Estimating FAO Blaney-Criddle b-Factor Using Soft Computing Models

FAO Blaney-Criddle has been generally an accepted method for estimating reference crop evapotranspiration. In this regard, it is inevitable to estimate the b-factor provided by Food and Agriculture Organization (FAO) of United Nations Irrigation Drainage Paper number 24. study, five soft computing methods, namely random forest (RF), M5 model tree (M5), support vector regression with polynomial function (SVR-poly), radial basis kernel (SVR-rbf), (RT), were adapted b-factor. And Their performances also compared. The suitable hyper-parameters each investigated. Five statistical indices deployed evaluate their performance, i.e., coefficient determination (r2), mean absolute relative error (MARE), maximum (MXARE), standard deviation (DEV), samples greater than 2% (NE > 2%). Findings reveal that SVR-rbf gave highest performance among models, followed M5, RF, SVR-poly, RT. derived a new explicit equation b estimation. bit lower efficacy network but outperformed equations. Models’ Applicability monthly evapotranspiration (ETo) was demonstrated.