Comparative Study of the Regulation Effects of Artificial Intelligence-Assisted Planting Strategies on Strawberry Production in Greenhouse

doi:10.12133/j.smartag.SA202203006

Abstract

Abstract:

Artificial intelligence (AI) assisted planting can improve in the precise management of protected horticultural crops while also alleviating the increasingly prevalent problem of labor shortage. As a typical representative of labor-intensive industries, the strawberry industry has a growing need for intelligent technology. To assess the regulatory effects of various AI strategies and key technologies on strawberry production in greenhouse, as well as provide valuable references for the innovation and industrial application of AI in horticultural crops, four AI planting strategies were evaluated. Four 96 m²modern greenhouses were used for planting strawberry plants. Each greenhouse was equipped with standard sensors and actuators, and growers used artificial intelligence algorithms to remotely control the greenhouse climate and crop growth. The regulatory effects of four different AI planting strategies on strawberry growth, fruit yield and qualitywere compared and analyzed. And human-operated cultivation was taken as a reference to analyze the characteristics, existing problems and shortages. Each AI planting strategy simulated and forecast the greenhouse environment and crop growth by constructing models. AI-1 implemented greenhouse management decisions primarily through the knowledge graph method, whereas AI-2 transferred the intelligent planting model of Dutch greenhouse tomato planting to strawberry planting. AI-3 and AI-4 created growth and development models for strawberries based on World Food Studies (WOFOST) and Product of Thermal Effectiveness and Photosynthesis Active Radiation (TEP), respectively. The results showed that all AI supported strategy outperformed a human-operated greenhouse that served as reference. In comparison to the human-operated cultivation group, the average yield and output value of the AI planting strategy group increased 1.66 and 1.82 times, respectively, while the highest Return on Investment increased 1.27 times. AI can effectively improve the accuracy of strawberry planting management and regulation, reduce water, fertilizer, labor input, and obtain higher returns under greenhouse production conditions equipped with relatively complete intelligent equipment and control components, all with the goal of high yield and quality. Key technologies such as knowledge graphs, deep learning, visual recognition, crop models, and crop growth simulators all played a unique role in strawberry AI planting. The average yield and Return on Investment (ROI) of the AI groups were greater than those of the human-operated cultivation group. More specifically, the regulation of AI-1 on crop development and production was relatively stable, integrating expert experience, crop data, and environmental data with knowledge graphs to create a standardized strawberry planting knowledge structure as well as intelligent planting decision-making approach. In this study, AI-1 achieved the highest yield, the heaviest average fruit weight, and the highest ROI. This group's AI-assisted strategy optimized the regulatory effect of growth, development, and yield formation of strawberry crops in consideration of high yield and quality. However, there are still issues to be resolved, such as the difficulty of simulating the disturbance caused by manual management and collecting crop ontology data.

Key words: artificial intelligence, strawberry, planting strategies, regulation effects, automated greenhouse, knowledge graphs

CLC Number:

S625.5+1

GENG Wenxuan, ZHAO Junye, RUAN Jiwei, HOU Yuehui. Comparative Study of the Regulation Effects of Artificial Intelligence-Assisted Planting Strategies on Strawberry Production in Greenhouse[J]. Smart Agriculture, 2022, 4(2): 183-193.

Figures/Tables 8

Table 1

Artificial intelligence planting strategy and technical protocols of strawberry

处理	主要特点	技术策略和实施过程
AI-1	知识图谱+视觉识别+作物模型	结合草莓生长模型和视觉识别，通过知识推理^［14］的方法实现温室管理决策以达到产量最优的目标。首先将所调研的10位专家种植经验和环境及作物传感器数据翻译成计算机语言，构建基于Neo4j的草莓种植管理知识图谱^［15］。然后利用作物水肥模型和温室气候模型分析草莓植株的营养生长和生殖生长过程，由路径排序算法^［16］根据知识图谱模拟专家进行决策。其中机器视觉识别主要针对作物来源数据，采用YOLOv4神经网络多特征融合法^［17］实现草莓生育期、吐水情况、花序和果实的识别，通过与潜在作物长势对比的生长偏差为知识图谱决策提供依据
AI-2	温室番茄种植模式迁移+双层算法	将荷兰温室番茄的智能种植模式^{［11, 18］}迁移到草莓种植，通过改良后的机器学习和条件控制算法制定智能种植管理策略，并引入深度学习处理作物图像信息数据，预测和判断作物生长发育情况^{［12, 19］}。采用双层算法，第一层算法是条件决策，主要是根据专家经验设定阈值，防止极端决策越过不合理界限；第二层是融合产量预测决策和设定值优化决策的混合决策。其中产量预测是基于大数据通过机器学习制定的决策，设定值优化决策是基于传统植物生理模型和专家经验的决策
AI-3	视觉识别+作物模型+专家系统	将作物生长仿真器SUCROS87^［20］应用于草莓潜在产量预测，计算得出在本试验条件下，每株草莓在盛果期每天最多可形成1.6 g干物质，通过与实际干物质量对比，为管理调控提供参考。基于比叶面积（Specific Leaf Area，SLA）构建了WOFOST （World Food Studies）^［21］作物生长模型，预测草莓产量，结合视觉识别对比潜在长势和实际长势，由专家系统提供种植策略。其中利用CNN构建了图像识别系统，通过加入残差模块减少复杂农业背景的干扰，实现自动单叶分割、叶面积测算的目的
AI-4	作物生长模型+发育模型	基于作物干物质生产分配规律和辐热积（Product of Thermal Effectiveness and Photosynthesis Active Radiation，TEP）构建草莓生长发育模型^{［22, 23］}，对作物生长和产量形成进行预测和干预。草莓干物质生产模型主要包括叶面积指数模型、光能截获模型和干物质分配指数模型，用于既定水肥条件下的产量预测。辐热积参数的计算依据主要是基于三基点温度的相对热效应和光合有效辐射。通过作物生长模型和发育模型，自动控制相应发育期的水分和肥料，并根据作物实际长势调节辐热积参数推迟或者加快生育进程

Table 1

Fig. 1

Fig. 2

Fig. 3

Table 2

Table 3

Table 4

Table 5

References 28

1	张运涛, 雷家军, 赵密珍, 等. 新中国果树科学研究70年——草莓[J]. 果树学报, 2019, 36(10): 1441-1452.
	ZHANG Y, LEI J, ZHAO M, et al. Fruit scientific research in New China in the past 70 years: Strawberry[J]. Journal of Fruit Science, 2019, 36(10): 1441-1452.
2	王晓立, 韩浩章, 苗昌云, 等. 草莓栽培现状与栽培方式概述[J]. 安徽农学通报, 2020, 26(10): 36-37, 116.
	WANG X, HAN H, MIAO C, et al. Research cultivation status and cultivation methods of Fragaria ananassa [J]. Anhui Agricultural Science Bulletin, 2020, 26(10): 36-37, 116.
3	舒锐, 焦健, 臧传江, 等. 我国草莓产业现状及发展建议[J]. 中国果菜, 2019, 39(1): 51-53.
	SHU R, JIAO J, ZANG C, et al. The current situation and development suggestions of strawberry industry in China[J]. China Fruit & Vegetable, 2019, 39(1): 51-53.
4	LIN F, CHEN H, ZHUANG P. Intelligent greenhouse system based on remote sensing images and machine learning promotes the efficiency of agricultural economic growth[J]. Environmental Technology & Innovation, 2021: ID 101758.
5	XIAO J, CHUNG P, WU H, et al. Detection of strawberry diseases using a convolutional neural network[J]. Plants, 2020, 10(1): 31.
6	JIANG Q, WU G, TIAN C, et al. Hyperspectral imaging for early identification of strawberry leaves diseases with machine learning and spectral fingerprint features[J]. Infrared Physics & Technology, 2021, 118: ID103898.
7	MA L, GUO X, ZHAO S, et al. Algorithm of strawberry disease recognition based on deep convolutional neural network[J]. Cognitive Computing Solutions for Complexity Problems in Computational Social Systems, 2021: 1-10.
8	HE Z, KARKEE M, UPADHAYAY P. Detection of strawberries with varying maturity levels for robotic harvesting using YOLOv4[C]// 2021 ASABE Annual International Virtual Meeting, St. Joseph, Michigan: American Society of Agricultural and Biological Engineers, 2021: 1.
9	ZHANG Y, YU J, CHEN Y, et al. Real-time strawberry detection using deep neural networks on embedded system (rtsd-net): An edge AI application [J]. Computer and Electronics in Agriculture, 2022, 192: ID106586.
10	PARK S, KIM J W. Design and implementation of a hydroponic strawberry monitoring and harvesting timing information supporting system based on nano AI-Cloud and IoT-Edge[J]. Electronics, 2021, 10(12): ID 1400.
11	HEMMING S, DE ZWART F, ELINGS A, et al. Cherry tomato production in intelligent greenhouses—Sensors and AI for control of climate, irrigation, crop yield, and quality[J]. Sensors, 2020, 20(22): ID 6430.
12	HEMMING S, DE ZWART H F, ELINGS A, etal. Remote control of greenhouse vegetable production with artificial intelligence—Greenhouse climate, irrigation, and crop production[J]. Sensors, 2019, 19(8): ID 1807.
13	BUWALDA F, HENTEN E JVAN, DE GELDER A, et al. Toward an optimal control strategy for sweet pepper cultivation-1. a dynamic crop model[J]. Acta Hortic, 2006, 718: 367-374.
14	林森, 郭文忠, 郑建锋, 等. 基于知识图谱和机器视觉的智慧草莓生产托管服务系统实践[J]. 农业工程技术, 2021, 41(4): 17-20.
	LIN S, GUO W, ZHENG J, et al. Practice of smart strawberry production hosting service system based on knowledge graph and machine vision[J]. Agricultural Engineering Technology, 2021, 41(4): 17-20.
15	张宇, 郭文忠, 林森, 等. 基于Neo4j的草莓种植管理知识图谱构建及验证[J]. 现代农业科技, 2022(1): 223-230.
	ZHANG Y, GUO W, LIN S, et al. Construction and verification of knowledge graph of strawberry planting management based on Neo4j[J]. Modern Agricultural Science and Technology, 2022(1): 223-230.
16	张宇, 赵春江, 林森, 等. 基于Penman-Monteith模型和路径排序算法相结合的草莓灌溉方法与验证[J]. 智慧农业(中英文), 2021, 3(3): 116-128.
	ZHANG Y, ZHAO C, LIN S, et al. Irrigation method and verification of strawberry based on Penman-Monteith model and path ranking algorithm [J]. Smart Agriculture, 2021, 3(3): 116-128.
17	龙洁花, 郭文忠, 林森, 等. 改进YOLOv4的温室环境下草莓生育期识别方法[J]. 智慧农业(中英文), 2021, 3(4): 99-110.
	LONG J, GUO W, LIN S, et al. Strawberry growth period recognition method under greenhouse environment based on improved YOLOv4[J]. Smart Agriculture, 2021, 3(4): 99-110.
18	MARCELIS L F M, ELINGS A, DE VISSER PH B, et al. Simulating growth and development of tomato crop[J]. Acta Hortic, 2009, 821: 101-110.
19	MORIMOTO, T, HASHIMOTO Y. AI approaches to identification and control of total plant production systems[J]. Control Engineering Practice, 2000, 8: 555-567.
20	KROPFF M J, BASTIAANS L, GOUDRIAAN J. Implications of improvements in modeling canopy photosynthesis in SUCROS (a simple and universal crop growth simulator)[J]. Netherlands Journal of Agricultural Science, 1987, 35(2): 192-194.
21	AVAN DIEPEN C, WOLF J, HVAN KEULEN, et al. WOFOST: A simulation model of crop production[J]. Soil Use Manag, 1989, 5: 16-24.
22	倪纪恒, 陈学好, 陈春宏, 等. 用辐热积法模拟温室黄瓜果实生长[J]. 农业工程学报, 2009, 25(5): 192-196.
	NI J, CHEN X, CHEN C, et al. Simulation of cucumber fruit growth in greenhouse based on production of thermal effectiveness and photosynthesis active radiation[J]. Transactions of the CSAE, 2009, 25(5): 192-196.
23	王丹丹, 吕振宁, 李坚, 等. 基于辐热积的日光温室不同茬次袋培番茄干物质模型比较[J]. 西北农业学报, 2018, 27(2): 238-243.
	WANG D, LV Z, LI J, et al. Comparison of dry matter partitioning model of tomato cultivated with growth-bag during different growing seasons based on product of thermal effectiveness and photosynthesis active radiation in solar greenhouse[J]. Acta Agriculture Boreali-occidentalis Sinica, 2018, 27(2): 238-243.
24	RUAN J, WANG G, NING G, et al. Longer duration of short-day treatment is required to advance flowering and fruiting of decaploid strawberry 'Tokun' [J]. HortScience, 2020, 55(1): 30-34.
25	李永秀, 罗卫红, 倪纪恒, 等. 用辐热积法模拟温室黄瓜叶面积、光合速率与干物质产量[J]. 农业工程学报, 2005(12): 131-136.
	LI Y, LUO W, NI J, et al. Simulation of leaf area, photosynthetic rate and dry matter production in greenhouse cucumber based on product of thermal effectiveness and photosynthetically active radiation[J]. Transactions of the CSAE, 2005(12): 131-136.
26	徐超, 王明田, 杨再强, 等. 苗期高温对草莓生育期的影响及其模拟[J]. 中国农业气象, 2020, 41(10): 644-654.
	XU C, WANG M, YANG Z, et al. Effect of high temperature in seedling stage on phenological stage of strawberry and its simulation[J]. Chinese Journal of Agrometeorology, 2020, 41(10): 644-654.
27	徐凌翔, 陈佳玮, 丁国辉, 等. 室内植物表型平台及性状鉴定研究进展和展望[J]. 智慧农业(中英文), 2020, 2(1): 23-42.
	XU L, CHEN J, DING G, et al. Indoor phenotyping platforms and associated trait measurement: Progress and prospects[J]. Smart Agriculture, 2020, 2(1): 23-42.
28	周济, TARDIEU F, PRIDMORE T, 等. 植物表型组学: 发展、现状与挑战[J]. 南京农业大学学报, 2018, 41(4): 580-588.
	ZHOU J, TARDIEU F, RIDMORE T, et al. Plant phenomics: History,present status and challenges[J]. Journal of Nanjing Agricultural University, 2018, 41(4): 580-588.

定植后天数/d	第一花序				第二花序				第三花序
定植后天数/d	AI-1	AI-2	AI-3	AI-4	AI-1	AI-2	AI-3	AI-4	AI-1	AI-2	AI-3	AI-4
12~26	1.25	13.92	5.00	20.83	——	——	——	——	——	——	——	——
27~43	97.50	86.08	91.25	52.78	5.00	6.41	3.90	3.90	——	——	——	——
44~58	1.250	——	1.25	23.61	5.00	——	1.30	11.69	——	——	——	——
59~73	——	——	——	2.78	3.75	1.28	——	50.65	——	——	——	6.49
74~88	——	——	2.50	——	51.25	29.40	28.57	22.08	2.50	1.27	——	——
89~104	——	——	——	——	32.50	57.69	63.64	6.49	5.00	5.06	2.56	3.90
105~119	——	——	——	——	2.50	5.13	2.60	5.19	20.00	21.52	21.79	59.74
120~134	——	——	——	——	——	——	——	——	50.00	18.99	73.08	24.68

处理	定植后天数/d	产量/个	平均单果质量/g
AI-1	63~73	177	13.3
	74~104	15	13.3
	105~134	363	16.2
AI-2	63~73	274	12.0
	74~104	4	11.7
	105~134	155	14.3
AI-3	63~73	309	12.5
	74~104	5	11.5
	105~134	259	14.1
AI-4	63~73	78	12.8
	74~104	97	14.5
	105~134	265	13.1

处理	分级产量/g				总产量/g	可溶性固形物/%
处理	A级	B级	C级	D级	总产量/g	可溶性固形物/%
CK	96.40	449.80	436.40	1598.60	2581.20	10.21
AI-1	295.80	1535.20	225.30	4372.10	8456.10	9.80
AI-2	0.00	249.20	881.60	4406.30	5537.10	9.73
AI-3	0.00	529.00	1461.00	5583.20	7573.20	9.23
AI-4	30.60	481.00	1040.60	4325.20	5877.40	9.59

处理	投入结构/元					总成本/元	产值/元	投入产出比
处理	设施	管理	农药	肥料	水电费	总成本/元	产值/元	投入产出比
CK	64.00	240.00	14.80	29.20	15.80	375.60	181.30	0.48
AI-1	267.00	171.20	9.80	36.90	105.60	590.40	642.10	1.09
AI-2	264.00	160.00	10.20	129.40	129.40	692.90	422.20	0.61
AI-3	256.80	173.10	13.40	6.80	130.40	580.40	568.80	0.98
AI-4	256.80	160.00	15.90	31.70	162.70	627.00	413.00	0.66

[1]	ZHANG Fan, ZHOU Mengting, XIONG Benhai, YANG Zhengang, LIU Minze, FENG Wenxiao, TANG Xiangfang. Research Advances and Prospect of Intelligent Monitoring Systems for the Physiological Indicators of Beef Cattle [J]. Smart Agriculture, 2024, 6(4): 1-17.
[2]	GUO Wang, YANG Yusen, WU Huarui, ZHU Huaji, MIAO Yisheng, GU Jingqiu. Big Models in Agriculture: Key Technologies, Application and Future Directions [J]. Smart Agriculture, 2024, 6(2): 1-13.
[3]	FAN Jiangchuan, WANG Yuanqiao, GOU Wenbo, CAI Shuangze, GUO Xinyu, ZHAO Chunjiang. Fast Extracting Method for Strawberry Leaf Age and Canopy Width Based on Instance Segmentation Technology [J]. Smart Agriculture, 2024, 6(2): 95-106.
[4]	MAO Kebiao, ZHANG Chenyang, SHI Jiancheng, WANG Xuming, GUO Zhonghua, LI Chunshu, DONG Lixin, WU Menxin, SUN Ruijing, WU Shengli, JI Dabin, JIANG Lingmei, ZHAO Tianjie, QIU Yubao, DU Yongming, XU Tongren. The Paradigm Theory and Judgment Conditions of Geophysical Parameter Retrieval Based on Artificial Intelligence [J]. Smart Agriculture, 2023, 5(2): 161-171.
[5]	GUI Zechun, ZHAO Sijian. Research Application of Artificial Intelligence in Agricultural Risk Management: A Review [J]. Smart Agriculture, 2023, 5(1): 82-98.
[6]	ZHAO Ruixue, YANG Chenxue, ZHENG Jianhua, LI Jiao, WANG Jian. Agricultural Intelligent Knowledge Service: Overview and Future Perspectives [J]. Smart Agriculture, 2022, 4(4): 105-125.
[7]	WANG Hui, CHEN Ruipeng, YU Zhixue, HE Yue, ZHANG Fan, XIONG Benhai. Porphyrin and Semiconducting Single Wall Carbon Nanotubes based Semiconductor Field Effect Gas Sensor for Determination of Phytophthora Strawberries [J]. Smart Agriculture, 2022, 4(3): 143-151.
[8]	LONG Jiehua, GUO Wenzhong, LIN Sen, WEN Chaowu, ZHANG Yu, ZHAO Chunjiang. Strawberry Growth Period Recognition Method Under Greenhouse Environment Based on Improved YOLOv4 [J]. Smart Agriculture, 2021, 3(4): 99-110.
[9]	ZHANG Yu, ZHAO Chunjiang, LIN Sen, GUO Wenzhong, WEN Chaowu, LONG Jiehua. Irrigation Method and Verification of Strawberry Based on Penman-Monteith Model and Path Ranking Algorith [J]. Smart Agriculture, 2021, 3(3): 116-128.
[10]	LI Daoliang, LIU Chang. Recent Advances and Future Outlook for Artificial Intelligence in Aquaculture [J]. Smart Agriculture, 2020, 2(3): 1-20.
[11]	Zhao Chunjiang. State-of-the-art and recommended developmental strategic objectivs of smart agriculture [J]. Smart Agriculture, 2019, 1(1): 1-7.