Machine Learning Based Prediction of Reference Evapotranspiration (ET₀) Using IoT

Abstract

Accurate estimation of Reference Evapotranspiration (ET 0 ) is important for efficient management and conservation of irrigation water. Existing methods of ET 0 rate determination are complex for application at the farmer level. Apart from standard methods of ET 0 determination, many data-driven soft computing approaches were also proposed to determine the ET 0 with limited data set. We proposed a temperature and humidity-based ML approach for ET 0 rate determination on directly sensed environmental conditions of the crop field. Crop field environmental conditions for (ET 0 ) rate determination are sensed by the proposed Internet of Things (IoT) architecture. Crop field environmental conditions from the year 2015 to 2021 in Pakistan are used for the training and testing of the proposed model. Gaussian Naive Bayes (GNB), Support Vector Machine (SVM), k-Nearest Neighbours (KNN), and Artificial Neural Network (ANN) based models are compared for performance. Crop fields directly sensed temperature and humidity pass to the model to train and predict the ET 0 -rate of crop fields. The 10-fold cross-validation technique is applied for the evaluation of the proposed approach. The accuracy of the proposed solution for the ET 0 rate is compared against the Food and Agriculture Organization (FAO) recommended Penman-Monteith method for ET 0 rate determination. As concerned of the ML-based models the KNN model is more accurate as compared to SVM,GNB and ANN models with 92% accuracy. The KNN model of ET 0 is more efficient in reducing the Root Mean Squared Errors (RMSE) by 16% and Mean Absolute Errors (MAE) by 3% against the state of the art approach.INDEX TERMS Internet of Things (IoT), Reference Evapotranspiration (ET 0 ), Support Vector Machine (SVM), Gaussian Naive Bayes (GNB), K-Nearest Neighbour (KNN), Artificial Neural Network (ANN), Penman-Monteith

Smart irrigation for coriander plant: Saving water with AI and IoT

“…While Tr et al [16] achieved a lower RMSE (0.016), their results may not be directly comparable due to potentially limited data scope or specific application. Compared to other studies (Hill et al [9], Hu et al [12], Dong et al [18]), our approach demonstrates significantly lower and more consistent RMSE and MAE values across a wider range, which suggests greater generalizability and accuracy. This highlights the effectiveness of our method in precisely estimating EV T 0 for various agricultural applications.…”

Study of applications of Internet of Things and Machine Learning for Smart Agriculture

“…Different sensor nodes, network layer protocols, cloud services and ML algorithms developed for smart agriculture applications viz. irrigation monitoring ( [1], [26], [27], [34], [43], [44]), production process management ( [28], [29], [41]), plant growth and disease monitoring ( [30], [31], [32], [38], [39], [42]) and precision agriculture ( [33], [34], [40]) are considered in Table III.…”

Developing a Hybrid Irrigation System for Smart Agriculture Using IoT Sensors and Machine Learning in Sri Ganganagar, Rajasthan

“…We assess the accuracy of three machine learning techniques for determining ET0: Gaussian Naïve Bays (GNB), K-nearest neighbor (KNN), support vector machine (SVM), and artificial neural network (ANN). It has been demonstrated that KNN is more accurate than SVM and GNB models, with 92% accuracy, high precision, recall, and f-measure [32] 6. LR, LDA, KNN, CART, NB, and SVM The paper describes an intelligent system for the Internet of Things, LoRa-based wireless sensor networks, and machine learning for scheduling and monitoring precise irrigation.…”