Estimation of water's surface elevation in compound channels with converging and diverging floodplains using soft computing techniques

Abstract In this research, water's surface elevation in compound channels with converging and diverging floodplains using soft computing models including the Multi-Layer Perceptron Neural Network (MLPNN), Group Method of Data Handling (GMDH), Neuro-Fuzzy (NF-GMDH) Support Vector Machine (SVM) was modeled predicted. For purpose, laboratory data published field were used. Parameters convergence angle (with a positive sign) divergence negative sign), relative depth, distance used as input variables. The results showed that all have appropriate performance. However, best performance related to SVM model statistical indicators R2 = 0.998 RMSE 0.008 testing stage. use adaptive fuzzy approach developing GMDH led remarkable increase accuracy so its stage reached 0.985 0.203. It found activation kernel functions development MLPNN is sigmoid radial tangent functions.