Advanced Hybrid Metaheuristic Machine Learning Models Application for Reference Crop Evapotranspiration Prediction

Hybrid metaheuristic algorithm (MA), an advanced tool in the artificial intelligence field, provides precise reference evapotranspiration (ETo) prediction that is highly important for water resource availability and hydrological studies. However, hybrid MAs are quite scarcely used to predict ETo existing literature. To this end, abilities of two support vector regression (SVR) models coupled with three types including particle swarm optimization (PSO), grey wolf (GWO), gravitational search (GSA) were studied compared single SVR SVR-PSO predicting monthly using meteorological variables as inputs. Data obtained from Rajshahi, Bogra, Rangpur stations humid region, northwestern Bangladesh, was purpose a case study. The precision proposed trained tested nine input combinations assessed root mean square error (RMSE), absolute (MAE), Nash–Sutcliffe efficiency (NSE). results revealed SVR-PSOGWO model outperformed other applied soft computing all combinations, followed by SVR-PSOGSA, SVR-PSO, SVR. It found decreases RMSE SVR, SVR-PSOGSA 23%, 27%, 14%, 21%, 19%, 5% Bogra during testing stage. reduced 32%, 20%, 3%, respectively, employing Rajshahi Station. machine learning has been recommended potential region similar climatic regions worldwide.