Prediction of soil moisture using machine learning techniques: A case study of an IoT-based irrigation system in a naturally ventilated polyhouse

被引:1
|
作者
Challa, Lakshmi Poojitha [1 ]
Singh, Chandra Deep [1 ]
Rao, Kondapalli Venkata Ramana [1 ]
Subeesh, Anakkallan [2 ]
Srilakshmi, Mandru [1 ]
机构
[1] ICAR Cent Inst Agr Engn, Div Irrigat & Drainage Engn, Bhopal 462038, Madhya Pradesh, India
[2] ICAR Cent Inst Agr Engn, Div Agr Mechanizat, Bhopal, Madhya Pradesh, India
关键词
internet of things; machine learning; microenvironment; soil moisture; internet des objets; apprentissage automatique; microenvironnement; humidite du sol;
D O I
10.1002/ird.2933
中图分类号
S3 [农学(农艺学)];
学科分类号
0901 ;
摘要
The agricultural sector faces a massive challenge in enhancing food production for the growing population with limited water resources. For effective and optimum utilization of fresh water, developing smart irrigation systems based on the internet of things (IoT) is essential for scheduling irrigation based on crop water requirements. In this study, an IoT-based irrigation system was developed and evaluated inside a greenhouse located in the experimental fields of Indian Council of Agricultural Research-Central Institute of Agricultural Engineering (ICAR-CIAE), Bhopal, India. Data on microenvironmental parameters such as temperature, relative humidity, light intensity, soil temperature and soil moisture were collected from the sensors developed inside the greenhouse. Soil moisture was predicted based on the field data collected via different machine learning techniques, such as the decision tree (DT), random forest (RF), multiple linear regression (MLR), extreme gradient boosting (XGB), K-nearest neighbour (KNN) and artificial neural network (ANN) methods, with three input combinations. The ANN (coefficient of determination [R2] = 0.942, 0.939) models performed well but were found to be less effective than the RF (R2 = 0.991, 0.951) and XGB (R2 = 0.997, 0.941) models in the training and testing phases, respectively. The RF and XGB models outperformed the other models, while the MLR (R2 = 0.955, 0.875) technique underperformed. With respect to both the testing and training datasets, the models trained with all four inputs outperformed the models trained with two or three inputs. Le secteur agricole est confronte a un defi de taille en ce qui concerne l'amelioration de la production alimentaire pour une population croissante avec des ressources en eau limitees. Pour l'utilisation efficace et optimale de l'eau douce, le developpement de systemes d'irrigation intelligents bases sur l'internet des objets (IoT) est exige pour planifier l'irrigation en fonction des besoins en eau des cultures. Dans cette etude, un systeme d'irrigation a base l'IoT a ete developpe et evalue a l'interieur d'une serre situee dans les champs experimentaux de l'ICAR-CIAE, a Bhopal, en Inde. Les donnees sur les parametres microenvironnementaux tels que la temperature, l'humidite relative, l'intensite lumineuse, la temperature du sol et l'humidite du sol ont ete recueillies a partir des capteurs developpes a l'interieur de la serre. L'humidite du sol a ete predit sur la base des donnees de terrain recueillies au moyen de differentes techniques d'apprentissage automatique, telles que l'arbre de decision (DT), la foret aleatoire (RF), la regression lineaire multiple (MLR), la poussee de gradient extreme (XGB), le voisin le plus proche (KNN) et le reseau de neurones artificiels (ANN), avec trois combinaisons d'entree. Les modeles ANN (R2 = 0,942, 0,939) ont donne de bons resultats, mais se sont averes moins efficaces que les modeles RF (R2 = 0,991, 0,951) et XGB (R2 = 0,997, 0,941) dans les phases de formation et d'essai, respectivement. Les modeles RF et XGB ont surpasse les autres modeles, tandis que la technique MLR (R2 = 0,955, 0,875) a ete moins performante. En ce qui concerne les ensembles de donnees d'essais et de formation, les modeles formes avec les quatre entrees ont surpasse les modeles formes avec deux ou trois entrees.
引用
收藏
页码:1138 / 1150
页数:13
相关论文
共 50 条
  • [1] IoT-based group size prediction and recommendation system using machine learning and deep learning techniques
    Chopra, Deepti
    Kaur, Arvinder
    [J]. SN APPLIED SCIENCES, 2021, 3 (02)
  • [2] IoT-based group size prediction and recommendation system using machine learning and deep learning techniques
    Deepti Chopra
    Arvinder Kaur
    [J]. SN Applied Sciences, 2021, 3
  • [3] IoT-based disease prediction using machine learning
    Siddiqui, Salman Ahmad
    Ahmad, Anwar
    Fatima, Neda
    [J]. COMPUTERS & ELECTRICAL ENGINEERING, 2023, 108
  • [4] IoT-Based Smart Inventory Management System Using Machine Learning Techniques
    Manoharan, Geetha
    Kumar, Vipin
    Karthik, A.
    Asha, V
    Mohan, Chinnem Rama
    Nijhawan, Ginni
    [J]. 2024 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATION AND APPLIED INFORMATICS, ACCAI 2024, 2024,
  • [5] An IoT-Based Real-Time Intelligent Irrigation System using Machine Learning
    Shahriar, Saleh Mohammed
    Peyal, Hasibul Islam
    Nahiduzzaman, Md
    Pramanik, Md Abu Hanif
    [J]. PROCEEDINGS OF 2021 13TH INTERNATIONAL CONFERENCE ON INFORMATION & COMMUNICATION TECHNOLOGY AND SYSTEM (ICTS), 2021, : 277 - 281
  • [6] A Soil Moisture Calibration Service for IoT-based Smart Irrigation
    Zyrianoff, Ivan Dimitry
    Neto, Andre Torre
    Silva, Dener
    Cinotti, Tullio Salmon
    Di Felice, Marco
    Kamienski, Carlos
    [J]. 2021 IEEE INTERNATIONAL WORKSHOP ON METROLOGY FOR AGRICULTURE AND FORESTRY (IEEE METROAGRIFOR 2021), 2021, : 315 - 319
  • [7] IoT-Based Crop Yield Prediction System in Indian Sub-continent Using Machine Learning Techniques
    Nithya V.
    Josephine M.S.
    Jeyabalaraja V.
    [J]. Remote Sensing in Earth Systems Sciences, 2023, 6 (3-4) : 156 - 166
  • [8] Machine Learning based soil moisture prediction for Internet of Things based Smart Irrigation System
    Singh, Gursimran
    Sharma, Deepak
    Goap, Amarendra
    Sehgal, Sugandha
    Shukla, A. K.
    Kumar, Satish
    [J]. PROCEEDINGS OF 2019 5TH IEEE INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, COMPUTING AND CONTROL (ISPCC 2K19), 2019, : 175 - 180
  • [9] A smart IoT-based irrigation system design using AI and prediction model
    Behzadipour, Faeze
    Raeini, Mahmod Ghasemi Nezhad
    Mehdizadeh, Saman Abdanan
    Taki, Morteza
    Moghadam, Bijan Khalil
    Bavani, Mohammad Reza Zare
    Lloret, Jaime
    [J]. NEURAL COMPUTING & APPLICATIONS, 2023, 35 (35): : 24843 - 24857
  • [10] Waste Management System Using IoT-Based Machine Learning in University
    Tran Anh Khoa
    Cao Hoang Phuc
    Pham Duc Lam
    Le Mai Bao Nhu
    Nguyen Minh Trong
    Nguyen Thi Hoang Phuong
    Nguyen Van Dung
    Nguyen Tan-Y
    Hoang Nam Nguyen
    Dang Ngoc Minh Duc
    [J]. WIRELESS COMMUNICATIONS & MOBILE COMPUTING, 2020, 2020 (2020):