GEP to predict characteristics of a hydraulic jump over a rough bed

Abstract

This study presents new application of Gene Expression Programming (GEP) to predict characteristics of a hydraulic jump over a rough bed. Performances of the GEP model compared with traditional equations and common artificial intelligence techniques (ANN and SVR). Published data were used from the literature for the hydraulic jump characteristics over a rough bed. The prediction uncertainties of all of the models are quantified and compared. Results of this study showed that the GEP model is able to predict the characteristics of a hydraulic jump over a rough bed with acceptable precision (RMSE = 0.29, R ² = 0.975 for sequent depth ratio $\left( {\frac{{y_2 }} {{y_1 }}} \right)$ for test data and RMSE = 4.804, R ² = 0.8 for hydraulic jump length ratio $\frac{{L_j }} {{y_1 }}$ for test data). Comparison of GEP and traditional equations demonstrate that GEP models can represent more accurate equations for practical applications (traditional equations performance RMSE = 0.338, R ² = 0.967 for sequent depth ratio and RMSE = 5.72, R ² = 0.712 for jump length ratio). Comparison of common artificial intelligence techniques (ANN and SVR) indicated that the performance of these models is slightly better than GEP model but application of GEP model due to derivation of explicit equations is easier for practical purposes.