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

Accurate estimation of Reference Evapotranspiration (ET0) is important for efficient management and conservation irrigation water. Existing methods ET0 rate determination are complex application at the farmer level. Apart from standard determination, many data-driven soft computing approaches were also proposed to determine with limited data set. We a temperature humidity-based ML approach on directly sensed environmental conditions crop field. Crop field by Internet Things (IoT) architecture. year 2015 2021 in Pakistan used training testing model. Gaussian Naive Bayes (GNB), Support Vector Machine (SVM), k-Nearest Neighbours (KNN), Artificial Neural Network (ANN) based models compared performance. fields humidity pass model train predict ET0-rate fields. The 10-fold cross-validation technique applied evaluation approach. accuracy solution against Food Agriculture Organization (FAO) recommended Penman-Monteith method determination. As concerned ML-based KNN more accurate as SVM,GNB ANN 92% accuracy. reducing Root Mean Squared Errors (RMSE) 16% Absolute (MAE) 3% state art