Proposition of new ensemble data-intelligence model for evapotranspiration process simulation

Due to climatic change, a variation in meteorological aspects influences the water requirement for crops, evapotranspiration, and water allocation of agro-meteorological and agriculture. Accurate estimation of Evapotranspiration ( ET_o ) has great importance to improve the utilization of water efficiently and irrigation scheduling. The main overarching goal of this paper is to investigate the abilities and applicability of three supervised machine learning models: Extreme Machine Learning ( ELM_1 , ELM_2 , ELM_3 , ELM_4 ), Multi-layer Perceptrons-Neural Network ( MLP_1 , MLP_2 , MLP_3 , MLP_4 ), Support Vector Machine ( SVM_1 , SVM_2 , SVM_3 , and, SVM_4 ) to modeling the daily ET_o . Further, a three-layer multi-model ensemble machine learning approach is presented to predict evapotranspiration ET_o . The first layer consists of different statistical models to produce individual forecasts. The blending approach is employed to create an ensemble of the forecasts generated by the initial layer to produce probabilistic forecasts. In the second layer, three ensemble models ( Ensemble_ELM , Ensemble_MLP , Ensemble_SVM ) are trained for prediction of ET_o by using the previous layer predictions and training data. In the third-layer, accuracy of the ( ET_o ) is estimated by tuning the parameters of second layer ensemble model. It has been analyzed that all statistical models showed effectiveness in high performance for modeling everyday ET_o (e.g. Nash-Sutchliffe efficiency (NSE)= 0.93-0.99, coefficient of determination (r ^2 ) = 0.93-0.99, Accuracy (ACC) = 80-99, Mean Square error (MSE) = 0.0103-0.1516). Particularity, the ensemble method with SVM achieved good accuracy (99.46