Prediction of the Discharge Coefficient in Compound Broad-Crested-Weir Gate by Supervised Data Mining Techniques

The current investigation evaluated the discharge coefficient of a combined compound rectangular broad-crested-weir (BCW) gate (Cdt) using computational fluid dynamics (CFD) modeling approach and soft computing models. First, CFD was applied to experimental data 61 BCW gates were numerically simulated by resolving Reynolds-averaged Navier–Stokes equations stress turbulence Then, six data-driven procedures, including M5P tree, random forest (RF), support vector machine (SVM), Gaussian process (GP), multimode ANN multilinear regression (MLR) used for estimating weir gates. results showed superlative accuracy SVM model compared M5P, RF, GP MLR in predicting coefficient. sensitivity revealed h1/H as most effective parameter Cdt, followed d/p, b/B0, B/B0 z/p. reduced root mean square error (RMSE) GP, 37, 13, 6.9, 6.5 32%, respectively. graphical inspection indicated suitable Cdt with minimum RMSE maximum correlation.