effects of technical operation parameters on spray characteristics of rotor plant protection UAV | Open Access Zhu Hang, Li Hongze, Huang Yu, Yu Haitao, Dong Yunzhe, Li Junxing Smart Agriculture    2019, 1 (3): 113-122.   doi:10.12133/j.smartag.2019.1.3.201906-SA001 Abstract （841）   HTML （327）    PDF （3184KB）（735）       High-quality operation of plant protection UAV is the premise of precision operation in agricultural aviation, so it is particularly important to study the characteristics of spray system. In order to explore the factors that affect the spray quality, the comprehensive experimental platform of spray performance (developed by Jilin Agricultural Machinery Research Institute) was used to test the droplet deposition distribution and droplet diameter under different UAV rotor speed, spray height and centrifugal nozzle speed in this research, and regression analysis on the deposition characteristics and particle diameter data of 12 groups of tests was conducted. The results showed that the three repeated tests of the same set of parameters had good consistency. Droplets had obvious drift and the maximum effective deposition rate was 46.31% and minimum 31.74%, which shows that the effective deposition rate of droplets was lower than 50%. Compared with the regression analysis results of droplet diameters DV10, DV50 and DV90, the spray height P value is greater than 0.5, and the nozzle speed and rotor speed P value are less than 0.5. So it can be inferred that spray height had a very significant effect on deposition, no significant effect on droplet size. The nozzle speed and rotor speed had very significant effect on droplet size, no significant effect on deposition. The test results of this research can provide theoretical basis and data support for improving the operation quality and spraying efficiency of UAVs.
 Select Apple detection model based on lightweight anchor-free deep convolutional neural network | Open Access Xia Xue, Sun Qixin, Shi Xiao, Chai Xiujuan Smart Agriculture    2020, 2 (1): 99-110.   doi:10.12133/j.smartag.2020.2.1.202001-SA004 Abstract （1392）   HTML （1773）    PDF （2005KB）（734）       Intelligent production and robotic oporation are the efficient and sustainable agronomic route to cut down economic and environmental costs and boosting orchard productivity. In the actual scene of the orchard, high performance visual perception system is the premise and key for accurate and reliable operation of the automatic cultivation platform. Most of the existing apple detection models, however, are difficult to be used on the platforms with limited hardware resources in terms of computing power and storage capacity due to too many parameters and large model volume. In order to improve the performance and adaptability of the existing apple detection model under the condition of limited hardware resources, while maintaining detection accuracy, reducing the calculation of the model and the model computing and storage footprint, shorten detection time, this method improved the lightweight MobileNetV3 and combined the object detection network which was based on keypoint prediction (CenterNet) to build a lightweight anchor-free model (M-CenterNet) for apple detection. The proposed model used heatmap to search the center point (keypotint) of the object, and predict whether each pixel was the center point of the apple, and the local offset of the keypoint and object size of the apple were estimated based on the extracted center point without the need for grouping or Non-Maximum Suppression (NMS). In view of its advantages in model volume and speed, improved MobileNetV3 which was equipped with transposed convolutional layers for the better semantic information and location information was used as the backbone of the network. Compared with CenterNet and SSD (Single Shot Multibox Detector), the comprehensive performance, detection accuracy, model capacity and running speed of the model were compared. The results showed that the average precision, error rate and miss rate of the proposed model were 88.9%, 10.9% and 5.8%, respectively, and its model volume and frame rate were 14.2MB and 8.1fps. The proposed model is of strong environmental adaptability and has a good detection effect under the circumstance of various light, different occlusion, different fruits’ distance and number. By comparing the performance of the accuracy with the CenterNet and the SSD models, the results showed that the proposed model was only 1/4 of the size of CenterNet model while has comparable detection accuracy. Compared with the SSD model, the average precision of the proposed model increased by 3.9%, and the model volume decreased by 84.3%. The proposed model runs almost twice as fast using CPU than the CenterNet and SSD models. This study provided a new approach for the research of lightweight model in fruit detection with orchard mobile platform under unstructured environment.
 Select An improved method for estimating dissolved oxygen in crab ponds based on Long Short-Term Memory | Open Access Zhu Nanyang, Wu Hao, Yin Daheng, Wang Zhiqiang, Jiang Yongnian, Guo Ya Smart Agriculture    2019, 1 (3): 67-76.   doi:10.12133/j.smartag.2019.1.3.201905-SA004 Abstract （929）   HTML （133）    PDF （2818KB）（719）       Dissolved oxygen (DO) is vital to aquaculture industry and affects the yield of aquaculture. Low DO in water can lead to death of crabs, therefore, it is important to measure DO accurately. However, the DO sensors are usually expensive and often lost function due to corrosion in water environmental and adsorption of different materials on their surface, which result in the inaccuracy in measured DO values. It is thus important to develop effective methods to estimate DO concentrations by using other environmental variables, which may reduce farmers' cost because DO sensors are not used. In this research, the collected environmental data, including temperature, pH, ammonia nitrogen, turbidity, were used to estimate DO concentrations in crab ponds. The data were preprocessed to eliminate missing values and outlier. Correlation analysis was applied to determine the relationship between environmental variables (temperature, pH, ammonia nitrogen, turbidity) and DO to show the rationale of using these four variables to forecast DO concentration. Principal component analysis was used to reduce the dimension of environmental data to reduce computation cost. For DO concentration estimation, it is more important to make the estimation of DO concentration at low values more accurate because DO concentration at low values is dangerous to crabs. This implies that estimation of DO concentrations at low or high values should be treated differently and applied different rates. Based on the Long Short-Term Memory (LSTM), a low DO concentration estimation model of Low Dissolved Oxygen Long Short-Term Memory(LDO-LSTM), which can improve the estimation accuracy of low DO values was proposed by optimizing the loss function of LSTM back propagation. The loss function of LDO-LSTM was based on the Mean Absolute Percentage Error (MAPE). According to the trend of DO, the true DO and the estimated DO values were applied weight functions. The Root Mean Square Error (RMSE) and the MAPE were used to evaluate the performance of LDO-LSTM and LSTM in DO estimation. Experimental results show that the value of RMSE and MAPE were stable at about 0.1 for LSTM and LDO-LSTM in forecasting DO when dissolved oxygen was higher than 6mg/L and the value of RMSE and MAPE of LDO-LSTM were lower than LSTM by 0.25 and 0.139. The results prove that the proposed method can not only provide desirable estimation accuracy for DO concentrations at high values but also make the estimated DO concentrations at low values more accurate. This research is expected very useful in reducing aquaculture costs and improving accuracy in forecasting DO especially at low values.
 Select Recognition and localization method of occluded apples based on K-means clustering segmentation algorithm and convex hull theory | Open Access Jiang Mei, Sun Sashuang, He Dongjian, Song Huaibo Smart Agriculture    2019, 1 (2): 45-54.   doi:10.12133/j.smartag.2019.1.2.201903-SA003 Abstract （869）   HTML （431）    PDF （1240KB）（692）       Accurate segmentation and localization of apple objects in natural scenes is an important part of wisdom agriculture research for information perception and acquisition. In order to solve the problem that apples recognition and positioning are susceptible to occlusion of leaves in natural scenes, based on the K-means clustering segmentation algorithm, the object recognition algorithm based on convex hull theory was proposed. And the algorithm was compared with the object recognition algorithm based on removing false contours and the full-contour points fitting object recognition algorithm. The object recognition algorithm based on convex hull theory utilized that apples were like circle, combining K-means algorithm with Otsu algorithm to separate fruit from background. The convex polygon was obtained by convex hull theory and fit it circle to determine the position of the fruit. To verify the effectiveness of the algorithm, 157 apple images in natural scenes were tested. The average overlap rates of the object recognition algorithm based on convex hull theory, the object recognition algorithm based on removing false contour points and the full-contour points fitting object recognition algorithm were 83.7%, 79.5% and 70.3% respectively, the average false positive rates were 2.9%, 1.7% and 1.2% respectively, and the average false negative rates were 16.3%, 20.5% and 29.7% respectively. The experimental results showed that the object recognition algorithm based on convex hull theory had better localization performance and environmental adaptability compared to the other two algorithms and had no recognition error, which can provide reference for occluded fruits segmentation and localization in the natural scenes.
 Select Distinguishing Volunteer Corn from Soybean at Seedling Stage Using Images and Machine Learning | Open Access FLORES Paulo, ZHANG Zhao, MATHEW Jithin, JAHAN Nusrat, STENGER John Smart Agriculture    2020, 2 (3): 61-74.   doi:10.12133/j.smartag.2020.2.3.202007-SA002 Online available: 12 October 2020 Abstract （1185）   HTML （2621）    PDF （1967KB）（687）       Volunteer corn in soybean fields are harmful as they disrupt the benefits of corn-soybean rotation. Volunteer corn does not only reduce soybean yield by competing for water, nutrition and sunlight, but also interferes with pest control (e.g., corn rootworm). It is therefore critical to monitor the volunteer corn in soybean at the crop seedling stage for better management. The current visual monitoring method is subjective and inefficient. Technology progress in sensing and automation provides a potential solution towards the automatic detection of volunteer corn from soybean. In this study, corn and soybean were planted in pots in greenhouse to mimic field conditions. Color images were collected by using a low-cost Intel RealSense camera for five successive days after the germination. Individual crops from images were manually cropped and subjected to image segmentation based on color threshold coupled with noise removal to create a dataset. Shape (i.e., area, aspect ratio, rectangularity, circularity, and eccentricity), color (i.e., R, G, B, H, S, V, L, a, b, Y, Cb, and Cr) and texture (coarseness, contrast, linelikeness, and directionality) features of individual crops were extracted. Individual feature's weights were ranked with the top 12 relevant features selected for this study. The 12 features were fed into three feature-based machine learning algorithms: support vector machine (SVM), neural network (NN) and random forest (RF) for model training. Prediction precision values on the test dataset for SVM, NN and RF were 85.3%, 81.6%, and 82.0%, respectively. The dataset (without feature extraction) was fed into two deep learning algorithms—GoogLeNet and VGG-16, resulting into 96.0% and 96.2% accuracies, respectively. The more satisfactory models from feature-based machine learning and deep learning were compared. VGG-16 was recommended for the purpose of distinguishing volunteer corn from soybean due to its higher detection accuracy, as well as smaller standard deviation (STD). This research demonstrated RGB images, coupled with VGG-16 algorithm could be used as a novel, reliable (accuracy >96%), and simple tool to detect volunteer corn from soybean. The research outcome helps provide critical information for farmers, agronomists, and plant scientists in monitoring volunteer corn infestation conditions in soybean for better decision making and management.
 Select Design and test of wheat stripe rust remote monitoring platform based on embedded system | Open Access Ji Yunzhou, Du Shengjia, Ji Tongkui, Song Huaibo Smart Agriculture    2019, 1 (3): 100-112.   doi:10.12133/j.smartag.2019.1.3.201903-SA004 Abstract （816）   HTML （293）    PDF （5092KB）（667）       Wheat stripe rust is an important biological disaster that affects the safe production of wheat in China for a long time. The number of spores of wheat stripe rust is a direct factor affecting its pathogenesis and transmission. At present, it mainly relies on the field sampling and investigation of agricultural technicians to predict and forecast. It is time-consuming and laborious, and difficult to achieve long-term monitoring of diseases, thus affecting the accuracy of forecasting and the timeliness of prevention and control. The existing automatic spore monitoring device also has the problems that the collecting device is mostly in the form of manual replacement of slides, and the direct acquisition of components in the air by a limited area of the slide may result in inaccurate sample collection and too small sample size. In order to further improve the monitoring and forecasting ability of wheat stripe rust, a wheat stripe rust monitoring device was designed and implemented, which based on the internet to build a wheat stripe rust monitoring platform, and based on the embedded system to establish a complete set of wheat stripe rust spore collection and image transmission processing device. Spore acquisition was performed using a slide adsorption device of "Six prism column + Electromagnet + Microscope". Control the up and down movement of the electromagnet to control the up and down movement of the slide; update the slide by controlling the rotation of the hexagonal shaft; obtain the image by controlling the time synchronization of the microscope and the shaft; control the cleaning solvent the smear and the movement of the cleaning block enable the slide to be cleaned. At the same time, a spore counting program based on the server platform was designed to process and analyze the collected slide images. The spore counting program used in this design is based on Python 3.6 and combined with the Skimage image processing package for spore image analysis and processing. The geometry factor feature based method was used, and the number of spores in the microscope field was finally obtained based on the regional attribute values. The experimental results show that the platform server image processing algorithm can achieve accurate counting of spores, the accuracy of counting the test images is 100%; the success rate of the slide switching system is 95%.This study can lay a foundation for the real-time monitoring of wheat stripe rust in the field, and can also provide references for the monitoring of other airborne diseases in the field.
 Select Developmental model of wheat smart production based on the integration of information technology, agricultural machinery and agronomy | Open Access Ma Xinming, Ma Zhaowu, Xu Xin, Xi Lei, Xiong Shuping, Li Haiyang Smart Agriculture    2019, 1 (4): 62-71.   doi:10.12133/j.smartag.2019.1.4.201910-SA001 Abstract （856）   HTML （1550）    PDF （1015KB）（665）       In order to study the development mode and realization way of smart agriculture, the technical route of agricultural information fusion of agricultural machinery in different production stages before, during and after wheat production was designed. Pre-production: use Beidou precision navigation technology and motion planning optimization method to realize the full area coverage path planning of the field operation of the automatic navigation tractor, combine the laser leveling equipment to realize the accurate and standardized land leveling and laser leveling, and realize the accurate and standardized operation of the land. On this basis, the spatial interpolation technology was used to make the variable fertilization prescription map and combining variable rate fertilizer machine and realized variable rate precise application of fertilizer and precise seeding. At the same time, combining with the optimal design of planting scheme, based on the prenatal database and knowledge base, it optimizes the decision-making of variety configuration and sowing time and seeding amount were optimized, and the software intelligent decision-making technology was used to recommend the varieties and sowing time and seeding amount suitable for planting at the decision-making point, and constructs the wheat and maize prenatal information service recommendation system based on WebGIS was constructed. In production: based on the image technology of automatic segmentation and color feature extraction of wheat image in the field environment, a remote monitoring model of wheat nutritional status with the function of wheat population image segmentation and nutritional estimation was established to realize the non-destructive monitoring of wheat nutritional status in the field environment. After production, the integrated measurement sensor, speed sensor, header height sensor and GPS were adopted, and controller area network bus was adopted with wireless communication technology, a real-time wheat yield measurement system was developed, which was installed on a large-scale combine harvester to carry out the real-time prediction service of wheat yield, so as to realize the synchronous process of wheat harvest and yield measurement, with the error less than 5%. The intelligent transformation of common agricultural machinery equipment and the research and development of sowing and harvesting equipment adapted to agricultural production were completed and realized, and the small scale with high-efficiency utilization of light and heat resources, increase of output and green development were studied. The model of wheat planting production was optimized .A real time measurement and prediction system for postpartum yield was developed, which included the selection of sowing date, fertilization recommendation, seedling growth and nutrition diagnosis. The experimental results show that the adoption of agricultural information fusion technology can increase wheat yield by 18.4%, input-output ratio by 16.6% and 7.9%, which shows that the intelligent agriculture of Henan province is effective and feasible.
 Select Design and Experimental Research of Long-Term Monitoring System for Bee Colony Multiple Features | Open Access HONG Wei​, XU Baohua​, LIU Shengping Smart Agriculture    2020, 2 (2): 105-114.   doi:10.12133/j.smartag.2020.2.2.202005-SA001 Abstract （557）   HTML （551）    PDF （1997KB）（665）       The pollination during bees’ foraging is vital to continue species on the earth. However, bee colonies in some areas of America and Europe frequently appeared colony collapse disorder in the past decade due to many possible factors such as climate change and pesticide usage, which has not received enough attention and positive response from human beings. In this research, bee colony’s activities were investigated with seven detectable features (i.e., weight, temperature, humidity, gas concentration, vibration, sound and entrance counts), and the applicability of the features was evaluated by considering four factors (i.e. the relevance to bee colony’s activities, the richness of information, the cheapness of cost and the simplicity of engineering). Based on the investigation and evaluation, an Internet of Things(IoT) based system was presented for long-time monitoring of bee colonies, which could hourly detect the temperature and humidity inside of hive, bee combs’ weight, bee colony’s sounds and bees’ counts of passing through hive entrance. In this system, each hive has an individual detection device for the monitoring of bee colony, and the colony information could be automatically collected and transferred to a remote cloud server which took responsible for the information storing. Finally, the users could freely visit the server to browse the history data and manage their bee colonies. Moreover, a 235 days continuous monitoring for Apis mellifera ligustica was performed from August, 2019 to April, 2020 to demonstrate the system performance, and long-time and one-day monitoring results were both analyzed. The monitoring results indicated that the system could continuously operate without human intervention, and the data could reveal bee colony’s activity and growth, e.g., the temperature and humidity could reflect the micro climate of the bee hive, the weight could show the forging and stock of food, the sounds contained lots of information about bees’ behavior and the entrance count was strongly related to the activeness and scale of bee colony. Compared with the reported monitoring system, this system is superior in the diversity of detected features, the capability of power self-support and the wireless of data transmission that can benefit to the system’s deployment in the field and long-term operation without maintenance. In the visible future, this system will effectively promote the study related to the biology of bee’s behavior, the reason of colony collapse disorder and the development of precision beekeeping.
 Select Using fusion of texture features and vegetation indices from water concentration in rice crop to UAV remote sensing monitor | Open Access Wan Liang, Cen Haiyan, Zhu Jiangpeng, Zhang Jiafei, Du Xiaoyue, He Yong Smart Agriculture    2020, 2 (1): 58-67.   doi:10.12133/j.smartag.2020.2.1.201911-SA002 Abstract （966）   HTML （2009）    PDF （1511KB）（623）       Water concentration is a key parameter to characterize crop physiological and healthy status. It is of great significance of employing unmanned aerial vehicle (UAV) low-altitude remote sensing technology to predict crop water concentration for crop breeding and precision agriculture management. UAV remote sensing has been widely used for monitoring crop growth status, mainly focusing on using vegetation indices to estimate crop growth parameters at single or several growth stages. Few studies have been performed on evaluating crop water concentration. Consequently, this study mainly used vegetation indices and texture features extracted from UAV-based RGB and multispectral images to monitor water concentration of rice crop during the whole growth period. Firstly, a multi-rotor UAV equipped with high-resolution RGB and multispectral cameras to collect canopy images of rice crop, and water concentration was also measured by ground sampling. Then, vegetation indices and texture features calculated from RGB and multispectral images were used to analyze the growth changes of rice. Finally, random forest regression method was used to establish a prediction model of water concentration based on different image features. The results show that: (1) vegetation index, texture features and ground-measured water concentration could be used to dynamically monitor rice growth, and there existed correlations among these parameters; (2) image features extracted from multispectral images possessed more potential than those from RGB images to evaluate water concentration of rice crop, and normalized difference spectral index NDSI771, 611 achieved the best prediction accuracy (R2 = 0.68, RMSEP = 0.039, rRMSE = 5.24%); (3) fusing vegetation indices and texture features could further improve the prediction of water concentration (R2 = 0.86, RMSEP = 0.026, rRMSE = 3.21%), and the prediction error of RMSEP was reduced by 16.13% and 18.75%, respectively. These results demonstrats that it is feasible to apply UAV-based remote sensing to monitor water concentration of rice crop, which provides a new insight for precision irrigation and decision making of field management.
 Select Beehive Key Parameters Online Monitoring System and Performance Test | Open Access YANG XuanJiang, LI Hualong​, LI Miao​, HU Zelin​, LIAO Jianjun​, LIU Xianwang​, GUO Panpan​, YUE Xudong​ Smart Agriculture    2020, 2 (2): 115-125.   doi:10.12133/j.smartag.2020.2.2.202004-SA001 Abstract （528）   HTML （467）    PDF （2059KB）（606）       With the development of information technology, using big data analysis, monitoring of Internet of Things, sensor perception, wireless communication and other technologies to build a real-time online monitoring system for beehive is a feasible solution for reducing the stress response of bee colony caused by check the beehive artificially. Focusing on situation that real-time monitoring in the closed environment of the beehive is difficult, the STM32F103VBT6 32-bit microcontroller, integrated with the temperature and humidity sensor, microphone, and laser beam sensor were used in this study to develop a low-power, continuous working online monitoring system for the multi-parameter information acquisition and monitoring of beehive key parameters. The system mainly includes core processing module, data acquisition module, data sending module and database server. The data collection module includes a temperature and humidity collection unit inside the beehive, a bee colony sound collection unit, a bee in and out nest number counting unit, etc., and transfers data by accessing the mobile communication network. The performance test results of system on-site deployment showed that the developed system could monitor the temperature and humidity in the beehive in real time, effectively distinguish the bees of entering and leaving the beehive, record the numbers of bees of entering and leaving the nest door, and the bee colony sounds that the automatically obtained were consistent with the standard sound distribution of bee colony. The results indicate that this system meets the design requirements, can accurately and reliably collect the beehive parameters data, and can be used as a data collection method for related research of bee colony.
 Select Yield Estimation Method of Apple Tree Based on Improved Lightweight YOLOv5 | Open Access LI Zhijun, YANG Shenghui, SHI Deshuai, LIU Xingxing, ZHENG Yongjun Smart Agriculture    2021, 3 (2): 100-114.   doi:10.12133/j.smartag.2021.3.2.202105-SA005 Abstract （792）   HTML （68）    PDF （3571KB）（594）       Yield estimation of fruit tree is one of the important works in orchard management. In order to improve the accuracy of in-situ yield estimation of apple trees in orchard, a method for the yield estimation of single apple tree, which includes an improved YOLOv5 fruit detection network and a yield fitting network was proposed. The in-situ images of the apples without bags at different periods were acquired by using an unmanned aerial vehicle and Raspberry Pi camera, formed an image sample data set. For dealing with no attention preference and the parameter redundancy in feature extraction, the YOLOv5 network was improved by two approaches: 1) replacing the depth separable convolution, and 2) adding the attention mechanism module, so that the computation cost was decreased. Based on the improvement, the quantity of fruit was estimated and the total area of the bounding box of apples were respectively obtained as output. Then, these results were used as the input of the yield fitting network and actual yields were applied as the output to train the yield fitting network. The final model of fruit tree production estimation was obtained by combining the improved YOLOv5 network and the yield fitting network. Yield estimation experimental results showed that the improved YOLOv5 fruit detection algorithm could improve the recognition accuracy and the degree of lightweight. Compared with the previous algorithm, the detection speed of the algorithm proposed in this research was increased by up to 15.37%, while the mean of average accuracy (mAP) was raised up to 96.79%. The test results based on different data sets showed that the lighting conditions, coloring time and with white cloth in background had a certain impact on the accuracy of the algorithm. In addition, the yield fitting network performed better on predicting the yield of apple trees. The coefficients of determination in the training set and test set were respectively 0.7967 and 0.7982. The prediction accuracy of different yield samples was generally stable. Meanwhile, in terms of the with/without of white cloth in background, the range of relative error of the fruit tree yield measurement model was respectively within 7% and 13%. The yield estimation method of apple tree based on improved lightweight YOLOv5 had good accuracy and effectiveness, which could achieve yield estimation of apples in the natural environment, and would provide a technical reference for intelligent agricultural equipment in modern orchard environment.
 Select Characteristics Analysis and Challenges for Fault Diagnosis in Solar Insecticidal Lamps Internet of Things | Open Access YANG Xing, SHU Lei, HUANG Kai, LI Kailiang, HUO Zhiqiang, WANG Yanfei, WANG Xinyi, LU Qiaoling, ZHANG Yacheng Smart Agriculture    2020, 2 (2): 11-27.   doi:10.12133/j.smartag.2020.2.2.202005-SA002 Abstract （1265）   HTML （2473）    PDF （3592KB）（568）       Solar insecticidal lamps Internet of Things (SIL-IoTs) is a novel physical agricultural pest control implement, which is an emerging paradigm that extends Internet of Things technology towards Solar Insecticidal Lamp (SIL). SIL-IoTs is composed of SIL nodes with functions of preventing and controlling of agricultural migratory pests with phototaxis feature, which can be deployed over a vast region for the purpose of ensuring pests outbreak area location, reducing pesticide dosage and monitoring agricultural environmental conditions. SIL-IoTs is widely used in agricultural production, and a number of studies have been conducted. However, in most current research projects, fault diagnosis has not been taken into consideration, despite the fact that SIL-IoTs faults have an adverse influence on the development and application of SIL-IoTs. Based on this background, this research aims to analyze the characteristics and challenges of fault diagnosis in SIL-IoTs, which naturally leads to a great number of open research issues outlined afterward. Firstly, an overview and state-of-art of SIL-IoTs were introduced, and the importance of fault diagnosis in SIL-IoTs was analyzed. Secondly, faults of SIL nodes were listed and classified into different types of Wireless Sensor Networks (WSNs) faults. Furthermore, WSNs faults were classified into behavior-based, time-based, component-based, and area affected-based faults. Different types of fault diagnosis algorithms (i.e., statistic method, probability method, hierarchical routing method, machine learning method, topology control method, and mobile sink method) in WSNs were discussed and summarized. Moreover, WSNs fault diagnosis strategies were classified into behavior-based strategies (i.e., active type and positive type), monitoring-based strategies (i.e., continuous type, periodic type, direct type, and indirect type) and facility-based strategies (i.e., centralized type, distributed type and hybrid type). Based on above algorithms and strategies, four kinds of fault phenomena: 1) abnormal background data, 2) abnormal communication of some nodes, 3) abnormal communication of the whole SIL-IoTs, and 4) normal performance with abnormal behavior actually were introduced, and fault diagnosis tools (i.e., Sympathy, Clairvoyant, SNIF and Dustminer) which were adapted to the mentioned fault phenomena were analyzed. Finally, four challenges of fault diagnosis in SIL-IoTs were highlighted, i.e., 1) the complex deployment environment of SIL nodes, leading to the fault diagnosis challenges of heterogeneous WSNs under the condition of unequal energy harvesting, 2) SIL nodes task conflict, resulting from the interference of high voltage discharge, 3) signal loss of continuous area nodes, resulting in the regional link fault, and 4) multiple failure situations of fault diagnosis. To sum up, fault diagnosis plays a vital role in ensuring the reliability, real-time data transmission, and insecticidal efficiency of SIL-IoTs. This work can also be extended for various types of smart agriculture applications and provide fault diagnosis references.
 Select Edge extraction method of remote sensing UAV terrace image based on topographic feature | Open Access Yang Yanan, Kang Yang, Fan Xiao, Chang Yadong, Zhang Hanwen, Zhang Hongming Smart Agriculture    2019, 1 (4): 50-61.   doi:10.12133/j.smartag.2019.1.4.201908-SA005 Abstract （819）   HTML （988）    PDF （2234KB）（553）       Terraces achieve water storage and sediment function by slowing down the slope and soil erosion. This kind of terraced or wave-section farmland built along the contour line on is a high-yield and stable farmland facility with key construction in the dry farming area. It provides a strong guarantee for increasing grain production and farmers' income. In recent years, Gansu province has carried out a large amount of construction on terraces, however, due to the poor quality of the previous construction and management, the terraced facilities are in danger of being destroyed. In order to prevent and repair the terraces, it is necessary to timely and accurately extract the terrace information. The segmentation of terraces can be obtained by edge extraction, but the effect of satellite data is not ideal. With the continuous development of remote sensing technology of drones, the acquisition of high-precision terrace topographic information has become possible. In this research, the slope is extracted from the digital elevation model data in the data preprocessing stage, then the orthophoto data of the three experimental areas are merged with the corresponding slope data, respectively. Then the rough edge extraction method based on Canny operator and the fine edge extraction method based on multi-scale segmentation are used to perform edge detection on two data sources. Finally, the influence of slope on the extraction of terraced edges of remote sensing images of UAVs was analyzed based on the overall accuracy of edge detection and user accuracy. The experimental results showed that, in the rough edge extraction method, the data source accuracy of the fusion slope and image was improved by 23.97% in the OA precision evaluation, and the average improvement in the UV accuracy was 20.68%. In the fine edge extraction method, the accuracy based on the data source 2 was also increased by 17.84% on average in the OA accuracy evaluation of the data source 1, and by an average of 19.0% in the UV accuracy evaluation. The research shows that in the extraction of terraced edges of UAV remote sensing images, adding certain terrain features can achieve better edge extraction results.
 Select Remote sensing inversion of chlorophyll content in rice leaves in cold region based on Optimizing Red-edge Vegetation Index (ORVI) | Open Access Yu Fenghua, Xu Tongyu, Guo Zhonghui, Du Wen, Wang Dingkang, Cao Yingli Smart Agriculture    2020, 2 (1): 77-86.   doi:10.12133/j.smartag.2020.2.1.201911-SA003 Abstract （781）   HTML （1196）    PDF （1328KB）（549）       Rice is one of the important staple crops in China, and the rice planted in Northeast China, such as in Liaoning, Jilin, and Heilongjiang regions, is called cold-region rice. The chlorophyll content in rice leaves is the most direct indicator of the rice growth period and can directly reflect on its nutritional value. Previous research demonstrates that when the chlorophyll content of rice changes, the reflectance of different bands changes at the spectral level. In addition, most of the research studies on the inversion of the rice’s chlorophyll content are based on the complex machine learning algorithms. Although the accuracy of the inversion of the constructed model has been improved, the structure of the model is relatively complex, and the model’s transplantation and universality are poor in the actual application process. Hence, in this study, the inversion of the chlorophyll content of rice leaves in the cold regions was assessed. An ASD ground object spectrometer was employed to procure the hyperspectral information of rice leaves in the critical growth period. On the basis of the feature selection method, the hyperspectral feature subset of the inversion of the chlorophyll content of rice was selected. The characteristic band vegetation index was constructed by combining the chlorophyll content absorption coefficients, and the chlorophyll content of rice was established through using regression analysis. Additionally, by combining the chlorophyll content absorption coefficients in the PROSPECT model, referring to the construction method and form of the existing hyperspectral vegetation index, and using correlation analysis, the continuous projection method and the genetic algorithm optimized the rough set attribute reduction, the hyperspectral features was selected, and the red edge optimization index (ORVI) with only 695, 507, and 465nm hyperspectral feature bands was proposed. Compared with the other vegetation indexes retrieved from the IDB database, namely, ND528,587, SR440,690, CARI, and MCARI, the results demonstrated that the determination coefficients of the abovementioned vegetation index inversion models were 0.672, 0.630, 0.595, and 0.574 respectively. The accuracy of the inversion model of chlorophyll content established by ORVI vegetation was higher than that of other vegetation indexes wherein the decision coefficients of the model were R2 =0.726 and RMSE = 2.68, revealing that ORVI can be used as a hyperspectral vegetation index for the rapid inversion of the rice’s chlorophyll content in practical applications. This research can thereby provide some objective data support and model reference for remote sensing diagnosis and management decision of the rice’s chlorophyll content in the cold regions.
 Select Identification and Morphological Analysis of Adult Spodoptera Frugiperda and Its Close Related Species Using Deep Learning | Open Access WEI Jing, WANG Yuting, YUAN Huizhu, ZHANG Menglei, WANG Zhenying Smart Agriculture    2020, 2 (3): 75-85.   doi:10.12133/j.smartag.2020.2.3.202008-SA001 Online available: 27 September 2020 Abstract （1090）   HTML （793）    PDF （1962KB）（533）       Invasive pest fall armyworm (FAW) Spodoptera frugiperda is one of the serious threats to the food safety. Early warning and control plays a key role in FAW management. Nowadays, deep learning technology has been applied to recognize the image of FAW. However, there is a serious lack of training dataset in the current researches, which may mislead the model to learn features unrelated to the key visual characteristics (ring pattern, reniform pattern, etc.) of FAW adults and its close related species. Therefore, this research established a database of 10,177 images belonging to 7 species of noctuid adults, including FAW and 6 FAW close related species. Based on the small-scale dataset, transfer learning was used to build the recognition model of FAW adults by employing three deep learning models (VGG-16, ResNet-50 and DenseNet-121) pretrained on ImageNet. All of the models got more than 98% recognition accuracy on the same testing dataset. Moreover, by using feature visualization techniques, this research visualized the features learned by deep learning models and compared them to the related key visual characteristics recognized by human experts. The results showed that there was a high consistency between the two counterparts, i.e., the average feature recognition rate of ResNet-50 and DenseNet-121 was around 85%, which further demonstrated that it was possible to use the deep learning technology for the real-time monitoring of FAW adults. In addition, this study also found that the learning abilities of key visual characteristics among different models were different even though they have similar recognition accuracy. Herein, we suggest that when evaluating the model capacity, we should not only focus on the recognition rate, the ability of learning individual visual characteristics should be allocated importance for evaluating the model performance. For those important taxonomical traits, if the visualization results indicated that the model didn't learnt them, we should then modify our datasets or adjusting the training strategies to increase the learning ability. In conclusion, this study verified that visualizing the features learnt by the model is a good way to evaluate the learning ability of deep learning models, and to provide a possible way for other researchers in the field who want to understand the features learnt by deep learning models.
 Select Application Analysis and Prospect of Nanosensor in the Quality and Safety of Agricultural Products | Open Access WANG Peilong , TANG Zhiyong Smart Agriculture    2020, 2 (2): 1-10.   doi:10.12133/j.smartag.2020.2.2.202003-SA003 Abstract （1003）   HTML （1416）    PDF （1634KB）（524）       Nano materials with special size effect and excellent photoelectric properties have been highly valued and widely used in sensing analysis for greatly improving the performance of sensor analysis technology. In recent years, with the rapid development of smart agriculture, the quality and safety of agricultural products as an important part of agricultural production have attracted more and more attentions. There are many harmful ingredients, including pesticides, veterinary drugs, mycotoxins, and environmental contaminants etc, can potentially affected the quality and safety of agricultural products. Therefore, high performance analytical methods and sensing technologies are essential. Thanks to the emerging of nano materials, they provide a novel approach to improve the analytical performances of the sensing technologies. Furthermore, the sensors based on nano materials have also been utilized into monitoring the harmful substances in agricultural products. This review briefly described the properties and characteristics of several commonly used nano materials, including carbon nano materials, noble metal based nano materials and metal-organic framework materials, follow discussed on the common sensing and analysis technologies and devices based on nano materials, such as chemical sensor, biosensor, electrochemical sensor and spectral sensor, as well as the application of nano sensing technology in the quality and safety monitoring of agricultural products. Especially, the function of nano materials in sensors and analytical performances of the developed sensors had been discussed in detailed. Chemical sensor devices had the characteristics of fast response speed and high sensitivity. They were widely used in environmental monitoring, food safety and medical diagnosis, such as monitoring hazardous substances, clenbuterol and melamine, metronidazole, dioxins, etc. Biosensors were widely used to monitor prohibited additives, mycotoxins, and so on. Electrochemical sensors were typically equipped with miniaturized analysis equipment, which detected trace targets, including small organic molecules, metal ions and biomolecules, by measuring changed in current and other electrochemical signals. This article introduced surface-enhanced Raman spectroscopy (SERS) , which was one of spectral sensor, and its applications. SERS technology had the advantages of good sensitivity, single molecule detection capability and rich spectral information. It had become a promising spectral technology in the rapid sensing analysis of target objects, and is developing rapidly in the fields of food safety, environmental monitoring and health. Finally, the existing problems of nano sensing and analysis technology, such as achievement of high-performance nano materials, fabrication of sensing devices and construction of high flux sensing arrays were summarized. The development trend and prospect of nanosensor were also discussed. It is believed that the review could provide a lot of useful information for the readers to understand the development of sensing technology for the quality and safety of agricultural products.
 Select Design and Test of Disinfection Robot for Livestock and Poultry House | Open Access FENG Qingchun, WANG Xiu, QIU Quan, ZHANG Chunfeng, LI Bin, XU Ruifeng, CHEN Liping Smart Agriculture    2020, 2 (4): 79-88.   doi:10.12133/j.smartag.2020.2.4.202010-SA005 Abstract （901）   HTML （589）    PDF （2302KB）（521）       In order to improve the efficiency and safety of epidemic prevention and disinfection operations for livestock and poultry breeding, the disinfection robot system and the automatic disinfecting mode were researched in this study. The robot system is composed of four components, namely the automatic bearing vehicle, the disinfection spraying unit, the environmental monitoring sensors, and the controller. The robot supports two working modes: fully automatic mode and remote control mode. Aiming at the low-light and low-stress condition in the livestock and poultry houses, the method for detecting navigation path based on "Magnet-RFID" marks in the ground was proposed to realize the robot's automatic moving between the cages. In view of the large-flow and long-range requirements of the disinfectant's spraying, the air-assisted nozzle was designed, which could atomize and disperse the liquid independently. Based on the CFD simulation of airflow in the nozzle, the nozzle's parts structural parameters were optimized, as the angle of the cone-shaped guide pad and the inclination angle of the grid respectively determined as 75°and 90°. Finally, the robot's performance was tested in a poultry house in Beijing. The results showed that, the robot's mobile platform could automatically navigate at the speed of 0.1－0.5 m/s, and the maximal deviation distance between the actual trajectory and the expected path was 50.8 mm. The air-assisted nozzle could realize the atomization and diffusion of the liquid medicine at the same time, and was suitable for spraying the liquid medicine with a flow rate of 200－400 mL/min. The diameter (DV.9) of the liquid droplets formed was 51.82－137.23 μL, and became larger as the flow rate of the liquid medicine increased. The deposition density of spray droplets formed by the nozzle was 116－149/cm2, and decreased as the spray distance increased. The size and density of the liquid droplets of the spray nozzle in different areas of the cage all met the index requirements for effectively killing adherent pathogenic microorganisms. The robot could be applied as an automatic sprayer for disinfectant and immune reagent in the livestock and poultry house.
 Select Rapid detection of citrus Huanglongbing using Raman spectroscopy and Auto-fluorescence spectroscopy | Open Access Dai Fen, Qiu Zeyuan, Qiu Qian, Liu Chujian, Huang Guozeng, Huang Yalin, Deng Xiaoling Smart Agriculture    2019, 1 (3): 77-86.   doi:10.12133/j.smartag.2019.1.3.201812-SA026 Abstract （940）   HTML （75）    PDF （4597KB）（519）       In order to detect citrus Huanglongbing (HLB, also named citrus greening) quickly, Auto-fluorescence and Raman spectra of HLB leaf samples and healthy ones were collected and analyzed. PLS-DA models based on Auto-fluorescence spectra, Raman spectra and mixed spectra were established and compared respectively. Finally, ROC curves of the three models were drawn, and the performance of the models were further evaluated by using the area under curve AUC parameters. The results demonstrated spectral differences between Huanglongbing samples and healthy ones could be seen. With 785 nm laser irradiation, citrus leaf samples produced strong Auto-fluorescence and Raman peaks. The Auto-fluorescence of HLB leaves was weaker than that of healthy samples in the range of 800-1203 cm -1, but stronger in the range of 1206-1800 cm -1, and the slope of decline (absolute value) was smaller than that of healthy samples. The similar shapes were found in the Raman spectra of typical HLB samples and healthy ones. But the HLB samples had larger Raman peak intensity and spectral bandwidth at 1257 cm -1, 1396 cm -1, 1446 cm -1, 1601 cm -1 and 1622 cm -1 than healthy ones. The Raman peak intensity of HLB samples was weaker than that of healthy samples at 1006 cm -1, 1160 cm -1, 1191 cm -1 and 1529 cm -1 positions, suggesting that the carotenoid content of HLB samples was lower than healthy ones. The Auto-fluorescence model, the Raman spectral model and the mixed spectral model could distinguish two kinds of samples with the accuracy of 86.08%, 98.17% and 94.75%, respectively. Furthermore, AUCs of Receiver Operating Characteristic Curve (ROC) were calculated. The AUCs for the Auto-fluorescence model, the Raman spectral model and the mixed spectral model were0.9313、0.9991 and 0.9875, respectively. Through further analysis of ROC curve, the identification effect of the Raman spectral model was optimal. Raman spectroscopy could be a new way to explore the rapid diagnosis of citrus HLB.
 Select Current State and Challenges of Automatic Lameness Detection in Dairy Cattle | Open Access HAN Shuqing, ZHANG Jing, CHENG Guodong, PENG Yingqi, ZHANG Jianhua, WU Jianzhai Smart Agriculture    2020, 2 (3): 21-36.   doi:10.12133/j.smartag.2020.2.3.202006-SA003 Accepted: 25 September 2020 Online available: 25 September 2020 Abstract （1151）   HTML （688）    PDF （1720KB）（509）       Lameness in dairy cattle could cause significant economic losses to the dairy industry. Detection of lameness in a timely manner is critical to the high-quality development of dairy industry. The traditional method is visual locomotion scoring by dairy farmers, which is low efficiency, high cost and subjective. The demand for automated lameness detection is increasing. The review was conducted to find out the current state and challenges of automatic lameness detection technology development and to learn from the latest findings. The current automatic lameness detection systems were reviewed in this paper mainly rely on five technologies or combinations thereof, including machine vision, pressure distribution measuring system, wearable sensor system, behavior analysis and classification; the principle, function and features of these technologies were analyzed. Machine vision technique is to extract feature variables (e.g. back arch, head bob, abduction, stride length, walking speed, temperature, etc.) from video recordings of cattle movement by image processing. Pressure distribution measuring system contains an array of load cells to sense gait variables, when dairy cattle are walking by. By using accelerometer with high frequency data collection, the gait cycle parameters can be extracted and used for lameness detection. By using wearable devices, the number of lying/standing bouts and their duration, the total time spent lying, standing and ruminating per day can be recorded for individual cattle. The lameness can also be detected by behavior analysis. Currently, most of these studies were in the stage of sensor development or validation of algorithm. A few studies were in the stage of validation of performance and decision support with early warning system. The challenges to apply automatic lameness detection system in dairy farm includes the difficulties of acquiring high quality data of lameness features, lack of techniques to detect early lameness, identification errors caused by individual gait differences among dairy cattle, difficulties to function well in unstructured environment and difficulties to evaluate the benefits. To accelerate the development of automatic lameness detection systems, recommendations are proposed as follows: ①promoting lameness data sharing and data exchange among dairy farms; ②developing individual-based lameness classification model; ③developing multifunctional smart station which can detect lameness, measure body condition score, weighing, etc; ④evaluating the significance of automatic lameness detection to the dairy industry from the perspective of animal welfare, environment and food safety.
 Select Research on the application of multi-source agricultural land spatial data for "Two-Zone" demarcation | Open Access You Jiong, Pei Zhiyuan, Wang Fei Smart Agriculture    2019, 1 (3): 56-66.   doi:10.12133/j.smartag.2019.1.3.201906-SA005 Abstract （602）   HTML （87）    PDF （5259KB）（489）       The basis and premise of developing intelligent agriculture is digitization, especially digitization of agricultural land resources utilization, agricultural land ownership, agricultural production and other agricultural elements. At present, China's agriculture digitization is at a low level, the spatial information of agricultural land resources are applied few. It is necessary to accelerate the application of the big data with respect to agricultural land for agricultural production information collecting and agricultural policy implementing to promote the development of China's intelligent agriculture. One typical case is "food production function zone" and "important agricultural product production protection zone"(Two-Zone) demarcation. In order to realize the study on the technologies of "Two-Zone" demarcation, in this research, the following work was conducted . Firstly, the basic concept of the multi-source spatial data with respect to agricultural land was elaborated, and the existing multi-source spatial data with respect to agricultural land were summarized into four categories. Then, the workflows of "Two-Zone" demarcation was summed up. Considering the topological requirements of digital mapping for "Two-Zone" and the business requirements of intelligent management for agricultural production in "Two-Zone", a three-level spatial structure of "zone-patch-plot" was designed for "Two-Zone" demarcation. The key technology of digital mapping was proposed, based on the analysis of the functions of "Two-Zone" and the "zone-patch-plot" spatial structure, which integrate existing multi-source farmland spatial data depending on the relevance of spatial distribution and semantic attributes and then realize "Two-Zone"'s spatial distribution map at a specific spatial scale. The key technology of establishing the database for "Two-Zone" demarcation was also proposed, which realizes the abstraction of the geographical space entity delimited by "Two-Zone" from the perspective of spatial information structure. Therefore, the key technologies of "Two-Zone" demarcation based on multi-source agricultural land spatial data was scientifically designed, through the key work such as data acquisition, digital mapping and database construction. Finally, the key scientific problems in the technical links were extracted, which shown that "Two-Zone" demarcation requires a comprehensive consideration of data sources and user requirements, and it is necessary to analyze the availability of data with respect to multi-source agricultural land, decreasing the influence derived from the bias and partial loss of data with respect to multi-source agricultural land. Further consideration about statuses of the land use and crop planting in the farmland of "Two-Zone" is also needed. This study will provide a basic support for the intelligent management of agricultural land resources in the "Two-Zone".
 Select Design and Application of Facility Greenhouse Image Collecting and Environmental Data Monitoring Robot System | Open Access GUO Wei, WU Huarui, ZHU Huaji Smart Agriculture    2020, 2 (3): 48-60.   doi:10.12133/j.smartag.2020.2.3.202007-SA006 Online available: 14 October 2020 Abstract （824）   HTML （1956）    PDF （2668KB）（486）       China's facility horticulture has developed rapidly in the past 30 years and now comes to the first in the world in terms of area. However, the number of farmers is decreasing. "Machine replaces labor" has become the current research hotspot. In order to realize the fine collection of crop images and environmental monitoring data, a three-dimensional environmental robot monitoring system for crops was designed. The robot consists of three parts: perception center, decision center and execution center, which carry out environmental perception from machine perspective, data analysis, decision instruction generation and action execution respectively. In perception layer, the system realized real-time videos, images, data monitoring such as air temperature, air humidity, illumination intensity and concentrations of carbon dioxide in grid scale from multi-angle with high accuracy. At the system level, automatic speech recognition was integrated to make the system easier to use, especially for farmers who usually work in the fields. In transport layer, monitoring data and control instructions were converged to local data center through wireless bridges. Concretely, transmission mode was chosen according to different characteristics of data, wire transmission is available for big size data, such as images and videos, while wireless transmission is mainly applied to small size data, such as environmental monitoring parameters. In data processing layer, feedbacks and control instructions were made by multi-source heterogeneous data of crop model analysis, in terms of commands, independent inspection mode and real-time remote-control mode were available for users. Plant type, user information, historical data and management data were taken into consideration. Finally, in application layer, the system provided web and mobile intelligence services that could be used for the whole growth periods in terms of images, real-time videos, monitoring data collection and analysis of cucumbers, tomatoes, greenhouse peaches, etc. The system has been demonstrated and applied in solar greenhouse No. 7 of Beijing Xiaotangshan National Precision Agriculture Base and No. 5 of Shijiazhuang Agricultural and Forestry Science Research Institute with good achievements. Farmers and researchers have realized real-time monitoring, remote control and management. On one hand, the system can used to avoid working in extreme environment, such as high temperature and pesticide environment. On the other hand, with the help of the robot, independent inspection and data collection could achieve instead of people, and it is very intuitive in time-saving and indirect costs saving for productions and researchers. The results showed that the system could be widely applied in greenhouse facilities production and research.
 Select Distilled-MobileNet Model of Convolutional Neural Network Simplified Structure for Plant Disease Recognition | Open Access QIU Wenjie, YE Jin, HU Liangqing, YANG Juan, LI Qili, MO Jianyou, YI Wanmao Smart Agriculture    2021, 3 (1): 109-117.   doi:10.12133/j.smartag.2021.3.1.202009-SA004 Online available: 22 February 2021 Abstract （806）   HTML （62）    PDF （1643KB）（480）       The development of convolutional neural networks(CNN) has brought a large number of network parameters and huge model volumes, which greatly limites the application on devices with small computing resources, such as single-chip microcomputers and mobile devices. In order to solve the problem, a structured model compression method was studied in this research. Its core idea was using knowledge distillation to transfer the knowledge from the complex integrated model to a lightweight small-scale neural network. Firstly, VGG16 was used to train a teacher model with a higher recognition rate, whose volume was much larger than the student model. Then the knowledge in the model was transfered to MobileNet by using distillation. The parameters number of the VGG16 model was greatly reduced. The knowledge-distilled model was named Distilled-MobileNet, and was applied to the classification task of 38 common diseases (powdery mildew, Huanglong disease, etc.) of 14 crops (soybean, cucumber, tomato, etc.). The performance test of knowledge distillation on four different network structures of VGG16, AlexNet, GoogleNet, and ResNet showed that when VGG16 was used as a teacher model, the accuracy of the model was improved to 97.54%. Using single disease recognition rate, average accuracy rate, model memory and average recognition time as 4 indicators to evaluate the accuracy of the trained Distilled-MobileNet model in a real environment, the results showed that, the average accuracy of the model reached 97.62%, and the average recognition time was shortened to 0.218 s, only accounts for 13.20% of the VGG16 model, and the model size was reduced to only 19.83 MB, which was 93.60% smaller than VGG16. Compared with traditional neural networks, distilled-mobile model has a significant improvement in reducing size and shorting recognition time, and can provide a new idea for disease recognition on devices with limited memory and computing resources.
 Select An algorithm for estimating field wheat canopy light interception based on Digital Plant Phenotyping Platform | Open Access Liu Shouyang, Jin Shichao, Guo Qinghua, Zhu Yan, Baret Fred Smart Agriculture    2020, 2 (1): 87-98.   doi:10.12133/j.smartag.2020.2.1.202002-SA004 Abstract （1036）   HTML （1393）    PDF （1794KB）（475）       The capacity of canopy light interception is a key functional trait to distinguish the phenotypic variation over genotypes. High-throughput phenotyping canopy light interception in the field, therefore, would be of high interests for breeders to increase the efficiency of crop improvement. In this research, the Digital Plant Phenotyping Platform（D3P） was used to conduct in-silico phenotyping experiment with LiDAR scans over a wheat field. In this experiment virtual 3D wheat canopies were generated over 100 wheat genotypes for 5 growth stages, representing wide range of canopy structural variation. Accordingly, the actual value of traits targeted were calculated including GAI (green area index), AIA (average inclination angle) and FIPARdif (the fraction of intercepted diffuse photosynthetically activate radiation). Then, virtual LiDAR scanning were accomplished over all the treatments and exported as 3D point cloud. Two types of features were extracted from point cloud, including height quantiles (H) and green fractions (GF). Finally, an artificial neural network was trained to predict the traits targeted from different combinations of LiDAR features. Results show that the prediction accuracy varies with the selection of input features, following the rank as GF + H > H > GF. Regarding the three traits, we achieved satisfactory accuracy for FIPARdif (R2=0.95) and GAI (R2=0.98) but not for AIA (R2=0.20). This highlights the importance of H feature with respect to the prediction accuracy. The results achieved here are based on in-silico experiments, further evaluation with field measurement would be necessary. Nontheless, as proof of concept, this work further demonstrates that D3P could greatly facilitate the algorithm development. Morever, it highlights the potential of LiDAR measurement in the high-throuhgput phenopyting of canopy light interpcetion and structural traits in the field.
 Select A Fluorescence Based Dissolved Oxygen Sensor | Open Access GU Hao​, WANG Zhiqiang​, WU Hao​, JIANG Yongnian​, GUO Ya Smart Agriculture    2020, 2 (2): 48-58.   doi:10.12133/j.smartag.2020.2.2.202005-SA004 Abstract （684）   HTML （212）    PDF （1763KB）（471）       The measurement of dissolved oxygen content in water is of great significance to aquaculture. However, the dissolved oxygen sensors on the market in China are expensive, and are difficult to maintain continuous online measurement and update parts, so they cannot be widely applied in real production and play expected role in the aquaculture Internet of things(IoT). Based on the principle of fluorescence quenching, a low cost and easy maintenance of dissolved oxygen sensor was developed in this work based on the relationship between the concentration of dissolved oxygen in water and the phase difference of fluorescence signal. The self-made oxygen-sensitive membrane was used to generate red fluorescence which being excited by blue light, and the fluorescence life was regulated by the concentration of dissolved oxygen. Photoelectric conversion circuit with optical signal sensing device was designed to sense optical signal. The STM32F103 microprocessor was used as the main control chip, and the lower computer program was programmed to generate the excitation light pulse. The phase-sensitive detection principle and fast Fourier transform (FFT) were used to calculate the phase difference between the excitation light and the reference light, which was converted into the concentration of dissolved oxygen and realized the measurement of dissolved oxygen. The fluorescence detection part and the main control part of the system were designed as detachable independent modules, and shield lines were used to plug and pull directly, so as to facilitate replacement and maintenance and realize online remote measurement. The testing results showed that, the measurement range of the sensor was 0-20 mg/L, system time delay was less than 2 s, and the life time of the oxygen sensitive membrane would be about 1 year. The dissolved oxygen sensor has the characteristics of convenient measurement, stable result output, low cost and small volume, which will lay a good foundation for the development and marketization of low-cost dissolved oxygen sensors in aquaculture industry of China.
 Select Recognition method for corn nutrient based on multispectral image and convolutional neural network | Open Access Wu Gang, Peng Yaoqi, Zhou Guangqi, Li Xiaolong, Zheng Yongjun, Yan Haijun Smart Agriculture    2020, 2 (1): 111-120.   doi:10.12133/j.smartag.2020.2.1.202001-SA001 Abstract （778）   HTML （1266）    PDF （2440KB）（468）       Excessive application of water and fertilizer not only causes resources serious waste of, but also causes serious environmental pollution. The implementation of precision irrigation and fertilization can effectively reduce nutrient loss and environmental pollution, save irrigation water and improve the utilization rate of water and fertilizer resources, which is one of the important ways to promote the sustainable development of agriculture. The use of the integrated water-fertilizer equipment can effectively improve the utilization rate of water-fertilizer resources, but it is necessary to know the nutritional status of crops and water-fertilizer demand before operation. To acquire the information by hand-held measuring instruments, there are some disadvantages, such as poor timeliness and high labor intensity. In response to the above problems, this study took the common corn crop as an example, used the DJI Phantom III drone to carry RedEdge-M multispectral camera to collect multispectral images of corn crops over the fields, and measured nitrogen and moisture content of corn plants by YLS-D series plant nutrition tester. Based on this information, the collected images were divided into 3 levels, each level contains 530 five channel images (2650 single channel images), including 480 five channel images (2400 single channel images) in the training set and 50 five channel images (250 single channel images) in the verification set, and a method of identifying the nutritional status of corn crops based on convolutional neural network was proposed. Based on the TensorFlow deep learning framework, ResNet18 convolution neural network model was constructed. By entering color image data and five-channel multispectral image data into the model, the nutritional status recognition model of corn plant suitable for color image and multispectral image was trained, and the experimental results showed that the trained model could be used to recognize the multispectral images of corn, and the nutritional status of corn, topdressing guidance and GPS information could be outputted, the correct rate of the recognition color image model in the verification set was 84.7%. The correct rate of identifying multispectral image model in the verification set was 90.5%, the average time of model training was 4.5h, and the average time of recognizing a five channel image is 3.56 seconds, which can detect the nutritional status of corn crops quickly and undamaged, and provides a theoretical and technical basis for the accuracy of the application of water fertilizer in intelligent agriculture.
 Select Effect of Downwash Airflow Field of 8-rotor Unmanned Aerial Vehicle on Spray Deposition Distribution Characteristics under Different Flight Parameters | Open Access WANG Changling, HE Xiongkui, BONDS Jane, QI Peng, YANG Yi, GAO Wanlin Smart Agriculture    2020, 2 (4): 124-136.   doi:10.12133/j.smartag.2020.2.4.202003-SA005 Online available: 28 October 2020 Abstract （730）   HTML （269）    PDF （2470KB）（468）       Pesticide application using UAV sprayer has become a new highlight in the development of agricultural machinery and plant protection in China. Spray droplets from UAV could reach the crop canopy and deposit on the control target surface under the assistance of rotor's downwash airflow after atomization, including a secondary atomization effect of airflow on the droplets, so the spray performance of aerial pesticide application is inseparable from the effect of the rotor's downwash airflow field. In order to explore the effect of downwash airflow field on UAV's spray deposition characteristics, taking the main model of eight-rotor UAV with "X-type" as the research object and designing the actual measuring test, a multi-channel micro-meteorology measurement system(MMMS) was used to determine the downwash airflow speed at different horizontal positions, and meanwhile the tracer Allura Red solution was applied instead of chemicals to obtain the distribution characteristics of spray deposition. The visual analysis of the measured results of the downwash airflow field distribution was focused, and then the distribution characteristics of both the downwash airflow field and the droplet deposition at a certain flight height and speed, and the correlation relationship between them were analyzed. During the flight operation of the 8-rotor UAV, as the flight speed increased from 1.0 to 6.0 m/s and the flight height increased from 1 to 2 m, the intensity of the downwash airflow field in directions of X, Y, and Z generally changed from strong to weak, and the distribution state changed from concentration to dispersion; the X direction airflow was the vortex generated by the interaction between the downwash airflow and the outside air and its effect on droplets was reversed flight direction; the airflow in Y direction was to the both sides from flight path, caused by the combination of downwash airflow and ground effect; the airflow in Z direction, the vertical downward component of the downwash airflow, had a direct promotion effect on spray deposition. Significant negative correlations were shown between both the flying speed and the peak value in the range of the downwash airflow field (P <0.05, r = -0.836), and the flying speed and the average deposition within the effective spray swath(P <0.05, r = -0.833). When the flight speed was 1.0 and 3.0 m/s, the droplet deposition showed a very significant positive correlation with downwash airflow speed(P <0.01, r> 0), that was, the stronger the downwash airflow field in the vertical ground direction, the more droplets deposited in the effective spray swath. When the flight speed increased to 6.0 m/s, the wind speed was significantly reduced, and the promotion effect of the downwash airflow field on the droplet deposition disappeared(P> 0.05). The operation speed of UAV should not be set faster than 6.0 m/s to avoid the chemicals loss caused by the weakened effect of the downwash airflow field. The findings of this study are expected to provide theoretical basis and data support for improving the quality of low-altitude and low-volume application operations and the formulation of UAV field operations specifications.
 Select Automatic Weed Detection Method Based on Fusion of Multiple Image Processing Algorithms | Open Access MIAO Zhonghua, YU Xiaoyao, XU Meihong, HE Chuangxin, LI Nan, SUN Teng Smart Agriculture    2020, 2 (4): 103-115.   doi:10.12133/j.smartag.2020.2.4.202010-SA006 Abstract （712）   HTML （1513）    PDF （4725KB）（463）       Automatic weeding is a hot research field of smart agriculture, which has many benefits such as achieving precise weed control, saving human cost, and avoiding damage on crops, etc. Recently, many researchers have focused on the research using the deep learning method, such as the convolutional neural network (CNN) and recurrent neural network (RNN) and have achieved decent outcomes related to the automatic weed detection. However, there are still generally problems of the projects such as weak robustness and excessive reliance on a large number of samples. To solve these problems, a recognition algorithm for automatic identification and weed removal was designed, and a soybean field weed detection and localization method based on the fusion of multiple image processing methods was proposed in this study. The images and video stream were obtained through the camera mounted on a mobile robot platform. Firstly, the soil background inside the image was segmented from the foreground (including the weeds and crops) by setting the threshold for a specific color space (hue). Then, three different methods including the area threshold method, template matching and saturation threshold method were used to classify the crops and weeds. Finally, based on a proposed innovative voting method, the three recognition methods were comprehensively weighed and fused to achieve more accurate recognition and localization results of the crops and weeds inside the image. Experimental validations were carried out using the samples obtained through the moving platform, and the experimental results showed that the average accuracy of the proposed weed detection algorithm was as high as 98.21%, while the recognition error was only 1.79%. Meanwhile, compared with each single method as the scale threshold, template matching and saturation threshold, the fused method based on the weighted voting has been able to raise the average accuracy by 5.71%. Even though the samples used in the validations were limited in covering different scenarios, the high recognition accuracy has proved the practicability of the proposed method. In addition, the robustness test that images with raindrop and shadow interference in the complex and unstructured agricultural scene was carried out, and satisfied results showed that above 90% of the plant were successfully detected, which verified the fine adaptability and robustness of the proposed method.
 Select Visual Positioning and Harvesting Path Optimization of White Asparagus Harvesting Robot | Open Access LI Yang, ZHANG Ping, YUAN Jin, LIU Xuemei Smart Agriculture    2020, 2 (4): 65-78.   doi:10.12133/j.smartag.2020.2.4.202009-SA003 Abstract （687）   HTML （997）    PDF （3495KB）（455）       For white asparagus selective harvesting is the best harvesting method determined by its growth characteristics. Focusing on the difficulties that the texture and the color of shoot tips are similar with ridge surface under machine vision, the recognition method of asparagus shoots and precise positioning were studied in this research. A changeable scale ROI detection method was proposed, with the fusion of color transformation, histogram averaging, morphology and texture filtering. After that, a harvesting path optimization method of multiple asparaguses was proposed, which solved the problem of harvesting efficiency reduction caused by unreasonable harvesting paths. Firstly, real-time acquisition of the image and individual RGB channel Gaussian filtering were implemented. Based on the HSV color transformation and histogram averaging processing, the asparagus shoot and soil feature clustering analysis were carried out. According to the sprout degrees of asparaguses, the changeable scale ROI detection method was studied. The morphology and the texture of the shoot, and soil were statistically analyzed. According to the texture feature parameters, the position of shoot was determined and its geometric center was calculated. Secondly, in order to improve harvesting efficiency, a path optimization algorithm based on multiple asparaguses was designed according to the locations of the asparaguses and the bins to obtain the optimal harvesting path. Finally, in order to verify the reliability of the proposed methods, asparagus shoot location and harvest verification tests were carried out on the established harvesting test platform. The results showed that the recognition rate of white asparagus in the visual system was more than 98.04%, the maximum positioning error of the center coordinate of the white asparagus shoot was 0.879 mm in X direction and 0.882 mm in Y direction, and the average reduction of end-effector motion distance could be 43.89% after path optimization under different circumstances, the success rate of end-effector localization was 100% and the harvest rate of white asparagus in the laboratory test was 88.13%. The research verified the feasibility of the visual positioning and harvesting path optimization of the white asparagus selective harvesting robot.
 Select Application of Satellite Remote Sensing Yield Estimation Technology in Regional Revenue Protection Crop Insurance: A Case of Soybean | Open Access CHEN Ailian, LI Jiayu, ZHANG Shengjun, ZHU Yuxia, ZHAO Sijian, SUN Wei, ZHANG Qiao Smart Agriculture    2020, 2 (3): 139-152.   doi:10.12133/j.smartag.2020.2.3.202006-SA002 Online available: 18 November 2020 Abstract （759）   HTML （788）    PDF （4211KB）（454）       In recent years, revenue protection crop insurance is an innovative insurance that has been prioritized in China. But it still lacks the support of the third-party yield data around crop harvest time. Aiming to provide objective yield data for revenue protection crop insurance, satellite remote sensing production estimation technology was employed to discuss its application mode and applicability. Taking the soybean revenue protection insurance in Jiaxiang county, Shandong province as an example, we first extracted soybean planting plots, calculated vegetation index and crop physiological parameters based on Sentinel-2 satellite images in 2018 . Combining to TRMM precipitation data from TRMM precipitation-monitoring radar satellite and MODIS land surface temperature data from Terra/Aqua satellite and site yield data, we established a multi-parameter linear regression model, and estimated soybean yield per unit area. The crop extraction results showed that the soybean planting area in the study area was 1.24 km2, which was in good agreement with the 1.27 km2 reported by the local agricultural bureau; and with using the actual measurement plots, the remote sensing identification accuracy of the planting distribution plots reached 90%. The yield estimation results showed that the NDVI of the soybean pod stage on August 23 and the leaf area index of the soybean seedling stage on September 7 explained the soybean yield per hectare the best, and the average estimated yield of the whole area was 244,500 kg/m2, which reflects the severely affected agricultural conditions, comparing to 299,800 kg/km2 in previous years.The regression coefficient between the estimated yield data and the measured data reached 0.92, which meet the application needs.With this results, the estimated yield of different towns can be summarized, and the regional yield was present, and was used as the real yield in 2018, multiplying with the average soybean price around October 11 to December 10 from the local price bureau, the real revenue was obtained. Compared the real revenue to the expected revenue in the contract of insurance, the claims work was decided. The results indicated that the Sentinel-2 satellite data could be used to identify the soybean planting distribution in the study area accurately, and to complete the yield estimation as soon as one week after the soybean harvest, which could guide the insurance company's claims work. The whole methodology is capable of aiding the claims work in revenue protection crop insurance.
 Select State-of-the-Art and Prospect of Automatic Navigation and Measurement Techniques Application in Conservation Tillage | Open Access WANG Chunlei, LI Hongwen, HE Jin, WANG Qingjie, LU Caiyun, CHEN Liping Smart Agriculture    2020, 2 (4): 41-55.   doi:10.12133/j.smartag.2020.2.4.202002-SA002 Online available: 10 December 2020 Abstract （884）   HTML （1663）    PDF （2504KB）（453）       Intelligent technology is one of the important approaches to improve working quality and efficiency of conservation tillage machine. Automatic navigation and measurement & control technology, which are the key components of intelligent technology, have been rapidly developed and applied in conservation tillage. In this paper, the application progress of automatic navigation and measurement & control technology in conservation tillage, including automatic guidance technology, operation monitoring technology for operating parameters and operation controlling technology of conservation tillage machine were reviewed. Firstly, wheat-maize planting mode was taken as an example to expound the automatic guidance technology for conservation tillage machine due to many types of crop planting modes under conservation tillage. According to the principle of navigation, it could be divided into automatic guidance technology of touch type, automatic guidance technology of machine vision type and automatic guidance technology of GNSS type. From these different automatic guidance technologies for no/minimum tillage seeding in maize stubble field, the application progress of automatic navigation technology in conservation tillage machine was introduced in detail. Secondly, the development of the operation monitoring technology for operating parameters of conservation tillage machine was systematically presented as follows: 1) The rapid detection technology for surface straw coverage, including surface straw coverage before and after operation, which was of great significance for the determination of conservation tillage technology and the evaluation of the performance of the conservation tillage machine; 2) The monitoring technology for seeding parameters of no/minimum tillage planter, mainly contained seeding quantity, missed seeding and multiples seeding, which were the key indicators for seeding quality; 3) The monitoring technology for operating area of conservation tillage machine, which was mainly calculated based on the forward speed of the testing machine. Thirdly, the development status of operation controlling technology for conservation tillage machine was reviewed, mainly focusing on the compensation and controlling technology for missed seeding and operation depth controlling technology. The operation controlling technology for conservation tillage machine, which was capable of realizing certain active control of the machine key components under the condition of accurate and real-time monitoring of the current operation status of conservation tillage machine, was important for working quality. To be specific, the operation depth controlling technology was composed of seeding depth, subsoiling depth and topsoil tillage depth. In the end, on the basis of summarizing the current application of automatic navigation and measurement technology in conservation tillage, the future research directions of automatic guidance technology, operation monitoring technology for operating parameters, and operation controlling technology in conservation tillage machine were prospected.
 Select Construction of Standard System Framework for Intelligent Agricultural Machinery in China | Open Access HU Xiaolu, LIANG Xuexiu, ZHANG Junning, MEI Anjun, LYU Chengxu Smart Agriculture    2020, 2 (4): 116-123.   doi:10.12133/j.smartag.2020.2.4.202004-SA002 Online available: 16 October 2020 Abstract （792）   HTML （542）    PDF （1107KB）（449）       Standard system is the overall strategic planning and implementation guidance for standardization in professional field. In view of the missing of standard system on intelligent agricultural machinery, a standard system framework was contributed for the industry of intelligent agricultural machinery in this study. Currently, in China, standardization work for the industry of intelligent agricultural machinery is carrying out unplanned and disorderly. Published standard is of limited number, and could not meet the industry needs. The adopted international standards take a high percentage of national standards, however, China-made intelligent agricultural machinery standard has not been promoted abroad. Based on the development goals and principles of standard system framework, 9 dimensions of level, binding force, generality, property, object, standard category, reference model, industry classification and industry sector were identified for the standard system framework of intelligent agricultural machinery. Three dimensional standard system framework was contributed for intelligent agricultural machinery. The level dimension included 5 elements of national standard, industry standard, local standard, group standard, and enterprise standard. The category dimension included 8 elements of safety, health, environmental protection, basic, methods, management, products, and others. The industry sector dimension included 9 elements of power machinery, seeding and fertilizing machinery, plant protection machinery, harvester, seed breeding and selection machinery, agricultural product storage and transport machinery, facility agriculture, livestock and poultry breeding machinery, and agricultural product processing machinery. In order to clear standard level and intuitively guide standard system table development, the three dimensional standard system framework was decomposed in two dimensions. The first layer was basis, included terminology, safety, environmental protection and reliability. The second layer was common features, included information perception, navigation and positioning, control communication, big data analysis, agricultural management platform. The third layer was applications, included operating power, seeding and fertilization, plant protection, harvesting, selection and breeding of seed, agricultural product storage, facility agriculture, livestock and poultry breeding, and agricultural product processing. Suggestions were proposed for standardization of intelligent agricultural machinery in China. Firstly, priorities of the standard system table should be worked out based on industry need and technological maturity. Secondly, practicability of the standard was suggested to be improved by developing the standard content based on industry needs and market prospect. In addition, a variety of resources of industry, university and research institute was suggested to be organized together to contribute to standardization work. In addition, the progress of international standardization was suggested to be tracked, and the China-made standard was suggested to be internationalized. Finally, the standardization work should be operated by the professional organizations and specialized talents. This standard system framework could be used to systematically guide the development, revision, implementation, and service of intelligent agricultural machinery standards, and lead the rapid development of intelligent agricultural machinery industry in China.
 Select Wheat Lodging Ratio Detection Based on UAS Imagery Coupled with Different Machine Learning and Deep Learning Algorithms | Open Access FLORES Paulo, ZHANG Zhao Smart Agriculture    2021, 3 (2): 23-34.   doi:10.12133/j.smartag.2021.3.2.202104-SA003 Abstract （610）   HTML （74）    PDF （1857KB）（448）       Wheat lodging is a negative factor affecting yield production. Obtaining timely and accurate wheat lodging information is critical. Using unmanned aerial systems (UASs) images for wheat lodging detection is a relatively new approach, in which researchers usually apply a manual method for dataset generation consisting of plot images. Considering the manual method being inefficient, inaccurate, and subjective, this study developed a new image processing-based approach for automatically generating individual field plot datasets. Images from wheat field trials at three flight heights (15, 46, and 91 m) were collected and analyzed using machine learning (support vector machine, random forest, and K nearest neighbors) and deep learning (ResNet101, GoogLeNet, and VGG16) algorithms to test their performances on detecting levels of wheat lodging percentages: non- (0%), light (<50%), and severe (>50%) lodging. The results indicated that the images collected at 91 m (2.5 cm/pixel) flight height could yield a similar, even slightly higher, detection accuracy over the images collected at 46 m (1.2 cm/pixel) and 15 m (0.4 cm/pixel) UAS mission heights. Comparison of random forest and ResNet101 model results showed that ResNet101 resulted in more satisfactory performance (75% accuracy) with higher accuracy over random forest (71% accuracy). Thus, ResNet101 is a suitable model for wheat lodging ratio detection. This study recommends that UASs images collected at the height of about 91 m (2.5 cm/pixel resolution) coupled with ResNet101 model is a useful and efficient approach for wheat lodging ratio detection.
 Select Estimation Method of Leaf Area Index for Summer Maize Using UAV-Based Multispectral Remote Sensing | Open Access SHAO Guomin, WANG Yajie, HAN Wenting Smart Agriculture    2020, 2 (3): 118-128.   doi:10.12133/j.smartag.2020.2.3.202006-SA001 Online available: 09 October 2020 Abstract （828）   HTML （760）    PDF （3246KB）（442）       Maize is an important food crop in China. In order to quickly and non-destructively estimate summer maize leaf area index (LAI) under different water stress conditions, in this study, maize samples with multiple irrigation treatments throughout the growth period were used for modeling analysis. Then, based on the unmanned aerial vehicle (UAV) multi-spectral remote sensing technology, combined with the summer maize LAI collected in the field during the same period, five kinds of vegetation indices, including the normalized difference vegetation index (NDVI), soil adjusted vegetation index (SAVI), enhanced vegetation index (EVI), green normalized difference vegetation index (GNDVI) and visible atmospherically resistant index (VARI) were selected in this research as model input parameters, and random forest regression algorithm was used to establish the relationship between the field maize canopy vegetation indices and LAI under different irrigation conditions during the entire growth period. The accuracies of the model were compared with that of the model established by the university linear regression and multiple linear regression algorithms. The results showed that under sufficient irrigation condition, the vegetation index using multiple linear regression model could well (R2 = 0.83, RMSE = 0.05) estimate LAI; under water stress conditions, the vegetation index using random forest regression model could well estimate LAI (R2 = 0.74~0.87, RMSE = 0.02~0.10), water stress factors had little effect on the random forest regression model, and NDVI and VARI contributed the LAI estimation model better. The spatial distribution map of LAI was generated based on the random forest regression algorithm. The above results showed that it was feasible to use the random forest regression algorithm to estimate the summer maize LAI under various irrigation conditions based on the UAV multi-spectral remote sensing technology. The results indicates that the model established has a good applicability. This research can provide technical and method support for the rapid and accurate monitoring of field summer maize LAI under different irrigation conditions during the entire growth period.
 Select Short-Term Price Forecast of Vegetables Based on Combination Model of Lasso Regression Method and BP Neural Network | Open Access YU Weige, WU Huarui, PENG Cheng Smart Agriculture    2020, 2 (3): 108-117.   doi:10.12133/j.smartag.2020.2.3.202008-SA003 Online available: 19 November 2020 Abstract （758）   HTML （398）    PDF （1295KB）（438）       Vegetables are an important part of residents' diet. The abnormal fluctuation of vegetable prices has caused losses to the economic interests of vegetable farmers and also affected the daily diet and quality of life of residents. However, there are some difficulties in vegetable price prediction, such as large price fluctuation and complicated influencing factors. Cucumber is the main category of vegetables and a common food on the daily table of residents and its recent price fluctuations have aroused widespread concern. In this research, taking cucumber as the research object, a combination model (L-BPNN) combining Lasso regression method and BP neural network was constructed to forecast the short-term price of cucumber. Firstly, the factors affecting the price of cucumber, such as supply, demand and circulation were analyzed. Then the price fluctuation characteristics of cucumber in China from 2010 to 2018 were analyzed and 24 factors were selected as the influencing factors of cucumber price. In the case of complex factors, Lasso regression was used to compress the 24 input influencing factors and the 12 remaining influencing factors with large correlation degree after compression were used as the input influencing factors of BP neural network. Among the 12 related factors , the positive effects included: land cost, per capita disposable income of urban residents, urban vegetable consumption price index, fuel surcharge, booth fee, packaging and processing fee, inflation rate, affected area and temperature deviation from normal value; negative effects included sown area, industrial support amount and average temperature. On this basis, a combination model combining Lasso regression method with BP neural network (L-BPNN) was constructed to forecast the short-term price of cucumber. The neural network was used to train and adjust the model between the input influencing factors and the output price. Compared with the regression analysis and intelligent analysis methods, the results show that the average relative error of L-BPNN combination model was the smallest, only 0.66%, which was 64.52%, 82.11% and 86.2% lower than Lasso regression model, BP neural network model and RBF neural network model respectively, and had higher prediction accuracy. The results of this study realizes the short-term price forecast of cucumber, and can also be extended to other vegetable varieties, which is of great significance for guaranteeing the income of vegetable farmers and stabilizing the market price of vegetables.
 Select Progress of Agricultural Drought Monitoring and Forecasting Using Satellite Remote Sensing | Open Access HAN Dong, WANG Pengxin, ZHANG Yue, TIAN Huiren, ZHOU Xijia Smart Agriculture    2021, 3 (2): 1-14.   doi:10.12133/j.smartag.2021.3.2.202104-SA002 Online available: 07 July 2021 Abstract （744）   HTML （112）    PDF （1255KB）（422）       Agricultural drought is a major factor that affects agricultural production. Traditional agricultural drought monitoring is mainly based on meteorological and hydrological data, and although it can provide more accurate drought monitoring results at the point level, there are still limitations in monitoring agricultural drought at the regional scale. The rapid development of remote sensing technology has provided a new mean of monitoring agricultural droughts at the regional scale, especially since the electromagnetic wavelengths sensed by satellite sensors in orbit now cover visible, near-infrared, thermal infrared and microwave wavelengths. It is important to make full use of the rich surface information obtained from satellite remote sensing data for agricultural drought monitoring and forecasting. This paper described the research progress of agricultural drought monitoring based on satellite remote sensing from three aspects: remote sensing index-based method, soil water content method and crop water demand method. The research progress of agricultural drought monitoring based on remote sensing index-based method was elaborated from five aspects: vegetation drought index, temperature drought index, integrated vegetation and temperature drought index, water drought index and microwave drought index; the research progress of agricultural drought monitoring based on soil water content method was elaborated from two aspects: soil water content retrieval based on visible to thermal infrared data and soil water content retrieval based on microwave data; the research progress of agricultural drought monitoring based on crop water demand method was elaborated from two aspects: agricultural drought monitoring based on crop canopy water content retrieval method and crop growth model method. Agricultural drought forecasting is a timeline prediction based on drought monitoring. Based on the summary of the progress of drought monitoring, the research progress of agricultural drought forecasting by the drought index method and the crop growth model method was further briefly described. The existing agricultural drought monitoring methods based on satellite remote sensing were summarized, and its shortcomings were sorted out, and some prospects were put forward. In the future, different remote sensing data sources can be used to combine deep learning methods with crop growth models and based on data assimilation methods to further explore the potential of satellite remote sensing data in the monitoring of agricultural drought dynamics, which can further promote the development of smart agriculture.
 Select | Open Access Smart Agriculture    2019, 1 (1): 98-98.   Abstract （675）      PDF （1706KB）（415）
 Select Near-Field Telemetry Detection of Soil Nutrient Based on Modulated Near-Infrared Reflectance Spectrum | Open Access JIAO Leizi, DONG Daming, ZHAO Xiande, TIAN Hongwu Smart Agriculture    2020, 2 (2): 59-66.   doi:10.12133/j.smartag.2020.2.2.202005-SA003 Abstract （491）   HTML （873）    PDF （1790KB）（391）       Proper soil nutrients content plays an important role in agricultural production—undernutrition would reduce crop yield and quality and overnutrition would cause environmental pollution. Though the traditional approaches based on sampling and chemical analysis can comprehensively and accurately measure soil nutrients, but the soil sampling and pretreatment process are cumbersome, complicated, time-consuming, and costly. Therefore, rapid and accurate measurement of soil nutrients is of great significance for precise fertilizer application, which can increase yield, improve crop quality, and alleviate environmental pollution. Toward this objective, a rapid soil nutrients detection method based on modulated near infrared spectroscopy for active near-field telemetry was proposed, which could effectively minimize effect of sunlight during the measuring process. Eight channels narrow-band laser diodes with wavelengths of 1260, 1310, 1350, 1410, 1450, 1510, 1550 and 1610 nm were selected as active lighting sources for measuring the reflectance of soil samples. Eight channels narrow-band laser diodes were symmetrically placed on a concentric circle. A photodetector with a circular photosensitive area of 5 mm in diameter was placed at the center of the concentric circle to maximize the reception of laser beam reflected by soil. A focusing lens was placed in front of the photodetector to collect the laser beam reflected from the soil sample to increase the sensitivity. The sensing area of the photodetector was located at the focus of the lens. seventy four groups of soil samples with known N content were divided into training set (54 groups) and prediction set (20 groups) for data analysis. The spectral reflectance significantly correlated with soil N content was screened by analyzing the training set based on a general linear model and a quantitative measurement model with R2 of 0.97 between the screened spectral reflectance and soil N content was achieve. The predicted soil N content obtained from prediction set based on the established model and the referenced soil N content of the prediction set had a R2 of 0.9, indicating that this method has an ability to quickly, as well as accurately detect soil nutrients.
 Select Foxtail Millet Ear Detection Approach Based on YOLOv4 and Adaptive Anchor Box Adjustment | Open Access HAO Wangli, YU Peiyan, HAO Fei, HAN Meng, HAN Jiwan, SUN Weirong, LI Fuzhong Smart Agriculture    2021, 3 (1): 63-74.   doi:10.12133/j.smartag.2021.3.1.202102-SA066 Abstract （748）   HTML （73）    PDF （2620KB）（376）       谷穗的检测和计数对于预测谷子产量和育种至关重要。但是，传统的谷穗计数主要基于人工统计，既费时又费力。为解决上述问题，本研究首先建立了一个包含784张图像和10,000个谷穗样本的谷穗检测数据集。提出了一种基于YOLOv4和自适应锚框调整的谷穗检测方法，可快速准确地检测特定框中的谷穗。通过自适应地调整锚框，可生成符合谷穗目标的候选框，从而提升检测的准确率。为验证该方法的有效性，采用了多个标准，包括平均精度（mAP），F1得分（F1-Score），精度（Precision）和召回率（Recall）进行评价。此外，设计了对比试验验证所提出方法的有效性，包括与其他模型（YOLOv2，YOLOv3和Faster-RCNN）进行比较来评估模型的性能，评估模型在不同交并比（IOU）取值下的性能，评估模型在自适应锚框调整下的谷穗检测性能，评估引起模型评价标准变化的原因，以及评估模型在不同原始输入图像尺寸下的性能。试验结果表明，YOLOv4获得了良好的谷穗检测性能。YOLOv4的mAP达到78.99%，F1-score达到83.00%，Precision达到87%和Recall达到79.00%，在所有评价标准上均比其他比较模型高出8%。试验结果表明，该方法具有较好的准确性和高效性。
 Select Optimal Model of Chicken Distribution Vehicle Scheduling Based on Order Clustering | Open Access CHEN Dong, Tian'en CHEN, JIANG Shuwen, ZHANG Chi, WANG Cong, LU Mengyao Smart Agriculture    2020, 2 (4): 137-148.   doi:10.12133/j.smartag.2020.2.4.202011-SA006 Abstract （430）   HTML （431）    PDF （2529KB）（374）       In order to solve the problems that orders are widely distributed, scheduling of distribution vehicle needs a lot of manpower,and high cost of chicken distribution in large-scale poultry enterprise, in this research, combined with the idea of solving vehicle routing optimization problem, a chicken distribution vehicle scheduling optimization model based on order location clustering was proposed. By introducing the K-means clustering algorithm, a distribution unit division method based on order location was implemented, an automated order location clustering process based on the elbow rule and contour coefficient method to realize the autonomous division of order distribution units was designed. On the basis of the divided groups of orders, the optimal delivery cost was taken as the objective function to establish a chicken delivery vehicle scheduling optimization model, and the model was solved with an improved genetic algorithm.The actual order data of a poultry company in Beijing was used to compare the results of the overall scheduling optimization in the case of orders without clustering and the scheduling optimization in the case of with clustering grouping. The results showed that the model in the case of orders with clustering could reduce the average daily mileage of delivery vehicles by 69% compared with orders without clustering, it could be seen that the optimization of order grouping with clustering algorithm was more suitable for vehicle scheduling scenarios with a large actual order position span and a large number of orders. Based on the above research, a vehicle scheduling optimization service system was developed, functions such as automatic order clustering, delivery vehicle scheduling optimization were realized, and model service application programming interface was customized.The practical application results of the model showed that, the average total mileage per day decreased by 5.04% compared with manual routing, the manual routing time took 20 to 30 minutes per day, and the average time for the model to complete the routing was 14.49 s. The goal of providing intelligent delivery vehicle scheduling optimization services for poultry industry enterprises has been achieved, which could effectively improve the operation efficiency and reduce the distribution cost of the poultry enterprise.
 Select Comparison analysis of spatial and spectral feature in vegetation classification based on AVIRIS hyperspectral image | Open Access Fu Yuanyuan, Yang Guijun, Duan Dandan, Zhang Yongtao, Gu Xiaohe, Yang Xiaodong, Xu Xingang, Li Zhenhai Smart Agriculture    2020, 2 (1): 68-76.   doi:10.12133/j.smartag.2020.2.1.201911-SA005 Abstract （571）   HTML （512）    PDF （825KB）（356）       With the development of hyperspectral sensor technology and remote sensing data acquisition platform, the application of hyperspectral data is becoming more and more popular in precision agriculture. Spectral features and spatial features are two main kinds of features used in hyperspectral image classification. The comparison of spectral features and spatial features in vegetation classification of hyperspectral image is a special application in hyperspectral image classification. Therefore, this study compared the performance of several typical spectral features and spatial features in vegetation classification of hyperspectral image. The considered spatial features include grey level co-occurrence matrix (GLCM) based features, Gabor features and morphological features. The considered spectral feature selection or extraction methods include minimal-redundancy-maximal-relevance (mRMR), joint mutual information (JMI), conditional mutual information maximization (CMIM), double input symmetrical relevance (DISR), Jeffreys-Matusita (JM), principal component analysis (PCA), independent component analysis (ICA) and linear discriminant analysis (LDA). PCA, an effective subspace feature extraction method, is widely used in the feature extraction of hyperspectral image. The first several principal components (PCs) are usually selected as spectral features in hyperspectral image classification. However, the first several PCs have no guarantee to achieve good class separability and classification accuracy. Considering that, a hybrid feature extraction approach named as PCA_ScatterMatrix was proposed which combined PCA and an improved scatter-matrix-based feature selection method, aiming to select PCs with high class separability and get high overall classification accuracy. The experiments and comparative analyses were conducted with a widely used hyperspectral image, which was collected over the agricultural area in northwestern Indiana, USA (United States of America) by the AVIRIS (Airborne Visible / Infrared Imaging Spectrometer). The experimental results indicated that: (1) The proposed hybrid feature extraction method PCA_ScatterMatrix got the highest overall classification accuracy on both data sets (82.7% and 86.5%) among three classic subspace feature extraction methods (PCA, ICA and LDA) and respectively improved overall classification accuracy by 1.5% and 2.5% on both data sets, comparing to original PCA; (2) Compared to spectral features, spatial feature extraction methods generally got higher overall classification accuracy, especially Gabor spatial features got the highest overall classification accuracy on both data sets (95.5% and 96.7%). The results suggest that the proposed method is effective in vegetation classification of hyperspectral image and the spatial features play a much more important role in vegetation classification of hyperspectral image, comparing with spectral features.
 Select Hyperspectral Estimation Model Construction and Accuracy Comparison of Soil Organic Matter Content | Open Access LIU Tianlin, ZHU Xicun, BAI Xueyuan, PENG Yufeng, LI Meixuan, TIAN Zhongyu, JIANG Yuanmao, YANG Guijun Smart Agriculture    2020, 2 (3): 129-138.   doi:10.12133/j.smartag.2020.2.3.201912-SA004 Online available: 29 September 2020 Abstract （639）   HTML （365）    PDF （1642KB）（350）       Soil organic matter (SOM) is an important source of crop growth, its content can reflect soil fertility status. In order to realize the fast and real-time estimation of the SOM, based on hyperspectral data, a rapid estimation model of SOM content in orchards was established. A total of 100 brown soil samples were collected from the apple orchard of Qixia county, Yantai city, Shandong province. After drying and grinding, the hyper-spectrum of the soil was measured in the laboratory using ASD FieldSpec. The spectral data was preprocessed by the method of moving average, and the spectral reflectance features of orchard soil were analyzed to study the correlation between spectral reflectance and its soil organic matter content. In order to enhance the correlation between relevant spectral parameters and soil indexes, the original data were processed by using the multivariate scattering correction, the first derivative and the first derivative of MSC. After the sensitive wavelengths of soil organic matter content were selected and the spectral indexes were constructed. Multiple linear regression models (MLR), support vector machines (SVM) and random forest (RF) models were respectively established. The estimation accuracy of the orchard soil organic matter estimation model was measured by the determination coefficient (R2), root mean square error (RMSE) and relative analysis error (RPD). The sensitive wavelengths of soil organic matter content selected were 678, 709, 1931, 1939, 1996 and 2201 nm. The spectral parameters were constructed using the selected wavelengths, which were NDSI(678, 709), NDSI(678, 1931), NDSI(678, 2201), NDSI(709, 1939), and NDSI(1939, 2201). These models established include MLR, SVM and RF model. The RF model had the best precision. The calibration sample R2 was 0.8804, the RMSE was 0.1423 and RPD reached 2.25; the R2 of the verification model was 0.7466, the RMSE was 0.1266, and the RPD was 1.79. The results showed that the fitting effect of the hyperspectral inversion model based on RF regression analysis was better than that based on MLR analysis and SVM regression analysis. As a promising and effective method, RF can play a vital role in predicting soil organic matter. The results can help understanding the distribution of soil nutrients, guiding farmers to apply fertilizer reasonably and improving the efficiency of orchard production and management.
 Select Vision Servo Control Method and Tapping Experiment of Natural Rubber Tapping Robot | Open Access ZHOU Hang, ZHANG Shunlu, ZHAI Yihao, WANG Song, ZHANG Chunlong, ZHANG Junxiong, LI Wei Smart Agriculture    2020, 2 (4): 56-64.   doi:10.12133/j.smartag.2020.2.4.202010-SA001 Online available: 26 January 2021 Abstract （680）   HTML （221）    PDF （1923KB）（338）       Automated rubber tapping not only frees the workers from heavy physical labor and harsh working conditions, but also reduces the dependence on the workers' skills and greatly increases tapping efficiency. The key technologies for tapping robots are the independent acquisition of operational information and servo control of the tapping position in unstructured environments. In this study, taking rubber tree in rubber plantations as object, incorporating robot kinematics, machine vision technology and multi-sensor feedback control technology, a modular prototype of a rubber tapping robot was developed. The rubber tapping robot was mainly composed of an orbital mobile platform, a multi-joint robotic arm, a binocular stereo vision system and an end-effector. The binocular stereo vision and structured light system were used to obtain the structural parameters of the rubber trunk and secant. A six-joint tandem robotic arm was used for the planning and realization of complex rubber tapping trajectories. An multi-sensor fusion end-effector was developed to complete the identification of the starting point, the measurement of cut compensation and the tapping operation. To address the technical difficulties in rubber tapping operations, such as complex and variable environment, superimposed interaction of operational information, similar target background features and sub-millimeter operational accuracy requirements, the spatial mathematical model of the rubber tapping trajectory was established to plan the robot's movement path for fast approaching and moving away from the operation space. The results of the field tests conducted at a natural rubber plantation in Hainan province showed that the accuracy in bark consumption was about 0.28 mm and the accuracy in cutting depth was about 0.49 mm when the rubber tapping robot cut 1 mm thick bark. Compared to manual operations, the continuity of the chips and the flatness of the rubber output surface were improved significantly. This research could provide a positive reference and development direction for exploring automated rubber tapping operations.
 Select Estimation Model of Cucumber Leaf Wetness Duration Considering the Spatial Heterogeneity of Solar Greenhouse | Open Access LIU Jian, REN Aixin, LIU Ran, JI Tao, LIU Huiying, LI Ming Smart Agriculture    2020, 2 (2): 135-144.   doi:10.12133/j.smartag.2020.2.2.202001-SA003 Abstract （532）   HTML （292）    PDF （1629KB）（338）       Leaf wetness duration (LWD) is one of the important input variables of plant disease model, which is related to the infection of many leaf pathogens and affects the pathogen infection and developmental rate. In order to accurately predict the occurrence time and location of cucumber diseases in solar greenhouse, nine sampling points were set up in two different greenhouses located in Beijing in March and September 2019, according to the chessboard method to deploy temperature, humidity and light sensors. The fixed-point visual inspection method was used to collect the data every 1 h. From the leaf wetting to the leaf drying is the leaf wetness duration of a day. The relative humidity model (RHM) and back propagation neural network model (BPNN) were used to quantitatively estimate and analyze the LWD, the input layer of BPNN was temperature, humidity, radiation and location, the hidden layer was 10, and the output layer was location and whether the leaf surface was wet. The results showed that BPNN obtained similar accuracy ACC = 0.90 and 0.92 under the experimental conditions of two greenhouses, which was higher than RHM ACC = 0.82 and 0.84 in estimating of LWD, the mean absolute errors MAE were 1.81 h and 1.61 h, root mean squared error RMSE were 2.10 and 1.87, and coefficient of determination R2 were 0.87 and 0.85. In sunny and cloudy conditions, the spatial distribution of LWD was generally in the South > the Middle > the North. In the South, the average LWD was the longest, 12.17 h/d; from the east to the west, the spatial distribution of LWD was generally in the East > the West > the Middle. In the Middle, the average LWD was the shortest of 4.83h/d. The average LWD in rainy days was longer than that in sunny days and cloudy days, the average LWD in spring and autumn rainy days were 17.15 h/d and 17.41 h/d. These changes and differences had an important impact on the distribution of leaf wetness duration in the horizontal direction of cucumber population in greenhouse, which was closely related to the occurrence rule of most high humidity cucumber diseases. In this research, the method of regional analysis of the wet duration of cucumber leaves in greenhouse was proposed, which could provide a reference for simulating the spatial distribution of LWD in greenhouse, and also had a certain reference significance for the establishment of cucumber disease early warning system.
 Select | Open Access Yan Zhu, Guijun Yang Smart Agriculture    2020, 2 (1): 0-0.   Abstract （690）      PDF （58084KB）（336）
 Select Stereoscopic Light Environment Intelligent Control System Based on Characteristic Differences of Facility Cucumber Plants Light Requirements | Open Access ZHANG Zhongxiong, LI Bin, FENG Pan, ZHANG Pan, LAI Haibin, HU Jin, ZHANG Haihui Smart Agriculture    2020, 2 (2): 94-104.   doi:10.12133/j.smartag.2020.2.2.202005-SA007 Abstract （495）   HTML （776）    PDF （2566KB）（330）       Light is the main energy source for plants to carry out photosynthesis, and the quality of light directly affects the yield and quality of crops. In view of the fact that most of the existing plant light supplement systems are based on the photosynthetic capacity of functional leaves, problems such as photoinhibition of new leaves in the canopy and lack of supplementary light in the functional leaf position between plants, and the position of light supplement can’t be adjusted dynamically to adapt to crop growth exist, taking facility cucumber as the research object, an stereo light environment intelligent control system based on the characteristic differences of plant light requirements was designed in this research. The system is composed of intelligent control subsystem, canopy-plant environment monitoring subsystem, canopy-plant LED light-compensating lamp subsystem, and light-compensating lamp lifting subsystem. Wireless communication between subsystems was realized by using ZigBee technology. The canopy-interplant environmental monitoring subsystem obtains the canopy and interplant environmental information respectively and sends them to the intelligent control subsystem. According to the real-time environmental information, the intelligent control subsystem invokes the canopy regulation model and the appropriate interplant leaf position regulation model to obtain the corresponding regulation target values, and sends them to the canopy-interplant light-compensating lamp to realize the dynamic real-time regulation of the canopy and interplant light-compensating lamp. In November 2018, the stereoscopic light-compensating equipment and the traditional canopy light-compensating equipment were tested and verified with the natural control in the vegetable base of the vegetable industry comprehensive service area of Jingyang County, Shaanxi province. The results showed that, compared with the traditional canopy light-compensating area, the cucumber plant height and stem diameter in the stereoscopic light-compensating area increased significantly, and the average plant height and stem diameter increased by 8.03% and 7.24%, respectively. Compared with the natural treatment area, the average plant height and stem diameter increased by 26.51% and 36.03%, respectively. And during the one-month picking period, compared with the traditional canopy light-compensating area, the yield of the stereoscopic light-compensating area increased by 0.28 kg/m2, the economic benefit increased by 2.82 CNY/m2, the yield of the stereoscopic light-compensating area increased by 1.39 kg/m2, and the economic benefit increased by 4.88 CNY/m2; compared with the natural treatment area indicating that the stereoscopic light environment control system can improve economic benefits and has good application and promotion values.
 Select | Open Access Smart Agriculture    2019, 1 (1): 97-97.   Abstract （703）      PDF （4250KB）（309）
 Select Design and Prospect for Anti-theft and Anti-destruction of Nodes in Solar Insecticidal Lamps Internet of Things | Open Access HUANG Kai, SHU Lei, LI Kailiang, YANG Xing, ZHU Yan, WANG Xiaochan, SU Qin Smart Agriculture    2021, 3 (1): 129-143.   doi:10.12133/j.smartag.2021.3.1.202102-SA034 Abstract （647）   HTML （43）    PDF （2413KB）（305）       Solar insecticidal lamps (SILs) are widely used in agriculture for the purpose of effectively controlling pests and reducing pesticide dosage. With the increasing deployment of SILs, there are more and more reports about theft and destruction of SILs, seriously affecting the pest control effect and leading to great economic losses. Unfortunately, many efforts remain unsuccessful, since people can destruct the components of SIL in part but not steal the whole SIL, which cannot be detected by GPRS module or can only be labeled as a fault of component. To realize the broader effect of anti-theft and anti-destruction in the scenario of Solar Insecticidal Lamps Internet of Things (SIL-IoTs), there were two types of designs which would enable substantial improvements. On one hand, SIL was reformed and designed to obtain more information from different kinds of sensors and increase the difficulty of theft and destruction of SILs. Four modules were equipped including gated switch, voltage and current module, emergency power module, acceleration sensor module. Gated switch was used to judge whether the gate of power was open or closed. Voltage and current module of battery, solar panel, lamp, and metal mesh were used to judge whether the components were stolen or destructed. Emergency power module was used for communication module after the battery being stolen. Acceleration sensor module was used to judge whether the SIL was shaking by stealer. On the other hand, the auxiliary equipment of SIL, i.e., unmanned aerial vehicle insecticidal lamp (UAV-IL), was put forward for emergency applications after theft and destruction of SIL, e.g., deployment, tracking, patrol inspection, and so on. Through the above-mentioned hardware design and application of UAV-IL, more information from different kinds of sensors could be obtained to make judgements about the situation of theft and destruction. However, considering the short occurrence time of theft and destruction, the design was not enough to realize fast and accurate judgments. Therefore, six key research issues in the design of internal hardware, software algorithm and appearance structure design level were discussed, including 1) optimal design of anti-theft and anti-destruction of SILs; 2) establishment of anti-theft and anti-destruction judgment rules of SILs; 3) fast and accurate judgments of theft and destruction of SILs; 4) emergency measures after theft and destruction of SILs; and 5) prediction and prevention of theft and destruction of SILs; 6) optimal calculation to reduce the load of network data transmission. The anti-theft and anti-destruction have crucial roles in equipment safety, which can be extended to various agricultural applications.
 Select Estimating Grain Protein Content of Winter Wheat in Producing Areas Based on Remote Sensing and Meteorological Data | Open Access WANG Lin, LIANG Jian, MENG Fanyu, MENG Yang, ZHANG Yongtao, LI Zhenhai Smart Agriculture    2021, 3 (2): 15-22.   doi:10.12133/j.smartag.2021.3.2.202103-SA007 Online available: 30 June 2021 Abstract （503）   HTML （42）    PDF （1605KB）（303）       With the rapid development of economy and people's living standards, people's demands for crops have changed from quantity to quality. The rise and rapid development of remote sensing technology provides an effective method for crop monitoring. Accurately predicting wheat quality before harvest is highly desirable to optimize management for farmers, grading harvest and categorized storage for the enterprise, future trading price, and policy planning. In this research, the main producing areas of winter wheat (Henan, Shandong, Hebei, Anhui and Jiangsu provinces) were chosed as the research areas, with collected 898 samples of winter wheat over growing seasons of 2008, 2009 and 2019. A Hierarchical Linear model (HLM) for estimating grain protein content (GPC) of winter wheat at heading-flowering stage was constructed to estimate the GPC of winter wheat in 2019 by using meteorological factors, remote sensing imagery and gluten type of winter wheat, where remote sensing data and gluten type were input variables at the first level of HLM and the meteorological data was used as the second level of HLM. To solve the problem of deviation in interannual and spatial expansion of GPC estimation model, maximum values of Enhanced Vegetation Index (EVI) from April to May calculated by moderate-resolution-imaging spectroradiometer were computed to represent the crop growth status and used in the GPC estimation model. Critical meteorological factors (temperature, precipitation, radiation) and their combinations for GPS estimation were compared and the best estimation model was used in this study. The results showed that the accuracy of GPC considering three meteorological factors performed higher accuracy (Calibrated set: R2 = 0.39, RMSE = 1.04%; Verification set: R2 = 0.43, RMSE = 0.94%) than the others GPC model with two meteorological factors or single meteorological factor. Therefore, three meteorological factors were used as input variables to build a winter wheat GPC forecast model for the regional winter wheat GPC forecast in this research. The GPC estimation model was applied to the GPC remote sensing estimation of the main winter wheat-producing areas, and the GPC prediction map of the main winter wheat producing areas in 2019 was obtained, which could obtain the distribution of winter wheat quality in the Huang-Huai-Hai region. The results of this study could provide data support for subsequent wheat planting regionalization to achieve green, high-yield, high-quality and efficient grain production.
 Select Estimation of Maize Leaf Area Index and Aboveground Biomass Based on Hyperspectral Data | Open Access SHU Meiyan, CHEN Xiangyang, WANG Xiqing, MA Yuntao Smart Agriculture    2021, 3 (1): 29-39.   doi:10.12133/j.smartag.2021.3.1.202102-SA004 Abstract （525）   HTML （37）    PDF （1944KB）（300）       In order to assess maize growth status accurately and quickly for improving maize precise management, field experiment was conducted in Gongzhuling research station, Jilin Academy of Agricultural Sciences, Jilin province. Experimental design included 3 planting densities and 5 maize materials. The near-ground hyperspectral data and the unmanned aerial vehicle (UAV) hyperspectral images were obtained when maize were during V11－V12 stage. The application abilities of the hyperspectral data obtained from the two phenotyping platforms were compared and analyzed in the estimation of maize leaf area index (LAI) and aboveground biomass. In this study, 21 commonly used spectral vegetation indices were constructed based on ground hyperspectral data, and then the estimation models of maize LAI and aboveground biomass were established based on ground hyperspectral full-bands, UAV hyperspectral full-bands and vegetation indices and partial least square regression method, respectively. According to the variance estimation of regression coefficients, the important bands of LAI and aboveground biomass were selected, and the partial least square method was also used to establish the estimation model of maize LAI and aboveground biomass based on important bands. The results showed that the canopy spectral reflectance of the same maize material increased with the increase of planting density in the near infrared bands. Among the 5 maize materials under the same planting density, the canopy spectral reflectance of wild type material was the lowest in the visible and near infrared bands. For LAI, the model constructed based on vegetation indices had the best estimation result, with R2, RMSE and rRMSE values of 0.70, 0.92 and 15.94%. For aboveground biomass, the model constructed based on the sensitive spectral bands (839－893 nm and 1336－1348 nm) had the best estimation results, with R2, RMSE and rRMSE values of 0.71, 12.31 g and 15.89%, which showed that there was information redundancy in hyperspectral bands in the estimation of aboveground biomass, and the estimation accuracy could be improved by reducing the number of spectral bands and selecting sensitive spectral bands. In summary, the UAV hyperspectral images have a good application ability in the estimation of maize LAI and aboveground biomass, and can quickly and effectively extract the parameters information of maize growth. For specific parameters, sensitive spectral bands selected can provide reliable basis for the development and practical application of multi-spectrum in the future. The study can provide a reference for the use of hyperspectral technology in the management of precision agriculture at the community scale.
 Select Rapid Recognition Model of Tomato Leaf Diseases based on Kernel Mutual Subspace Method | Open Access ZHANG Yan, LI Qingxue, WU Huarui Smart Agriculture    2020, 2 (3): 86-97.   doi:10.12133/j.smartag.2020.2.3.202009-SA001 Online available: 04 November 2020 Abstract （541）   HTML （523）    PDF （1950KB）（300）       Research on tomato disease recognition based on leaf images has been widely concerned in recent years, and with the development of machine learning and deep learning, researchers from various countries have proposed a variety of methods and models to solve this problem. In this research, a new approach by fusion color and texture features, and kernal mutual subspace method (KMSM) were introduced and a rapid recognition model of tomato leaf disease was established. The color and texture features introduced in this research including color moment (CM), color coherence vector (CCV) and histogram of oriented gradient (HOG) features. The CCHKMSM (CM+CCV+HOG+KMSM) model firstly mapped the extracted color and texture features from different classes of leaf disease data sets to high-dimensional space using gauss kernal function. Then the principal component of the mapped high-dimensional space was analysed, and the nonlinear disease characteristic space was generated. Finally, the diseases based on the minimum cosine angle of nonlinear feature space were identified. Validation experiment was conducted based on public agricultural disease data sets of PlantVillage, which providing 9 kinds of most commonly tomato leaf disease and 1 kind of healthy leaf image, and the filed took image include 3 kinds of tomato leaf diseases images. For experiment based on PlantVillage data set, the results showed that the CCHKMSM realized the most high recognize accuracy rate of 100% when the number of each class was 350. The training time cost and recognition time cost was 0.1540 s and 0.013 s, respectively. Meanwhile, experiments were conducted in the range of sample image numbers from 150 to 1000 images for each class, with step length of 50, and the obtained results showed that the average recognition rate was 99.14%. For experiment based on field took tomato diseases data sets, after segment original image into sub-size image, average recognize accuracy for the kind of diseases arrived at 96.21%, which was higher than other typical machine learning models such as SVM and KMSM, and at the same level by comparing with deep learning-based recognition methods. On the other hand, as an significant adventure of the proposed CCHKMSM model, the computing cost was low, both the training time and testing time were much lower than deep learning methods, and requirement is loss the system to run. As a conclusion, the proposed CCHKMSM model, has high potential to be applied in low-configuration equipment such as hand-held devices and edge computing terminals.
 Select Study on the Micro-Phenotype of Different Types of Maize Kernels Based on Micro-CT | Open Access ZHAO Huan, WANG Jinglu, LIAO Shengjin, ZHANG Ying, LU Xianju, GUO Xinyu, ZHAO Chunjiang Smart Agriculture    2021, 3 (1): 16-28.   doi:10.12133/j.smartag.2021.3.1.202103-SA004 Abstract （682）   HTML （63）    PDF （2085KB）（292）       Plant micro-phenotype mainly refers to the phenotypic information at the tissue, cell, and subcellular levels, which is an important part of plant phenomics research. In view of the problems of low efficiency, large error, and few traits of traditional methods for detecting kernel microscopic traits, Micro-CT scanning technology was used to carry out precise identification of micro-phenotype on 11 varieties of maize kernels. A total of 34 microscopic traits were obtained based on CT sequence images of 7 tissues, including seed, embryo, endosperm, cavity, subcutaneous cavity, endosperm cavity and embryo cavity. Among the 34 microscopic traits, 4 traits, including endosperm cavity surface area, kernel volume, endosperm volume ratio and endosperm cavity specific surface area, were significantly different among maize types (P-value<0.05). The surface area of endosperm cavity and kernel volume of common maize were significantly higher than those of other types of maize. The specific surface area of endosperm cavity of high oil maize was the largest. The endosperm cavity of sweet corn had the smallest specific surface area. The endosperm volume ration of popcorn was the largest. Furthermore, 34 traits were used for One-way ANOVA and cluster analysis, and 11 different maize varieties were divided into four categories, of which the first category was mainly common maize, the second category was mainly popcorn, the third category was sweet corn, and the fourth category was high oil maize. The results indicated that Micro-CT scanning technology could not only achieve precise identification of micro-phenotype of maize kernels, but also provide supports for kernel classification and variety detection, and so on.
 Select Construction Method and Performance Test of Prediction Model for Laying Hen Breeding Environmental Quality Evaluation | Open Access LI Hualong, LI Miao, ZHAN Kai, LIU Xianwang, YANG Xuanjiang, HU Zelin, GUO Panpan Smart Agriculture    2020, 2 (3): 37-47.   doi:10.12133/j.smartag.2020.2.3.202003-SA010 Online available: 26 October 2020 Abstract （574）   HTML （495）    PDF （2140KB）（289）       Environmental quality of facilities affects the healthy growth and production of laying hens. The breeding environment of laying hens is a complex and non-linear system in which multiple environmental factors interact and restrict each other. It is difficult to make an accurate and effective evaluation on the suitability of laying hens with a single breeding environment parameter. In order to solve the above problem, an improved cuckoo search algorithm optimization neural network (CS-BP) model for the evaluation and prediction of the environmental suitability of laying hen facility was proposed in this research. In this model, the effects of environmental factors such as temperature, humidity, light intensity and ammonia concentration were comprehensively analyzed, and the problem of high prediction accuracy caused by BP neural network easily falling into local minimum value was overcome. In the experiment, the model was compared with BP neural network, genetic algorithm optimized BP neural network (GA-BP) and particle swarm optimization BP neural network (PSO-BP). The results showed that the mean absolute error (MAE), mean relative error (MAPE) and the coefficient of determination (R2) of the prediction model based on the improved CS-BP were 0.0865, 0.0159 and 0.8569, respectively. The prediction model based on the improved CS-BP had a strong generalization ability and a high testing precision, and its index performance was better than the above three comparison models. The classification accuracy of the improved CS-BP model was tested, and the result was 0.9333. The model constructed in this research can provide more comprehensive and effective scientific evaluation for the environmental quality of laying hens facility, which is of great significance to realize the optimal control of the production environment and promote the production performance of layers.
 Select Methods and New Research Progress of Remote Sensing Monitoring of Crop Disease and Pest Stress Using Unmanned Aerial Vehicle | Open Access YANG Guofeng, HE Yong, FENG Xuping, LI Xiyao, ZHANG Jinnuo, YU Zeyu Smart Agriculture    2022, 4 (1): 1-16.   doi:10.12133/j.smartag.SA202201008 Accepted: 25 March 2022 Abstract （713）   HTML （197）    PDF （937KB）（289）       Diseases and pests are main stresses to crop production. It is necessary to accurately and quickly monitor and control the stresses dynamically, so as to ensure the food security and the quality and safety of agricultural products, protect the ecological environment, and promote the sustainable development of agriculture. In recent years, with the rapid development of the unmanned aerial vehicle (UAV) industry, UAV agricultural remote sensing has played an important role in the application of crop diseases and pests monitoring due to its high image spatial resolution, strong data acquisition timeliness and low cost. The relevant background of UAV remote sensing monitoring of crop disease and pest stress was introduced, then the current methods commonly used in remote sensing monitoring of crop disease and pest stress by UAV was summarized. The data acquisition method and data processing method of UAV remote sensing monitoring of crop disease and pest stress were mainly discussed. Then, from the six aspects of visible light imaging remote sensing, multispectral imaging remote sensing, hyperspectral imaging remote sensing, thermal infrared imaging remote sensing, LiDAR imaging remote sensing and multiple remote sensing fusion and comparison, the research progress of remote sensing monitoring of crop diseases and pests by UAV worldwide was reviewed. Finally, the unresolved key technical problems and future development directions in the research and application of UAV remote sensing monitoring of crop disease and pest stress were proposed. Such as, the performance of the UAV flight platform needs to be optimized and upgraded, as well as the development of low-cost, lightweight, modular, and more adaptable airborne sensors. Convenient and automated remote sensing monitoring tasks need to be designed and implemented, and more remote sensing monitoring information can be obtained. Data processing algorithms or software should be designed and developed with greater applicability and wider applicability, and data processing time should be shortened by using 5G-based communication networks and edge computing devices. The applicability of the algorithm or model for UAV remote sensing monitoring of crop disease and pest stress needs to be stronger, so as to build a corresponding method library. We hope that this paper can help Chinese UAV remote sensing monitoring of crop diseases and pests to achieve more standardization, informatization, precision and intelligence.
 Select Research Progress of Deep Learning in Detection and Recognition of Plant Leaf Diseases | Open Access SHAO Mingyue, ZHANG Jianhua, FENG Quan, CHAI Xiujuan, ZHANG Ning, ZHANG Wenrong Smart Agriculture    2022, 4 (1): 29-46.   doi:10.12133/j.smartag.SA202202005 Online available: 18 February 2022 Abstract （607）   HTML （171）    PDF （1061KB）（281）       Accurate detection and recognition of plant diseases is the key technology to early diagnosis and intelligent monitoring of plant diseases, and is the core of accurate control and information management of plant diseases and insect pests. Deep learning can overcome the disadvantages of traditional diagnosis methods and greatly improve the accuracy of diseases detection and recognition, and has attracted a lot of attention of researchers. This paper collected the main public plant diseases image data sets all over the world, and briefly introduced the basic information of each data set and their websites, which is convenient to download and use. And then, the application of deep learning in plant disease detection and recognition in recent years was systematically reviewed. Plant disease target detection is the premise of accurate classification and recognition of plant disease and evaluation of disease hazard level. It is also the key to accurately locate plant disease area and guide spray device of plant protection equipment to spray drug on target. Plant disease recognition refers to the processing, analysis and understanding of disease images to identify different kinds of disease objects, which is the main basis for the timely and effective prevention and control of plant diseases. The research progress in early disease detection and recognition algorithm was expounded based on depth of learning research, as well as the advantages and existing problems of various algorithms were described. It can be seen from this review that the detection and recognition algorithm based on deep learning is superior to the traditional detection and recognition algorithm in all aspects. Based on the investigation of research results, it was pointed out that the illumination, sheltering, complex background, different disorders with similar symptoms, different changes of disease symptoms in different periods, and overlapping coexistence of multiple diseases were the main challenges for the detection and recognition of plant diseases. At the same time, the establishment of a large-scale and more complex data set that meets the specific research needs is also a difficulty that need to face together. And at further, we point out that the combination of the better performance of the neural network, large-scale data set and agriculture theoretical basis is a major trend of the development of the future. It is also pointed out that multimodal data can be used to identify early plant diseases, which is also one of the future development direction.
 Select Multi-Band Image Fusion Method for Visually Identifying Tomato Plant’s Organs With Similar Color | Open Access FENG Qingchun​, CHEN Jian, CHENG Wei​, WANG Xiu Smart Agriculture    2020, 2 (2): 126-134.   doi:10.12133/j.smartag.2020.2.2.202002-SA001 Abstract （509）   HTML （678）    PDF （1659KB）（279）       Considering at the robotic management for tomato plants in the greenhouse, it is necessary to identify the stem, leaf and fruit with the similar color from the broad-band visible image. In order to highlight the difference between the target and background, and improve the identification efficiency, the multiple narrow-band image fusion method for identifying the tomato’s three similar-colored organs, including stem, leaf, and green fruit, was proposed, based on the spectral features of these organs. According to the 300-1000 nm spectral data of three organs, the regularized logistic regression model with Lasso for distinguishing their spectral characteristic was built. Based on the sparse solution of the model’s weight coefficients, the wavelengths 450, 600 and 900 nm with the maximum coefficients were determined as the optimal imaging band. The multi-spectral image capturing system was designed, which could output three images of optimal bands from the same view-field. The relationship between the organs’ image gray and their spectral feature was analyzed, and the optimal images could accurately show the organs’ reflection character at the various band. In order to obtain more significant distinctions, the weighted-fusion method based NSGA-II was proposed, which was supposed to combine the organ’s difference in the optimal band image. The algorithm’s objective function was defined to maximize the target-background difference and minimize the background-background difference. The coefficients obtained were adopted as the linear fusion factors for the optimal band images.Finally, the fusion method was evaluated based on intuitional and quantitative indexes, respectively considering the one among stem, leaf and green fruit as target, and the other two as the backgrounds. As the result showed, compared with the single optimal band image, the fused image greatly intensified the difference between the similar-colored target and background, and restrained the difference among the background. Specifically, the sum of absolute difference (SAD) was used to describe the grey value difference between the various organs, and the fusion result images’ SAD between the target and the background raised to 2.02, 8.63 and 7.89 times than the single band images. The Otsu automatic segmentation algorithm could respectively obtain the recognition accuracy of 71.14%, 60.32% and 98.32% for identifying the stem, leaf and fruit on the fusion result image. The research was supposed as a reference for the identification on similar-colored plant organs under agricultural condition.
 Select | Open Access Smart Agriculture    2019, 1 (1): 99-99.   Abstract （580）      PDF （1629KB）（276）
 Select Cotton Phenotypic Trait Extraction Using Multi-Temporal Laser Point Clouds | Open Access YANG Xu, HU Songtao, WANG Yinghua, YANG Wanneng, ZHAI Ruifang Smart Agriculture    2021, 3 (1): 51-62.   doi:10.12133/j.smartag.2021.3.1.202102-SA003 Abstract （494）   HTML （35）    PDF （2561KB）（263）       To cope with the challenges posed by the rapid growth of world population and global environmental changes, scholars should employ genetic and phenotypic analyses to breed crop varieties with improved responses to limited resource environments and soil conditions to increase crop yield and quality. Therefore, the efficient, accurate, and non-destructive measurement of crop phenotypic traits, and the dynamic quantification of phenotypic traits are urgently needed for crop phenotypic research, and breeding as well as for modern agricultural development. In this study, cotton plants were taken as research objects, and the multi-temporal point cloud data of cotton plants were collected by using three-dimensional laser scanning technology. The multi-temporal point clouds of three cotton plants at four time points were collected. First, RANSAC algorithm was implemented for main stem extraction on the original point cloud data of cotton plants, then region growing based clustering was carried out for leaf segmentation. Plant height was estimated by calculating the end points of the segmented main stem. Leaf length and width measurements were conducted on the segmented leaf parts. In addition, the volume was also estimated through the convex hull of the original point cloud of plant cotton. Then, multi-temporal point clouds of plants were registered, and organ correspondence was constructed with the Hungarian method. Finally, dynamic quantification of phenotypic traits including plant volume, plant height, leaf length, leaf width, and leaf area were calculated and analyzed. The overall performance of the approaches achieved a matching rate through a series of experiments, and the traits extracted by using of point cloud showed high correlation with the manually measured ones. The relative error between plant height and manual measurement results did not exceed 1.0%. The estimated leaf length and width on point clouds were highly correlated with the manually measured ones, and the coefficient of determination was nearly 1.0. The proposed 3D phenotyping methodology can be introduced and used to other crops for phenotyping.
 Select Research Advances and Prospects of Crop 3D Reconstruction Technology | Open Access ZHU Rongsheng, LI Shuai, SUN Yongzhe, CAO Yangyang, SUN Kai, GUO Yixin, JIANG Bofeng, WANG Xueying, LI Yang, ZHANG Zhanguo, XIN Dawei, HU Zhenbang, CHEN Qingshan Smart Agriculture    2021, 3 (3): 94-115.   doi:10.12133/j.smartag.2021.3.3.202102-SA002 Abstract （645）   HTML （85）    PDF （1950KB）（255）       Crop 3-dimensional (3D) reconstruction is one of the most fundamental techniques in crop phenomics, and is an important tool to accurately describe the holographic structure of crop morphology. 3D reconstruction models of crops are important for high-throughput crop phenotype acquisition, crop plant characteristics evaluation, and plant structure and phenotype correlation analysis. In order to promote and popularize the 3D reconstruction technology in crop phenotype research, the basic methods and application characteristics, the current advances of research and the prospects of 3D reconstruction in crops were review in this paper. Firstly, the existing methods of crop 3D reconstruction were summarized, the basic principles of each method were reviewed, the characteristics, advantages and disadvantages of each method were analyzed, the applicability of each method on the basis of the general process of crop 3D reconstruction methods were introduced, and the specific process and considerations for the implementation of each method were summarized. Secondly, the application of crop 3D reconstruction were divided into three parts: single crop reconstruction, field group reconstruction and root system, according to different target objects, and the applications of crop 3D reconstruction technology from these three perspectives were reviewed, the research advances of each method for different crop 3D reconstruction based on accuracy, speed and cost were explored, and the problems and challenges of crop 3D reconstruction in the context of different reconstruction objects were organized. Finally, the prospects of crop 3D reconstruction technology were analyzed.
 Select Vertical Heterogeneity Analysis of Biochemical Parameters in Oilseed Rape Canopy Based on Fast Chlorophyll Fluorescence Technology | Open Access ZHANG Jiafei, WAN Liang, HE Yong, CEN Haiyan Smart Agriculture    2021, 3 (1): 40-50.   doi:10.12133/j.smartag.2021.3.1.202103-SA005 Abstract （421）   HTML （13）    PDF （3024KB）（240）       Accurate acquisition of crop canopy biochemical information is of great significance for monitoring crop growth and guiding precise fertilization. Previous vertical distribution researches of crop biochemical information were mainly based on hyperspectral inversion, which was lack of the association of plant photosynthesis physiology. This study mainly investigated the vertical distribution characteristics of biochemical parameters such as chlorophyll, carotenoid, dry matter, and water content in the oilseed rape canopy under different nitrogen treatments at the mid-seedling stage. The photosynthetic performance of leaves was measured by using fast chlorophyll fluorescence technology, and linear regression and principal component analysis were further implemented to explore the internal relationship between fluorescence response and biochemical parameters. The results showed that: (1) The chlorophyll content, carotenoid content, dry matter and water content of the rape canopy at the mid-seedling stage all showed a parabolic vertical distribution, while the ratio of chlorophyll to carotenoids content gradually decreases with the leaf position and nitrogen treatments, which was the same as the vertical distribution pattern of fluorescence parameters such as driving force comprehensive performance (DFTotal) and end electron chain quantum yield (φRo) and other fluorescence parameters could be used to diagnose nitrogen stress; (2) JIP-test parameters, especially DFTotal, had a good performance to evaluate the chlorophyll/carotenoids, chlorophyll and dry matter content of oilseed rape leaves; (3) Nitrogen deficiency would weaken the PSII and PSI performance of oilseed rape leaves at the mid-seedling stage, and the maximum photochemical efficiency (φPo) could be used to diagnose nitrogen stress. There was a significant difference in the PSI performance, namely electron transfer efficiency at the end acceptors of leaves in the different leaf position, hence the comprehensive performance parameter DFTotal could be an effective characterization of the vertical heterogeneity of canopy biochemical parameters. These findings indicated the feasibility of applying the rapid chlorophyll fluorescence technology to crop biochemical information heterogeneity monitoring and provided new ideas and technical support for guiding precise fertilization and achieving high-quality and high-yield.
 Select | Open Access Smart Agriculture    2020, 2 (3): 0-1.   Abstract （925）      PDF （140KB）（234）
 Select Research Progress of Sensing Detection and Monitoring Technology for Fruit and Vegetable Quality Control | Open Access GUO Zhiming, WANG Junyi, SONG Ye, ZOU Xiaobo, CAI Jianrong Smart Agriculture    2021, 3 (4): 14-28.   doi:10.12133/j.smartag.2021.3.4.202106-SA011 Online available: 30 December 2021 Abstract （463）   HTML （72）    PDF （959KB）（231）       Vegetable and fruit planting areas and products of China have always ranked first in the world, and the vegetable and fruit industry is respectively the second and third largest agricultural planting industry after grain. Vegetables and fruits are prone to quality deterioration during postharvest storage and transportation, resulting in reduced edible value and huge economic losses. To ensure fruit and vegetable quality and reduce the waste of resources caused by postnatal deterioration, this paper summarizes the latest research status of sensor detection and monitoring technology for fruit and vegetable quality deterioration and analyzed the principle, characteristics, advantages, and disadvantages of various detection technology. Among them, machine vision can detect the external quality and surface defects of fruits and vegetables, but fruits and vegetables are different from the standard machined products, and they are affected by many factors in the growth process, which seriously interfere with the image collection work and easily lead to misjudgment. An electronic nose equipped with expensive gas sensors can monitor the odor deterioration of fruits and vegetables but would require improved sensitivity and durability. Near-infrared can detect the internal quality and recessive defects of fruits and vegetables, but the applicability of the model needs to be improved. Hyperspectral imaging can visually detect the internal and external quality of fruits and vegetables and track the deterioration process, but the huge amount of data obtained leads to data redundancy, which puts forward higher requirements for system hardware. Therefore, low-cost multispectral imaging systems should be developed and characteristic wavelength extraction algorithms should be optimized. Raman spectroscopy can detect fruit and vegetable spoilage bacteria and their metabolites, but there is no effective Raman enhanced substrate production and accurate Raman standard spectrogram database. The comprehensive evaluation of fruit and vegetable deterioration can be realized by multi-technology and multi-information fusion. It can overcome the limitation of single sensor information analysis, improve the robustness and parallel processing ability of the detection model, and provide a new approach for high-precision detection or monitoring of fruit and vegetable quality deterioration. The Internet of Things monitoring system is constructed with various sensors as the sensing nodes to realize the intelligent real-time monitoring of fruit and vegetable quality deterioration information, provide a reference for solving the technical limitation of quality deterioration control in the processing of fruit and vegetable. This is of great significance for reducing the postpartum economic loss of fruits and vegetables and promoting the sustainable development of the fruit and vegetable industry.
 Select Improved AODV Routing Protocol for Multi-Robot Communication in Orchard | Open Access MAO Wenju, LIU Heng, WANG Dongfei, YANG Fuzeng, LIU Zhijie Smart Agriculture    2021, 3 (1): 96-108.   doi:10.12133/j.smartag.2021.3.1.202101-SA001 Abstract （429）   HTML （25）    PDF （2632KB）（221）       To satisfy the communication needs of multiple robots working in orchards, an improved Ad Hoc on-demand distance vector routing protocol based on signal strength threshold and priority nodes (AODV-SP), and the prediction model of Wi-Fi signal reception in peach orchards, was proposed in this study. Different from the traditional AODV protocol, AODV-SP utilizes the idea of priority nodes and strength thresholds to construct a discovery routing algorithm and a selection routing algorithm by seeking priority nodes and calculating the maximum strength threshold between nodes, respectively. The discovery routing message and selection routing message of the AODV-SP protocol were designed according to the discovery routing and selection routing algorithms. To verify the performance of the AODV-SP protocol, the performance of the protocol with different maximum movement speeds of nodes was analyzed by using NS2 simulation software and the performance was compared with the traditional AODV protocol. The simulation results showed that the average end-to-end delay, route initiation frequency, and route overhead of AODV-SP protocol with the introduction of priority node and path signal strength thresholds were smaller than those of the traditional AODV protocol, and the packet delivery rate improved significantly compared with that of AODV protocol. Among them, when the maximum node movement speed was 5 m/s, the route initiation frequency and route overhead of AODV-SP protocol reduced by 3.65% and 7.09%, respectively, compared with AODV protocol. When the maximum node movement speed was 8 m/s, the packet delivery rate of AODV-SP protocol improved by 0.59% and the average end-to-end delay reduced by 13.09%. To further verify the simulation results of AODV-SP making AODV-SP protocol applicable to a multi-robot wireless communication system and ensure the normal operation of multi-robot wireless communication in orchards, a physical platform for multi-robot wireless communication was built in a laboratory environment, and software was designed to enable the physical platform to communicate properly under the AODV-SP protocol. And the physical platform for multi-robot wireless communication using the AODV-SP protocol was tested under static and dynamic conditions, respectively. The experiment results showed that, under static condition, when distance between nodes was less than or equal to 25 m, the packet loss rate of the robot was 0; when distance between nodes was 100 m, tthe packet loss rate of the robot was 21.01%, and the following robots could maintain the chain topology with the leader robot in dynamic conditions. Simulation and physical platform experiments results showed that the AODV-SP protocol could be used for the construction of multi-robot communication systems in orchard.
 Select Underwater Fish Species Identification Model and Real-Time Identification System | Open Access LI Shaobo, YANG Ling, YU Huihui, CHEN Yingyi Smart Agriculture    2022, 4 (1): 130-139.   doi:10.12133/j.smartag.SA202202006 Accepted: 21 February 2022 Online available: 10 March 2022 Abstract （335）   HTML （42）    PDF （1329KB）（220）       Convolutional neural network models have different advantages and disadvantages, it is becoming more and more difficult to select an appropriate convolutional neural network model in an actual fish identification project. The identification of underwater fish is a challenge task due to varies in illumination, low contrast, high noise, low resolution and sample imbalance between each type of image from the real underwater environment. In addition, deploying models to mobile devices directly will reduce the accuracy of the model sharply. In order to solve the above problems, Fish Recognition Ground-Truth dataset was used to training model in this study, which is provided by Fish4Knowledge project from University of Edinburgh. It contains 27,370 images with 23 fish species, and has been labeled manually by marine biologists. AlexNet, GoogLeNet, ResNet and DenseNet models were selected initially according to the characteristics of real-time underwater fish identification task, then a comparative experiment was designed to explore the best network model. Random image flipping, rotation and color dithering were used to enhance data based on ground-truth fish dataset in response to the limited number of underwater fish images. Considering that there was a serious imbalance in the number of samples in each category, the label smoothing technology was used to alleviate model overfitting. The Ranger optimizer and Cosine learning rate attenuation strategy were used to further improve the training effect of the models. The accuracy and recall rate information of each model were recorded and counted. The results showed that, the accuracy and recall rate of the fish recognition model based on DenseNet reached 99.21% and 96.77% in train set and validation set respectively, its F1 value reached 0.9742, which was the best model obtained in the experiment. Finally, a remote fish identification system was designed based on Python language, in this system the model was deployed to linux server and the Android APP was responsible for uploading fish images via http to request server to identify the fishes and displaying the identification information returned by server, such as fish species, profiles, habits, distribution, etc. A set of recognition tests were performed on real Android phone and the results showed that in the same local area net the APP could show fish information rapidly and exactly within 1 s.
 Select Agricultural Named Entity Recognition Based on Semantic Aggregation and Model Distillation | Open Access LI Liangde, WANG Xiujuan, KANG Mengzhen, HUA Jing, FAN Menghan Smart Agriculture    2021, 3 (1): 118-128.   doi:10.12133/j.smartag.2021.3.1.202012-SA001 Abstract （634）   HTML （27）    PDF （1473KB）（217）       With the development of smart agriculture, automatic question and answer (Q&A) of agricultural knowledge is needed to improve the efficiency of agricultural information acquisition. Agriculture named entity recognition plays a key role in automatic Q&A system, which helps obtaining information, understanding agriculture questions and providing answer from the knowledge graph. Due to the scarcity of labeled ANE data, some existing open agricultural entity recognition models rely on manual features, can reduce the accuracy of entity recognition. In this work, an approach of model distillation was proposed to recognize agricultural named entity data. Firstly, massive agriculture data were leveraged from Internet, an agriculture knowledge graph (AgriKG) was constructed. To overcome the scarcity of labeled named agricultural entity data, weakly named entity recognition label on agricultural texts crawled from the Internet was built with the help of AgriKG. The approach was derived from distant supervision, which was used to solve the scarcity of labeled relation extraction data. Considering the lack of labeled data, pretraining language model was introduced, which is fine tuned with existing labeled data. Secondly, large scale pretraining language model, BERT was used for agriculture named entity recognition and provided a pretty well initial parameters containing a lot of basic language knowledge. Considering that the task of agriculture named entity recognition relied heavily on low-end semantic features but slightly on high-end semantic features, an Attention-based Layer Aggregation mechanism for BERT(BERT-ALA) was designed in this research. The aim of BERT-ALA was to adaptively aggregate the output of multiple hidden layers of BERT. Based on BERT-ALA model, Bidirectional LSTM (BiLSTM) and conditional random field (CRF) were coupled to further improve the recognition precision, giving a BERT-ALA+BiLSTM+CRF model. Bi-LSTM improved BERT's insufficient learning ability of the relative position feature, while conditional random field models the dependencies of entity recognition label. Thirdly, since BERT-ALA+BiLSTM+CRF model was difficult to serve online because of the extremely high time and space complexity, BiLSTM+CRF model was used as student model to distill BERT-ALA+BiLSTM+CRF model. It fitted the BERT-ALA+BiLSTM+CRF model's output of BiLSTM layer and CRF layer. The experiment on the database constructed in the research, as well as two open datasets showed that (1) the macro-F1 of the BERT-ALA + BiLSTM + CRF model was improved by 1% compared to the baseline model BERT + BiLSTM + CRF, and (2) compared with the model trained on the original data, the macro-F1 of the distilled student model BiLSTM + CRF was increased by an average of 3.3%, the prediction time was reduced by 33%, and the storage space was reduced by 98%. The experimental results verify the effectiveness of the BERT-ALA and knowledge distillation in agricultural entity recognition.
 Select | Open Access Smart Agriculture    2019, 1 (1): 96-96.   Abstract （774）      PDF （6518KB）（211）
 Select High-Throughput Dynamic Monitoring Method of Field Maize Seedling | Open Access ZHANG Xiaoqing, SHAO Song, GUO Xinyu, FAN Jiangchuan Smart Agriculture    2021, 3 (2): 88-99.   doi:10.12133/j.smartag.2021.3.2.202103-SA003 Online available: 07 July 2021 Abstract （409）   HTML （30）    PDF （3369KB）（210）       At present, the dynamic detection and monitoring of maize seedling mainly rely on manual observation, which is time-consuming and laborious, and only small quadrats can be selected to estimate the overall emergence situation. In this research, two kinds of data sources, the high-time-series RGB images obtained by the plant high-throughput phenotypic platform (HTPP) and the RGB images obtained by the unmanned aerial vehicle (UAV) platform, were used to construct the image data set of maize seedling process under different light conditions. Considering the complex background and uneven illumination in the field environment, a residual unit based on the Faster R-CNN was built and ResNet50 was used as a new feature extraction network to optimize Faster R-CNN to realize the detection and counting of maize seedlings in complex field environment. Then, based on the high time series image data obtained by the HTPP, the dynamic continuous monitoring of maize seedlings of different varieties and densities was carried out, and the seedling duration and uniformity of each maize variety were evaluated and analyzed. The experimental results showed that the recognition accuracy of the proposed method was 95.67% in sunny days and 91.36% in cloudy days when it was applied to the phenotypic platform in the field. When applied to the UAV platform to monitor the emergence of maize, the recognition accuracy of sunny and cloudy days was 91.43% and 89.77% respectively. The detection accuracy of the phenotyping platform image was higher, which could meet the needs of automatic detection of maize emergence in actual application scenarios. In order to further verify the robustness and generalization of the model, HTPP was used to obtain time series data, and the dynamic emergence of maize was analyzed. The results showed that the dynamic emergence results obtained by HTPP were consistent with the manual observation results, which shows that the model proposed in this research is robust and generalizable.
 Select Tassel Segmentation of Maize Point Cloud Based on Super Voxels Clustering and Local Features | Open Access ZHU Chao, WU Fan, LIU Changbin, ZHAO Jianxiang, LIN Lili, TIAN Xueying, MIAO Teng Smart Agriculture    2021, 3 (1): 75-85.   doi:10.12133/j.smartag.2021.3.1.202102-SA001 Abstract （570）   HTML （30）    PDF （1993KB）（205）       Accurate and high-throughput maize plant phenotyping is vital for crop breeding and cultivation research. Tassel-related phenotypic parameters are important agronomic traits. However, fully automatic and fine tassel organ segmentation of maize shoots from three-dimensional (3D) point clouds is still challenging. To address this issue, a tassel point cloud segmentation method based on point cloud super voxels clustering and local geometric features was proposed in this study. Firstly, the undirected graph of the maize plant point cloud was established, the edge weights were calculated by using the difference of normal vectors, and the spectral clustering method was used to cluster the point cloud to form multiple super voxel sub-regions. Then, the principal component analysis method was used to find the two end regions of the plant and based on the observation of the straight direction of the bottom stem regions, the top and bottom regions were distinguished by the point cloud linear features. Finally, the tassel points were identified based on the plane local features of the point cloud. The sub-regions of the top region of the plant were classified into leaf regions, tassel regions, and mixed regions by plane local features of the point cloud, the tassel points in the tassel sub-region, and the mixed region were the finally segmented tassel point clouds. In this study, 15 mature maize plants with 3 point cloud densities were tested. Compared with the ground truth segmented manually, the average F1 scores of the tassel segmentation were 0.763, 0.875 and 0.889 when the point cloud density was 0.8/cm, 1.3/cm, and 1.9/cm, respectively. The segmentation accuracy of this method increased with the increase of plant point cloud density. The increase of point cloud density and the number of point clouds mainly affected the calculation results of point cloud plane features in tassel segmentation. When the number of point clouds was small, the top leaf point cloud was relatively sparse. Therefore, the difference between the plane feature of the leaf point and the plane feature of the tassel point was not obvious, which led to the increase of the misclassification of the point cloud. However, the time complexity of the algorithm was O(n3), so the increase in the density and number of point clouds would lead to a significant increase in the running time. Considering the segmentation accuracy and running time, the research obtained the best effect on the mature maize plants with a point cloud density of 1.3/cm and an average number of 15,000. The segmentation F1 score reached 0.875 and the running time was 6.85 s. The results showed that this method could extract tassels from maize plant point cloud, and provided technical support for the research and application of high-throughput phenotyping and three-dimensional reconstruction of maize.
 Select EMD-RF-LSTM: Combination Prediction Model of Dissolved Oxygen Concentration in Prawn Culture | Open Access YIN Hang, LI Xiangtong, XU Longqin, LI Jingbin, LIU Shuangyin, CAO Liang, FENG Dachun, GUO Jianjun, LI Liqiao Smart Agriculture    2021, 3 (2): 115-125.   doi:10.12133/j.smartag.2021.3.2.202106-SA008 Online available: 23 August 2021 Abstract （437）   HTML （26）    PDF （1929KB）（204）       Dissolved oxygen is an important environmental factor for prawn breeding. In order to improve the prediction accuracy of dissolved oxygen concentration in prawn pond, and solve the problem of low prediction accuracy of different frequency domain modal classification after empirical modal decomposition of nonlinear time series data when there are few training samples, an combination prediction model based on empirical mode decomposition (EMD), random forest (RF) and long short term memory neural network (LSTM) was proposed in this research. Firstly, the time series data of prawn breeding dissolved oxygen concentration were decomposed at multiple scales by EMD to obtain a set of stationary intrinsic mode function (IMF). Secondly, with fewer training samples, poor predicts effects on the low-frequency were verified component by LSTM. Then, IMF1－IMF4 were divided into high-frequency components through test results and used for LSTM model. IMF5－IMF7, Rn were divided for RF model, the EMD-RF-LSTM combination model was constructed to improve the prediction accuracy. Modeled low-frequency and high-frequency components IMF using RF and LSTM, then predictions of each component were accumulated and the prediction value of dissolved oxygen of sequence data were got. Finally, the performance of the model was compared with the limit learning machine (ELM), RF, standard LSTM, EMD-ELM and EMD-RF, EMD-LSTM, etc. In the test based on real dataset, the EMD-ELM model contrasted with ELM model, reduced the mean absolute error (MAPE), root mean square error (RMSE) and mean absolute error (MAE) by 30.11%, 29.60% and 32.95%, respectively. The MAPE, RMSE, MAE for the proposed models were 0.0129,0.1156,0.0844, respectively. MAPE decreased by 84.07%, 57.57%, and 49.81% compared with EMD-ELM, EMD-RF and EMD-LSTM, respectively, the prediction accuracy was significantly improved. The results show that the proposed model EMD-RF-LSTM has good prediction performance and generalization ability, which is meets the actual demand of accurate prediction of dissolved oxygen concentration in prawn culture, and can provide reference for the prediction and early warning of prawn pond water quality.
 Select Identification of Tomato Leaf Diseases Based on Improved Lightweight Convolutional Neural Networks MobileNetV3 | Open Access ZHOU Qiaoli, MA Li, CAO Liying, YU Helong Smart Agriculture    2022, 4 (1): 47-56.   doi:10.12133/j.smartag.SA202202003 Abstract （299）   HTML （2）    PDF （1623KB）（204）       Timely detection and treatment of tomato diseases can effectively improve the quality and yield of tomato. In order to realize the real-time and non-destructive detection of tomato diseases, a tomato leaf disease classification and recognition method based on improved MobileNetV3 was proposed in this study. Firstly, the lightweight convolutional neural network MobileNetV3 was used for transfer learning on the image net data set. The network was initialized according to the weight of the pre training model, so as to realize the transfer and fine adjustment of large-scale shared parameters of the model. The training method of transfer learning could effectively alleviate the problem of model over fitting caused by insufficient data, realized the accurate classification of tomato leaf diseases in a small number of samples, and saved the time cost of network training. Under the same experimental conditions, compared with the three standard deep convolution network models of VGG16, ResNet50 and Inception-V3, the results showed that the overall performance of MobileNetV3 was the best. Next, the impact of the change of loss function and the change of data amplification mode on the identification of tomato leaf diseases were observed by using MobileNetV3 convolution network. For the test of loss value, focal loss and cross entropy function were used for comparison, and for the test of data enhancement, conventional data amplification and mixup hybrid enhancement were used for comparison. After testing, using Mixup enhancement method under focal loss function could improve the recognition accuracy of the model, and the average test recognition accuracy of 10 types of tomato diseases under Mixup hybrid enhancement and focal loss function was 94.68%. On the basis of transfer learning, continue to improve the performance of MobileNetV3 model, the dilated convolution convolution with expansion rate of 2 and 4 was introduced into convolution layer, 1×1 full connection layer after deep convolution of 5×5 was connected to form a perceptron structure in convolution layer, and GLU gating mechanism activation function was used to train the best tomato disease recognition model. The average test recognition accuracy was as high as 98.25%, the data scale of the model was 43.57 MB, and the average detection time of a single tomato disease image was only 0.27s, after ten fold cross validation, the recognition accuracy of the model was 98.25%, and the test results were stable and reliable. The experiment showed that this study could significantly improve the detection efficiency of tomato diseases and reduce the time cost of disease image detection.
 Select Detection and Grading Method of Pomelo Shape Based on Contour Coordinate Transformation and Fitting | Open Access LI Yan, SHEN Jie, XIE Hang, GAO Guangyin, LIU Jianxiong, LIU Jie Smart Agriculture    2021, 3 (1): 86-95.   doi:10.12133/j.smartag.2021.3.1.202102-SA007 Abstract （613）   HTML （9）    PDF （1652KB）（203）       Automatic grading method of pomelo fruit according to the shape and size is urgently needed in the industry since the work mainly depends on artificial judgment currently. In this research, a method, which detected the vertical and horizontal size of pomelo by using contour coordinate transformation fitting, fruit shape feature extraction and direction angle compensation algorithm, while it determined the shape defects based on fruit shape index, was proposed. The image acquisition system was self-designed and built up with a CMOS camera, a dot matrix LED light source, a plane mirror, the computer, a box and brackets. The image data containing whole surface information of Shatian pomelo samples with different sizes and shapes were collected by this system. The G-B component grayscale image was chosen for denoising and segmentation. The Laplacian edge detection algorithm was implemented to extract the edge pixels of the fruit. The polynomial fitting method was applied to converse the rectangular coordinates to polar coordinates so that the fruit shape description was simplified. The characteristic point polar angle value was used to compensate the random direction of the vertical and horizontal diameters of the sample. Then the vertical and horizontal diameters of fruit were calculated after classifying the sample shapes into the spherical and the pear-like categories. For the involved 168 pomelo samples, the average error, maximum absolute error and average relative error of the vertical diameters were 2.23 mm, 7.39 mm and 1.6% respectively, while these parameters of the horizontal diameters were 2.21 mm, 7.66 mm and 1.4% respectively. The fruit shape discriminant model was established by using BP neural network algorithm based on the seven features extracted from the fitting function and verified by independent validation set including 3 peak heights, 3 peak widths and 1 trough value difference. The total recognition rate of shape identification was 83.7%. The results illustrated that the method had the potential to measuring the pomelo size and shape for grading fast and non-destructively.
 Select From Stand to Organ Level—A Trial of Connecting DSSAT and GreenLab Crop Model through Data | Open Access WANG Xiujuan, KANG Mengzhen, HUA Jing, DE REFFYE Philippe Smart Agriculture    2021, 3 (2): 77-87.   doi:10.12133/j.smartag.2021.3.2.202103-SA006 Abstract （381）   HTML （15）    PDF （2152KB）（199）       Crop models involve complex plant processes, which can be built in different scales of space and time, from molecule, cell, organ, tissue, individual to stand in space and from second to year in time. Based on different research requirements, switching the model scales can make the applicability of the model more extensive and flexible. How to switch the crop model from stand level to organ level is the content of this research. The DSSAT software (stand level) and functional-structural plant model 'GreenLab' (organ level) were chosen to explore the possibility to switch the crop model from stand to organ level. The DSSAT can simulate the growth and development processes of crops in detail according to the growth period by taking the data of weather, soil, crop management, and observational data as input. The GreenLab can simulate the growth and development and their interaction of crops by considering plant structure, and the model parameters can be estimated according to the measurements. In this study, the experimental data contains two parts: the measurements of four maize cultivars with two treatments (irrigated and rainfed) in DSSAT, and the simulations including the weights of leaves, internodes and fruits per day using DSSAT based on the measurements. The simulation results of DSSAT were used to calibrate the parameters of the environmental (E), sink strength (Po), and remobilization (kb and ki) in GreenLab, and to compute the weights of leaves, internodes and fruits for each phytomer. The simulation results of the GreenLab model were compared and analyzed with the experimental data and the simulations of DSSAT. The consistency of calculation results could be an indicator to explore the method of building an interface between different-scale crop models, and to compare the characteristics of different models. The results showed that the GreenLab model could reproduce the simulation data of the DSSAT and the measurement data, including the leaf area index (LAI) and the total weight of the plants, and further could compute the biomass for each organ (leaf, internode and fruit), and the biomass distribution among organs, the biomass production (Q), the demand (D) and the ratio between Q and D during the growth. Therefore, the detailed information of organ growth and development could be reproduced and the 3D structures of plant could be given. Finally, the advantages and application fields of different-scale model integration were discussed.
 Select Multi-Factor Coordination Control Technology of Promoting Early Maturing in Southern Blueberry Intelligent Greenhouse | Open Access XU Lihong, LIU Huihui, XU He, WEI Ruihua, CAI Wentao Smart Agriculture    2021, 3 (4): 86-98.   doi:10.12133/j.smartag.2021.3.4.202109-SA007 Online available: 30 December 2021 Abstract （276）   HTML （29）    PDF （1965KB）（193）       In order to get blueberries goes on sale in advance and obtain greater economic benefits, southern blueberries were moved to an intelligent greenhouse with controllable environment for experimental production. The early maturing production control technology of southern blueberry intelligent greenhouse was explored and studied. First, a detailed and comprehensive investigation and summary were conducted on the production factors of blueberry soilless cultivation, such as the production characteristics of various blueberry varieties, the pH and composition of the substrate, the key points of water and fertilizer irrigation, and the scope of the microenvironment climate. Then, the existing Venlo-type greenhouse was deployed for blueberry production, and the geography, climate and internal structural conditions of the greenhouse were briefly described, and the greenhouse blueberry full-cycle control goal was planned. Finally, the production control system was designed and implemented based on the Internet of Things technology, and the overall framework of the software layer, the hardware layer and the cloud were introduced. Based on multi-factor coordinated control model of greenhouse environment, according to the characteristics of blueberry growth environment, a set of blueberry greenhouse multi-factor coordinated control algorithms were proposed and used for environmental regulation. The experimental greenhouse is located in the southeast of Huaqiao Town, Kunshan city, Suzhou city, Jiangsu province. It has been verified that the overall control system has a significant effect, and the first wave of fruits was harvested in early May 2021, making the southern variety of blueberry enter the fruit picking period nearly one month earlier. Compared with the blueberry plants without cold storage, the yields per plant of "Star" "Emerald" "Lanmei No. 1", and "Coast" after cold storage increased by 51.5%, 85.5%, 43.8%, and 94.7%, respectively, and the weight of each fruit was increased 10.9%, 7.2%, 2.6%, and 5.3%, respectively. Experiments proved that the use of multi-factor coordinated control algorithms for regulation can increase the yield and quality of blueberries and achieve significant economic benefits and provide a demonstration for the industrialization of blueberry plants in southern greenhouses to promote early maturity production and management.
 Select Development and Performance Test of Variable Spray Control System Based on Target Leaf Area Density Parameter | Open Access FAN Daoquan, ZHANG Meina, PAN Jian, LYU Xiaolan Smart Agriculture    2021, 3 (3): 60-69.   doi:10.12133/j.smartag.2021.3.3.202107-SA007 Online available: 04 November 2021 Abstract （303）   HTML （22）    PDF （1798KB）（191）       Variable spray technology is an important means to improve pesticide utilization rate and save pesticide. Fruit tree is a kind of three-dimensional space, and the densities of branches and leaves in the canopy of fruit trees at different locations are different at the same time. The ideal state of spray is to adjust the amount of spray according to local characteristics, so as to realize the application of the spray on the canopy of fruit trees as required and improve the utilization rate of pesticide. In order to achieve the effect of reducing the dosage and increasing the efficiency of pesticide application, a variable spray control system was developed and the methods for computing leaf area density parameter and pulse width modulation(PWM)'s duty ratio of actuators were proposed. As the dosage parameter, the leaf area density was derived based on the point cloud density detected by LiDAR sensor on the upper computer. Then PWM's duty ratio was calculated based on the leaf area density and sent to the slave computer-PLC in real time. The communication between upper and slave computer was carried out through RS485 standard. So the spray flow of each nozzle was controlled by the switching frequency of the solenoid valve with PWM's duty ratio signal. Key parameters were obtained by the test including the net size of spray unit, delay time of the system and the function relationship between the PWM's duty ratio and the spray flow of nozzle. The test results showed that there was a linear relationship between the PWM's duty ratio and the spray flow of nozzle under the pressure of 0.2, 0.3 and 0.4 MPa, and the linear goodness of fit were all above 0.98. Finally, the effectiveness of the variable spray system was verified by the spray test. The test results showed that the minimum number of droplets per unit area (cm2) on the water-sensitive paper was 35 drops at the sampling point, which was higher than the 25 drops defined by the common method for the spray amplitude of aerosol in the air supply spray. Under 39.9% of the canopy ratio between the target canopy area and the whole area, the variable spraying mode saved 71.96% of the pesticide dosage compared with the continuous spraying mode, and 29.72% compared with the target spraying mode, achieving the dose reduction effect.
 Select Research Progress of Key Technologies and Verification Methods of Numerical Modeling for Plant Protection Unmanned Aerial Vehicle Application | Open Access TANG Qing, ZHANG Ruirui, CHEN Liping, LI Longlong, XU Gang Smart Agriculture    2021, 3 (3): 1-21.   doi:10.12133/j.smartag.2021.3.3.202107-SA004 Abstract （330）   HTML （42）    PDF （2594KB）（191）       With the increasing application of plant protection unmanned aerial vehicle (UAV) in precision agriculture, the numerical simulation methods for the development of the downwash flow field of the plant protection UAV and the deposition and drift process of droplets affected by the downwash flow field have achieved rapid and diversified development, but the advantages, disadvantages, scope of application, and verification of each method still lack a systematic review. This article discusses the inviscid model, computational fluid dynamics model and lattice Boltzmann model (LBM) respectively. The advantage of the inviscid wake vortex model based on the vortex element method is that the calculation process is simple. Moreover, integrated with the most widely used aerial spray drift prediction software AGricultural DISPersal (AGDISP), it can be a promising way to do real-time UAV spray drift prediction. But due to lack of viscosity and turbulence models, the droplet deposition and drift simulation accuracy of inviscid model is relatively lower than other models. The computational fluid dynamics (CFD) model includes the finite volume method (FVM) and the finite difference method (FDM). The FVM in the computational fluid dynamics model has high robustness and can be applied to the simulation of various complex environments. Many commercial CFD software are based on FVM and achieved a fast development in aerial spray modeling recently. However, the FVM is greatly affected by the quality of the mesh, and its commonly used upwind style has limited accuracy (second-order accuracy). Under the same mesh density, it is easier to generate artificial dissipation when simulating the rotor tip vortex than the finite difference method. As a result, the simulated rotor tip vortex dissipation speed is much faster than the actual situation. Compared with the FVM, the structured grid used in the FDM is easier to construct a high-order precision numerical format. Which can reach 4-5 orders of accuracy, and with adaptive grid technology, FDM can simulate the evolution of rotor tip vortex with high temporal and spatial accuracy, and can reproduce the typical flow structure development process of the real rotor downwash flow field. However, it also has problems such as high grid structure requirements and excessive computing power requirements. LBM has advantages in computing three-dimensional flow field problems with complex boundary conditions and non-stationary moving objects. However, there are still shortcomings in its functional diversity and completeness. The accuracy of the numerical models mentioned above still needs field test and indoor experiment such as high-speed Particle Image Velocimetry (PIV)/ Phase Doppler Interferometry (PDI) method to verify and optimize. The authors finally pointed out the future direction of plant protection UAV application simulation and verification.
 Select Dynamic Simulation of Jujube Tree Growth and Water Use Evaluation Based on the Calibrated WOFOST Model | Open Access BAI Tiecheng, WANG Tao, ZHANG Nannan Smart Agriculture    2021, 3 (2): 55-67.   doi:10.12133/j.smartag.2021.3.2.202103-SA008 Online available: 07 July 2021 Abstract （593）   HTML （17）    PDF （1931KB）（190）       Irrigation schemes determined based on statistical analysis of field trials are usually only applicable to specific soils and meteorological environments. It is difficult to quantitatively analyze the impact of irrigation strategies on the growth of jujube trees. In order to realize the quantitative analysis of the influence of temperature, light and water resources on the growth of fruit trees, WOrld FOod Studies (WOFOST) model parameters were calibrated to simulate the jujube tree growth and water migration process. Firstly, the observed data obtained from field trials in 2016 and 2017 were used to calibrate the phenology development, initialization, green leaf, CO2 assimilation, dry matter partitioning, respiration, and water use parameters of the WOFOST model. Secondly, the time series of total above-ground biomass, leaf area index (LAI) and soil moisture content in field trials were dynamically simulated, and accuracy verification and analysis were also performed. Finally, the maximum LAI, yield, actual evapotranspiration $(ETa)$ and water use efficiency (WUE) data of 55 orchards were employed to evaluate the performance of the calibrated model at the county scale. The results showed that the coefficient of determination R2 of TAGP simulated in the field test area was between 0.92 and 0.98, and the normalized root mean square error (NRMSE) was between 8.7% and 20.5%, the R2 of simulated LAI ranged from 0.79 to 0.97, and the NRMSE ranged from 8.3% to 21.1%. The R2 of the simulated soil moisture content was between 0.29 and 0.75, and the NRMSE ranged from 4.1% and 6.1%. The model could well simulate the time series of jujube tree growth dynamics and soil moisture content changes. At the county scale, the R2 between the simulated and measured maximum LAI were 0.64 and 0.78, and the NRMSE were 13.3% and 10.7% in 2016 and 2017, respectively. The simulated yield showed R2 value of 0.48 and 0.60, and NRMSE of 12.1% and 11.9%, respectively. RMSE of the simulated versus measured $ETa$ were 36.1 mm (7.9%) and 30.8 mm (7.4%), respectively. The model also showed high WUE simulation accuracy (10%
 Select Investigation on Advances of Unmanned Aerial Vehicle Application Research in Agriculture and Forestry | Open Access CHEN Meixiang, ZHANG Ruirui, CHEN Liping, TANG Qing, XIA Lang Smart Agriculture    2021, 3 (3): 22-37.   doi:10.12133/j.smartag.2021.3.3.202107-SA006 Online available: 29 October 2021 Abstract （402）   HTML （53）    PDF （2611KB）（188）       Unmanned Aerial Vehicle(UAV) application in agriculture and forestry has the unique advantages of high efficiency, water and pesticide saving, and strong adaptability to complex terrain. The application research of UAV in agriculture and forestry has shown a fast growing trend. In order to explore the research hotspots and the scientific impact of countries/regions and institutions on UAV application in agriculture and forestry, the relevant literatures in the Web of Science(WoS) core collection database (2011-2020) were collected. The bibliometrics analysis was performed on the journal articles of UAV application in agriculture and forestry based on VOSviewer, WoS analysis tools and Microsoft Excel. The analysis results showed that the number of published papers increased rapidly since 2017, the researches on UAV application in agriculture and forestry were carried out in 94 countries/regions, including1778 institutions. Due to the strong scientific research group in the application of UAV in agriculture and forestry of the United States, China and Australia, a large number of papers had been published, resulting in a great academic influence. Remote sensing was the most widely used technology field of UAV application in agriculture and forestry, mainly involving remote sensing technology, ecological environment science, image processing technology, geological science, etc. Engineering was an important technical field of UAV application in agriculture and forestry, mainly involving control technology, sensor technology and fluid computing modeling technology related to UAV aerial pesticide application.There were 1508 articles and reviews been published in 398 journals, about 1.90% of all journals included in WoS core collection database, indicating that more and more journals paid attention to the application research of UAV in agriculture and forestry. Remote Sensing sponsored by MDPI (Multidisciplinary Digital Publishing Institute) was the journal that published the most of papers, the most cited paper mainly focused on the research status of UAV system in photogrammetry and remote sensing, including sensing, navigation, positioning and general data processing, etc. In addition, the analysis of the research hotspots of UAV application in agriculture and forestry showed that UAV pesticide application, UAV remote sensing of diseases and pests, plant phenotype acquisition were the research hotspots. This study can provide references for innovation research and cooperation between research teams of UAV application in agriculture and forestry.
 Select Optimum Sowing Date of Winter Wheat in Next 40 Years Based on DSSAT-CERES-Wheat Model | Open Access HU Yanan, LIANG Ju, LIANG Shefang, LI Shijuan, ZHU Yeping, E Yue Smart Agriculture    2021, 3 (2): 68-76.   doi:10.12133/j.smartag.2021.3.2.202104-SA005 Abstract （410）   HTML （20）    PDF （1378KB）（187）       Climate change requires crop adaptation. Plantint at the suitable date is a key management technology to promote crop yield and address the impact of climate change. Wheat is one of the most important staple crops in China. Huang-Huai-Hai and Jiang-Huai regions are high-quality and high-quantity planting areas for wheat. To deal with the adverse effects of climate change and promote the winter wheat yield in Huang-Huai-Hai and Jiang-Huai regions, the optimum sowing date was identified by creating a wheat simulation with DSSAT CERES-Wheat model. The simulation experiment was designed with 51 management inputs of sowing date and 4 climate scenarios (RCPs) under baseline period (1985－2004) and 40 years in future for three representative stations in the study region. The optimum sowing data of winter wheat was corresponding to the simulation set with highest yield in each site. The characters of changes in climate factors during the growth period and the optimum sowing date among the different period were detected, and the yield increase planted at the optimum sowing date was quantified. The results showed that, in the future, the climate during winter wheat growth period showed a trend of warming and drying would shorten the growth period. The optimum sowing date would be postponed with the rise of temperature, and the decrease of latitude in all periods and under various climate scenarios. Relative to the baseline period, the maximum delay days of the optimal sowing date increased from north to south during 2030s, which were 5 days, 8 days and 13 days at the three representative stations, respectively. The optimum sowing times in 2050s were delayed in different degrees compared with that in 2030s. The largest postponed days at each station was at the RCP8.5 scenario in 2050s. Adopting the management of optimum planting date could mitigate climatic negative effects and was in varying degrees of yield increasing effect at three sites. The smallest increase occurred in Huang-Huai-Hai north region, while Huang-Huai-Hai south region and Jiang-Huai region had the relatively higher yield increasement about 2%－4%. Therefore, the present study demonstrated an effective management of optimum sowing date to promote winter wheat yield under climate change in Huang-Huai-Hai and Jiang-Huai regions.
 Select Irrigation Method and Verification of Strawberry Based on Penman-Monteith Model and Path Ranking Algorith | Open Access ZHANG Yu, ZHAO Chunjiang, LIN Sen, GUO Wenzhong, WEN Chaowu, LONG Jiehua Smart Agriculture    2021, 3 (3): 116-128.   doi:10.12133/j.smartag.2021.3.3.202104-SA001 Accepted: 29 October 2021 Online available: 03 November 2021 Abstract （287）   HTML （34）    PDF （1359KB）（186）       Irrigation is an important factor that affects crop yield. In order to control irrigation of facility crops more effectively and accurately, this study took "Zhangji" strawberry as an example, introduced crop real-time growth characteristics into irrigation decision-making, and combined Penman-Monteith (P-M) model and knowledge reasoning to study the irrigation of strawberry. In the first step, the influencing factors and expert experience in identifying strawberry growth period of "Zhangji" strawberry irrigation were standardized, and the strawberry irrigation data structure based on Resource Description Framework (RDF) was established. The second step was to collect expert experience of strawberry irrigation according to the standardized knowledge structure model. Firstly, all data were unified into structured data, and then were stored in *.csv format together with expert experience, and strawberry irrigation knowledge map based on Neo4j was constructed. The third step was to collect the environmental data and plant data of strawberry in each growth period. The fourth step was using P-M model to calculate the initial irrigation value of strawberry, and then adjusted the initial irrigation value by knowledge reasoning.The fifth step was to conduct experimental planting and evaluate the sampled fruits. In knowledge reasoning, irrigation adjustment strategies of each expert was different. In strawberry irrigation experiment based on P-M model and path sorting algorithm, a group of irrigation reasoning values with the highest probability value were selected to adjust irrigation with the goal of maximizing strawberry yield. The experimental results showed that under the condition of harvesting at a specified time, The total fruit yield, average fruit yield per plant and average fruit weight percentage increased by 2478.5 g, 20.65 g and 12.15% (average fruit weight increased by 1.65 g per fruit) based on P-M model and path sorting algorithm compared with traditional P-M model, respectively. First, on the basis of P-M model, the yield-first irrigation adjustment strategy was adopted. Based on knowledge reasoning, the irrigation frequency and amount were adjusted timely according to the crop growth situation, which improved the yield. Second, under the condition of harvesting and recording yield at a specified time, the experiment accurately controlled the growth period to ensure early fruit ripening, while the other three groups of fruits were not fully mature and the yield of immature fruits were not calculated. Under the method of strawberry irrigation based on Penman-Monteith model and path sorting algorithm, the fruit was picked within a fixed time and reached 0.39 kg/cm2, which increased by 0.1 kg/cm2. Because the planting goal of this study was yield first, only the influence of irrigation on yield was considered. The experimental resulted show that the irrigation method based on model and knowledge reasoning could improve the yield of strawberry, and can provide a new idea for precise irrigation.
 Select Comparison of Remote Sensing Estimation Models for Leaf Area Index of Rubber Plantation in Hainan Island | Open Access DAI Shengpei, LUO Hongxia, ZHENG Qian, HU Yingying, LI Hailiang, LI Maofen, YU Xuan, CHEN Bangqian Smart Agriculture    2021, 3 (2): 45-54.   doi:10.12133/j.smartag.2021.3.2.202106-SA003 Abstract （368）   HTML （13）    PDF （2387KB）（183）       Leaf area index (LAI) is an important index to describe the growth status and canopy structure of vegetation, is of great theoretical and practical significance to quickly obtain LAI of large area vegetation and crops for ecosystem science research and agricultural & forestry production guidance. In this study, the typical tropical crop rubber tree in Hainan Island was selected as the research area, the LAI estimation model of rubber plantation based on satellite remote sensing vegetation indices was constructed, and its spatiotemporal variation was analyzed. The results showed that, compared with correlations between LAI and the indices of normalized difference vegetation index (NDVI), green NDVI (GNDVI), ratio vegetation index (RVI) and wide dynamic range vegetation index (WDRVI), correlations were higher between LAI and the indices of enhanced vegetation index (EVI), soil adjusted vegetation index (SAVI), difference vegetation index (DVI) and modified soil adjusted vegetation index (MSAVI). Among the LAI estimation models based on different vegetation indices (linear, exponential and logarithmic models), the linear estimation model based on EVI index was the best, and its coefficient of determination (R2) was 0.69. The accuracy of LAI estimation model was high. The linear fitting R2 of observed and simulated LAI was 0.67, the root mean square error (RMSE) was 0.16, and the average relative error (RE) was -0.25%. However, there was underestimation in the middle value and overestimation in the high and low value area of LAI. The high LAI values (4.40－6.23) were mainly distributed in Danzhou and Baisha in the west of Hainan Island, the middle LAI values (3.80－4.40) were mainly distributed in Chengmai, Tunchang and Qiongzhong in the middle of Hainan Island, and the low LAI values (2.69－3.80) were mainly distributed in Ding'an, Qionghai, Wanning, Ledong and Sanya in the east and south of Hainan Island. In summary, the linear estimation model for rubber plantation LAI based on EVI index obtained high accuracy, and has good values of popularization and appliance.
 Select Identification and Level Discrimination of Waterlogging Stress in Winter Wheat Using Hyperspectral Remote Sensing | Open Access YANG Feifei, LIU Shengping, ZHU Yeping, LI Shijuan Smart Agriculture    2021, 3 (2): 35-44.   doi:10.12133/j.smartag.2021.3.2.202105-SA001 Online available: 23 August 2021 Abstract （358）   HTML （25）    PDF （1233KB）（181）       The frequent occurrence of waterlogging stress in winter wheat not only seriously affects regional food security and ecological security, but also threatens social and economic stability and sustainable development. In order to identify the waterlogging stress level of winter wheat, a waterlogging stress gradient pot experiment was set up in this research. Three factors were controlled: waterlogging stress level (control, slight waterlogging, severe waterlogging), stress duration (5 days, 10 days, 15 days) and wheat variety (YF4, JM31, JM38). Leaf and canopy hyperspectral data were measured by using ASD Field Spec3 and Gaiasky-mini2 imaging spectrometer, respectively. The data were collected from the first waterlogging day of winter wheat. The sunny and windless weather was selected and measured every 7 days until the wheat was mature. Combined with vegetation index, normalized mean distance and spectral derivative difference entropy, if winter wheat was under waterlogging stress was monitored and stress level was identified. The results showed that: 1) the spectral response characteristics of winter wheat under waterlogging stress changed significantly in RW, RE, NIR and 1650－1800 nm region, which may be due to the sensitivity of these regions to physiological parameters affecting the spectral response characteristics, such as pigment, nutrient, leaf internal structure, etc; 2) the simple ratio pigment index SRPI was the optimal vegetation index for identifying the waterlogging stress of winter wheat. The excellent performance of this vegetation index may come from its extreme sensitivity to the epoxidation state and photosynthetic efficiency of the xanthophyll cycle pigment; 3) the red light absorption valley (RW: 640－680 nm) region was the optimal region for identifying waterlogging stress level. In RW region, waterlogging stress level of winter wheat could be determined by the spectral derivative difference entropy at heading, flowering and filling stages. The greater the level of waterlogging stress, the greater the spectral derivative difference entropy. This may be due to the fact that the RW region was more sensitive to pigment content, and the spectral derivative difference entropy could reduce the effects of spectral noise and background. This study could provide a new method for monitoring waterlogging stress, and would have a good application prospect in the precise prevention and control of waterlogging stress. There are still shortcomings in this study, such as the difference between the pot experiment and the actual field environment, the lack of independent experimental verification, etc. Next research could add pot and field experiments, combine with cross-validation, to further verify the feasibility of this research method.
 Select Research Progress and Application Prospect of Electronic Nose Technology in the Detection of Meat and Meat Products | Open Access LIU Yang, JIA Wenshen, MA Jie, LIANG Gang, WANG Huihua, ZHOU Wei Smart Agriculture    2021, 3 (4): 29-41.   doi:10.12133/j.smartag.2021.3.4.202011-SA003 Online available: 07 July 2021 Abstract （330）   HTML （21）    PDF （1178KB）（167）       With the continuous increase of import and export of various countries, people have put forward higher requirements on the efficiency and accuracy of meat and meat products safety indicators detection. Since electronic nose technology is simple to operate and allows rapid and nondestructive testing, it can meet today's need for efficient test of meat and meat products. In this paper, the detection principle of electronic nose technology was introduced firstly, and its development process was described from two aspects of hardware and software system. Then, the application research progress of electronic nose technology in meat and meat products detection in recent years from the aspects of freshness, adulteration, flavor evaluation and microbial contamination of meat and meat products was analyzed. Different electronic nose instruments and equipment or different pattern recognition algorithms result in different analysis results. Therefore, it highlighting the feasibility and advancement of electronic nose technology application in various aspects of meat and meat products detection. At the same time, in view of the application research results of electronic nose technology in the detection of meat and meat products, the paper pointed out the shortcomings of electronic nose technology, for example: The analysis effect of electronic nose technology was uneven, the price of electronic nose equipment was relatively expensive, and the application range of large electronic nose equipment was limited. Therefore, there were still some difficulties and problems of electronic nose technology in the aspects of universality and popularization. Finally, in view of the shortcomings of the current electronic nose technology, the development and application prospects of the electronic nose technology in the future were prospected. In terms of hardware system, with the research and development continuously of new gas sensitive materials, the durability and sensitivity to smell recognition of the electronic nose by improving the performance of the electrode film material of the electronic nose sensor array was enhanced. In terms of software system, with the upgrading continuously of computer systems, a supporting platform for the emerging and complex pattern recognition algorithms was provided. New pattern recognition algorithms in the pattern recognition system of electronic nose technology were explored and introduced, so that electronic nose technology can achieve faster and more accurate recognition and analysis of odors.
 Select Scale Adaptive Small Objects Detection Method in Complex Agricultural Environment: Taking Bees as Research Object | Open Access GUO Xiuming, ZHU Yeping, LI Shijuan, ZHANG Jie, LYU Chunyang, LIU Shengping Smart Agriculture    2022, 4 (1): 140-149.   doi:10.12133/j.smartag.SA202203003 Online available: 15 March 2022 Abstract （203）   HTML （28）    PDF （1997KB）（163）       Objects in farmlands often have characteristic of small volume and high density with variable light and complex background, and the available object detection models could not get satisfactory recognition results. Taking bees as research objects, a method that could overcome the influence from the complex backgrounds, the difficulty in small object feature extraction was proposed, and a detection algorithm was created for small objects irrelevant to image size. Firstly, the original image was split into some smaller sub-images to increase the object scale, and the marked objects were assigned to the sub-images to produce a new dataset. Then, the model was trained again using transfer learning to get a new object detection model. A certain overlap rate was set between two adjacent sub-images in order to restore the objects. The objects from each sub-image was collected and then non-maximum suppression (NMS) was performed to delete the redundant detection boxes caused by the network, an improved NMS named intersection over small NMS (IOS-NMS) was then proposed to delete the redundant boxes caused by the overlap between adjacent sub-images. Validation tests were performed when sub-image size was set was 300×300, 500×500 and 700×700, the overlap rate was set as 0.2 and 0.05 respectively, and the results showed that when using single shot multibox detector (SSD) as the object detection model, the recall rate and precision was generally higher than that of SSD with the maximum difference 3.8% and 2.6%, respectively. In order to further verify the algorithm in small target recognition with complex background, three bee images with different scales and different scenarios were obtained from internet and test experiments were conducted using the new proposed algorithm and SSD. The results showed that the proposed algorithm could improve the performance of target detection and had strong scale adaptability and generalization. Besides, the new algorithm required multiple forward reasoning for a single image, so it was not time-efficient and was not suitable for edge calculation.
 Select The Accuracy Differences of Using Unmanned Aerial Vehicle Images Monitoring Maize Plant Height at Different Growth Stages | Open Access YANG Jin, MING Bo, YANG Fei, XU Honggen, LI Lulu, GAO Shang, LIU Chaowei, WANG Keru, LI Shaokun Smart Agriculture    2021, 3 (3): 129-138.   doi:10.12133/j.smartag.2021.3.3.202105-SA008 Online available: 04 November 2021 Abstract （358）   HTML （37）    PDF （1548KB）（161）       The digital elevation model (DEM) of maize population in field was constructed by using optical imaging equipment mounted on unmanned aerial vehicle (UAV) to study the accuracy difference of maize population height monitoring at different growth stages. Three cultivars and eight sowing date treatments were set up to structure maize population with different plant heights. A multi-rotor UAV with high-definition digital camera and multispectral imaging sensor was used to take RGB images and multispectral images in the experiment area on July 25th and August 27th, 2018, which were the biggest and smallest differences in plant height. The DEM data of maize population and canopy height were obtained with image pose correction, image mosaic, point cloud generation, and space reconstruction, et al. The canopy height and plant height were normalized, and the correlation between different cultivars and sowing date was analyzed based on UAV and manual plant height measurement. The feasibility of using DEM data of maize canopy to monitor the difference of plant height was clarified. The results showed that the height difference of maize population could be reflected by the digital elevation information obtained from high-definition RGB camera and multispectral camera. The plant height monitoring accuracy of HD RGB camera was higher than that of multispectral camera. However, the monitoring accuracy of plant height was not enough under the ready-made image equipment and treatment method. So, it was difficult to reflect the smaller plant height difference of maize population. Growth stage had a great influence on the monitoring of maize plant height. When the canopy of early growth stage has not completely covered the surface or the leaf yellow and withered in the later stage of growth. The plant height of the population affected by the exposed surface was seriously underestimated. In this study, the effects of UAV imaging equipment on monitoring maize plant height were analyzed. The influence factors can be used as reference for the application of the method in field production.
 Select Detection Method of Apple Mould Core Based on Dielectric Characteristics | Open Access LI Dongbo, HUANG Lyuwen, ZHAO Xubo Smart Agriculture    2021, 3 (4): 66-76.   doi:10.12133/j.smartag.2021.3.4.202102-SA035 Online available: 07 July 2021 Abstract （328）   HTML （20）    PDF （1520KB）（157）       Apple mouldy core disease often occurs in the ventricle of apples and cannot be effectively identified by appearance. Near-infrared spectroscopy, nuclear magnetic resonance and other methods are usually used in traditional apple mouldy core disease detection, but these methods require complex equipment and high detection costs. In this research, a simple and fast nondestructive detection method of apple mouldy core disease was proposed by using a dielectric method to construct an apple mouldy core disease detection model. Japan's Hioki 3532-50 LCR tester was used to collect 108 dielectric indicators (12 dielectric indicators at 9 frequencies) of 220 apples as the original data. Due to the large differences in the distribution of data collected with different dielectric indexes and different frequencies, a standardized method was used for data preprocessing to eliminate the problem of large differences in dielectric data distribution. Afterwards, in order to eliminate the redundant information between the data, the principal component analysis algorithm was used to reduce the data dimensionality, and finally the three algorithms of BP neural network (BPNN), support vector machine (SVM) and random forest (RF) were used to construct the mouldy core disease detection model. After pre-experiment, the most effective parameters of each algorithm were selected, the test results showed that the apple mouldy core disease detection model based on the RF algorithm obtained the best performance, and the detection accuracy rate reached 96.66% and 95.71% in the training set (150 apples) and the test set (70 apples). The mouldy core disease detection model constructed by using BPNN was the second most effective, and the detection accuracy could reach 94.66% and 94.29%, respectively. The detection effect of the model built by using SVM was relatively poor, and the detection accuracies were 93.33% and 91.43%, respectively. The experimental results showed that the model constructed by using RF can more effectively identify mouldy core disease apples and healthy apples. This study could provide references for apple diseases and insect pests and non-destructive testing of apple quality.
 Select Application Scenarios and Research Progress of Remote Sensing Technology in Plant Income Insurance | Open Access CHEN Ailian, ZHAO Sijian, ZHU Yuxia, SUN Wei, ZHANG jing, ZHANG Qiao Smart Agriculture    2022, 4 (1): 57-70.   doi:10.12133/j.smartag.SA202201011 Abstract （206）   HTML （31）    PDF （820KB）（157）       Plant income insurance has become an important part of agricultural insurance in China. It has been recommended to pilot since 2016 by Chinese government in several counties, and is now (2022) required to be implemented in all major grain producing counties in the 13 major grain producing provinces. The measurement of yield for plant income insurance in such huge volume urgently needs the support of remote sensing technology. Therefore, the development history and application status of remote sensing technology in the whole agricultural insurance industry was reviewed to help understanding the whole context circumstances of plant income insurance firstly. Then, the application scenarios of remote sensing technology were analyzed, and the key remote sensing technologies involved were introduced. The technologies involved include crop field plot extraction, crop classification, crop disaster estimation, and crop yield estimation. Research progress of these technologies were reviewed and summarized,and the satellite data sources that most commonly used in plant income insurance were summarized as well. It was found that to obtain a better support for a development of plant income insurance as well as all crop insurance from remote sensing communities, issues existed not only in the involved remote sensing technologies, but also in the remote sensing industry as well as the insurance industry. The most two important technical problems in the current application scenario of planting income insurance are that: the plot extraction and crop classification are not automated enough; the yield estimation mechanism is not strong, and the accuracy is not high. At the industry level, the first issue is the limitation of the remote sensing technology itself in that the remote sensing is not almighty, suffering from limited data source, either from satellite or from other platform, laborious data preprocessing, and pricey data fees for most of the data, and the second is the compatibility between the current business of the insurance industry and the combination of remote sensing. In this regard, this paper proposed in total five specific suggestions, which are: 1st, to establish a data distribution platform to solve the problems of difficult data acquisition and processing and standardization of initial data; 2nd, to improve the sample database to promote the automation of plot extraction and crop classification; 3rd, to achieve faster, more accurate and more scientific yields through multidisciplinary research; 4th, to standardize remote sensing technology application in agricultural insurance, and 5th, to write remote sensing applications in crop insurance contract. With these improvements, the application mode of plant income insurance and probably the whole agriculture insurance would run in a way with easily available data, more automated and intelligent technology, standards to follow, and contract endorsements.
 Select | Open Access Smart Agriculture    2019, 1 (2): 94-95.   Abstract （497）      PDF （7561KB）（155）