Watershed prioritization and decision-making based on weighted sum analysis, feature ranking, and machine learning techniques

Prediction and validation of Compound factors for prioritization watersheds are an essential application using machine learning (ML) techniques in water resource engineering. The current paper proposes a methodology to derive 14 morphometric 3 topo-hydrological parameters remote sensing (RS) geographical information systems (GIS). factor (CF) values calculated weighted sum analysis (WSA), ReliefF, the Pearson correlation coefficient, important identified. Two models, multilayer perceptron (MLP) support vector (SVM), utilized predict CF values. Predication accuracy ML models is evaluated with three parameters, mean absolute error (MAE), coefficient (PCC), root square (RMSE). It observed that maximum value PCC equal 1 achieved through ReliefF SVM, whereas minimum MAE RMSE SVM when Tenfold cross-validation applied. Since shows better results, applied create watershed. proposed helpful accurately predicting advantageous allocating proper watershed, which will be useful decision-making implementation conservation soil water.