Design and Application of Soilless Cultivation System in Smart Agriculture Based on AIoT

doi:10.11923/j.issn.2095-4050.cjas2024-0095

Abstract

Abstract:

In response to the pressing challenges of land resource scarcity, climate change, and environmental pollution, this study designs an AIoT-based smart soilless cultivation system that integrates soilless cultivation with modern information technology. The system aims to overcome the limitations of traditional agriculture and promote the development of agricultural automation, intelligence, and precision management. This system incorporates Internet of Things (IoT) sensing, computer vision, big data analytics, and machine learning technologies. It employs multi-source heterogeneous data fusion to analyze crop growth conditions, utilizes artificial intelligence algorithms for intelligent greenhouse environment regulation, and enables remote visual monitoring through web and mobile interfaces. The entire system is highly integrated in terms of hardware and software on the Jetson nano platform, offering excellent parallel computing capabilities and scalability. Experimental results demonstrate that, compared to the manually managed control group, vegetables under the intelligent regulation exhibited a 15.4% shorter growth cycle, a 17.0% increase in plant height, a 26.7% increase in leaf count, and a 27.4% improvement in plant weight. Additionally, the remote control interface proved to be convenient and efficient, validating the system's outstanding performance in promoting the modernization of soilless agricultural cultivation. This system provides robust technical support for the development of precision agriculture and has the potential to drive modern agriculture towards sustainable, efficient, and environmentally friendly development.

Key words: soilless cultivation, smart agriculture, Internet of Things, artificial intelligence, big data analysis, AIoT

LIN Hai, HUANG Duhui, LI Jingguo. Design and Application of Soilless Cultivation System in Smart Agriculture Based on AIoT[J]. Journal of Agriculture, 2025, 15(7): 57-64.

Figures/Tables 7

References 25

[1]	赵春江, 李瑾, 冯献. 面向2035年智慧农业发展战略研究[J]. 中国工程科学, 2021, 23(4):1-9. doi: 10.15302/J-SSCAE-2021.04.001
[2]	ZHANG X, CAO Z, DONG W. Overview of edge computing in the agricultural internet of things: Key technologies, applications, challenges[J]. Ieee Access, 2020, 8:141748-141761.
[3]	吴吉义, 李文娟, 曹健, 等. 智能物联网AIoT研究综述[J]. 电信科学, 2021, 37(8):1-17. doi: 10.11959/j.issn.1000-0801.2021204
[4]	HORI M, KAWASHIMA E, YAMAZAKI T. Application of cloud computing to agriculture and prospects in other fields[J]. Fujitsu scientific & technical journal, 2010, 46(4):446-454.
[5]	HUANG Y, CHEN Z X, TAO Y, et al. Agricultural remote sensing big data: Management and applications[J]. Journal of integrative agriculture, 2018, 17(9):1915-1931.
[6]	BANNERJEE G, SARKAR U, DAS S, et al. Artificial intelligence in agriculture: A literature survey[J]. International journal of scientific research in computer science applications and management studies, 2018, 7(3):1-6.
[7]	孙锦, 李谦盛, 岳冬, 等. 国内外无土栽培技术研究现状与应用前景[J]. 南京农业大学学报, 2022, 45(5):898-915.
[8]	张新, 陈兰生, 赵俊. 基于物联网技术的智慧农业大棚设计与应用[J]. 中国农机化学报, 2015, 36(5):90-95.
[9]	TIAN H, WANG T, LIU Y, et al. Computer vision technology in agricultural automation—A review[J]. Information processing in agriculture, 2020, 7(1):1-19.
[10]	OJHA T, MISRA S, RAGHUWANSHI N S. Internet of things for agricultural applications: The state of the art[J]. IEEE internet of things journal, 2021, 8(14):10973-10997.
[11]	张开生, 张盟蒙. 基于ZigBee的温室大棚环境监测系统研究[J]. 陕西理工学院学报(自科版), 2015, 31(6):18-22.
[12]	何勉. 基于物联网的温室环境监控系统设计[J]. 陕西理工大学学报(自然科学版), 2020, 36(3):54-59.
[13]	曹耀鹏, 刘厚诚. 大数据和农业物联网技术在智能温室环境控制中的应用——以济南科百智慧农业产业园为例[J]. 农业工程技术(温室园艺), 2021, 41(2):21.
[14]	胡天让, 张旭红, 陈岩. 基于物联网技术的温室大棚智能控制系统设计分析[J]. 石河子科技, 2020,6:31-32.
[15]	江琳莉, 史磊. 从梁平柚到梅州柚—区块链技术助力农产品溯源[J]. 农业大数据学报, 2020, 2(2):94-103. doi: 10.19788/j.issn.2096-6369.200210
[16]	孔繁涛, 朱孟帅, 孙坦. 现代信息技术在农业领域的应用分析与建议[J]. 智慧农业, 2019, 1(4):31.
[17]	CHEN C J, HUANG Y Y, LI Y S, et al. An AIoT based smart agricultural system for pests detection[J]. IEEE access, 2020, 8:180750-180761.
[18]	岳学军, 蔡雨霖, 王林惠, 等. 农情信息智能感知及解析的研究进展[J]. 华南农业大学学报, 2020, 41(6):14-28.
[19]	姚艳敏, 白玉琪. 农业大数据标准体系框架研究[J]. 农业大数据学报, 2020, 1(4):76-85.
[20]	蒋心璐, 陈天恩, 王聪, 等. 农业害虫检测的深度学习算法综述[J]. 计算机工程与应用, 2023, 59(6):30-44. doi: 10.3778/j.issn.1002-8331.2205-0604
[21]	SÜZEN A A, DUMAN B, SEN B. Benchmark analysis of jetson tx2, jetson nano and raspberry pi using deep-cnn[C]. 2020 international congress on human-computer interaction, optimization and robotic applications (HORA), 2020:1-5.
[22]	FUE K G, PORTER W M, RAINS G C. Deep learning based Real-time GPU-accelerated tracking and counting of cotton bolls under field conditions using a moving camera[C]. 2018 ASABE annual international meeting, 2018:1.
[23]	XIAOJING Z, YUANGUAI L. Zigbee implementation in intelligent agriculture based on internet of things[C]. 2nd international conference on electronic & mechanical engineering and information technology. 2012:1842-1846.
[24]	LIN H, YANG J. Light weight IBP deep residual network for image super resolution[J]. IEEE access, 2021, 9:93399-93408.
[25]	JIANG P, ERGU D, LIU F, et al. A Review of Yolo algorithm developments[J]. Procedia computer science, 2022, 199:1066-1073.

植株	生长周期	实验组平均值	对照组平均值
植株高度/cm	1周	4.2	3.8
	2周	11.6	9.7
	3周	15.8	13.5
叶片数量/片	1周	4	3
	2周	12	9
	3周	19	15
株重/g	3周	121	95

植株	生长周期	实验组平均值	对照组平均值
植株高度/cm	1周	4.2	3.8
	2周	11.6	9.7
	3周	15.8	13.5
叶片数量/片	1周	4	3
	2周	12	9
	3周	19	15
株重/g	3周	121	95

指标类别	指标名称	实验组	对照组	统计检验结果
生长指标	植株高度	M=15.8 cm，SD=1.2 cm	M=13.5 cm，SD=1.0 cm	t(78)=9.32，p<0.001，Cohen's d=2.08
	叶片数量	M=19片，SD=2片	M=15片，SD=2片	t(78)=9.49，p<0.001，Cohen's d=2.12
	株重	M=121 g，SD=8 g	M=95 g，SD=7 g	t(78)=15.68，p<0.001，Cohen's d=3.51
	存活率	97.5%(39/40)	90%(36/40)	χ²(1，N=80)=1.92，p=0.166
环境参数	温度	M=23.2°C，SD=0.5°C	M=21.5°C，SD=1.8°C	F(1,58)=156.3，p<0.001，η²=0.73
	湿度	M=78.5%，SD=2.1%	M=72.3%，SD=5.7%	F(1,58)=89.7，p<0.001，η²=0.61
	光照强度	M=1210 lx，SD=50 lx	M=980 lx，SD=180 lx	F(1,58)=203.5，p<0.001，η²=0.78
	EC值	M=2.4 mS/cm，SD=0.1 mS/cm	M=2.0 mS/cm，SD=0.3 mS/cm	F(1,58)=112.4，p<0.001，η²=0.66

指标类别	指标名称	实验组	对照组	统计检验结果
生长指标	植株高度	M=15.8 cm，SD=1.2 cm	M=13.5 cm，SD=1.0 cm	t(78)=9.32，p<0.001，Cohen's d=2.08
	叶片数量	M=19片，SD=2片	M=15片，SD=2片	t(78)=9.49，p<0.001，Cohen's d=2.12
	株重	M=121 g，SD=8 g	M=95 g，SD=7 g	t(78)=15.68，p<0.001，Cohen's d=3.51
	存活率	97.5%(39/40)	90%(36/40)	χ²(1，N=80)=1.92，p=0.166
环境参数	温度	M=23.2°C，SD=0.5°C	M=21.5°C，SD=1.8°C	F(1,58)=156.3，p<0.001，η²=0.73
	湿度	M=78.5%，SD=2.1%	M=72.3%，SD=5.7%	F(1,58)=89.7，p<0.001，η²=0.61
	光照强度	M=1210 lx，SD=50 lx	M=980 lx，SD=180 lx	F(1,58)=203.5，p<0.001，η²=0.78
	EC值	M=2.4 mS/cm，SD=0.1 mS/cm	M=2.0 mS/cm，SD=0.3 mS/cm	F(1,58)=112.4，p<0.001，η²=0.66