Modern Techniques to Modeling Reference Evapotranspiration in a Semiarid Area Based on ANN and GEP Models

Evapotranspiration (ET) is a significant aspect of the hydrologic cycle, notably in irrigated agriculture. Direct approaches for estimating reference evapotranspiration (ET0) are either difficult or need large number inputs that not always available from meteorological stations. Over 6-year period (2006–2011), this study compares Feed Forward Neural Network (FFNN), Radial Basis Function (RBFNN), and Gene Expression Programming (GEP) machine learning daily ET0 station Lower Cheliff Plain, northwest Algeria. was estimated using FAO-56 Penman–Monteith (FAO56PM) equation observed data. The FAO56PM then used as target output models, while data were model inputs. Based on coefficient determination (R2), root mean square error (RMSE), Nash–Sutcliffe efficiency (EF), RBFNN GEP models showed promising performance. However, FFNN performed best during training (R2 = 0.9903, RMSE 0.2332, EF 0.9902) testing 0.9921, 0.2342, phases forecasting evapotranspiration.