Evaluating evapotranspiration using data mining instead of physical-based model in remote sensing

Precise calculations for determining the water requirements of plants and extent evapotranspiration are crucial in volume consumed plant production. In order to estimate over an extended area, different remote sensing algorithms require numerous climatological variables; however, variable measurements cover only limited areas thus resulting into erroneous areas. The exploiting both data mining technologies allows modeling process. this research, physical-based SEBAL algorithm was remodeled using M5 decision tree equations GIS. input variables consisted Albedo, emissivity, Normalized Difference Water Index (NDWI) which were defined as absorbed light, transformed moisture, respectively. After extracting best model 8 April 2019, these modeled GIS python scripts 2019 3 2020, calculated correlation coefficient (R2), mean absolute error (MAE), root squared (RMSE) 0.92, 0.54, 0.42, respectively, 2020 0.95, 0.31, 0.23 order. Moreover, further evaluation model, a sensitivity analysis uncertainty carried out. revealed that is more sensitive Albedo than two other inputs, when applying techniques instead SEBAL, estimation has lower accuracy.