Evaluation of the least square support vector machines (LS-SVM) to predict longitudinal dispersion coefficient

Abstract

Abstract In this study, the least square support vector machines (LS-SVM) method was used to predict the longitudinal dispersion coefficient (DL) in natural streams in comparison with the empirical equations in various datasets. To do this, three datasets of field data including hydraulic and geometrical characteristics of different rivers, with various statistical characteristics, were applied to evaluate the performance of LS-SVM and 15 empirical equations. The LS-SVM was evaluated and compared with developed empirical equations using statistical indices of root mean square error (RMSE), standard error (SE), mean bias error (MBE), discrepancy ratio (DR), Nash-Sutcliffe efficiency (NSE) and coefficient of determination (R2). The results demonstrated that LS-SVM method has a high capability to predict the DL in different datasets with RMSE = 58–82 m2 s−1, SE = 24–39 m2 s−1, MBE = −1.95–2.6 m2 s−1, DR = 0.08–0.13, R2 = 0.76–0.88, and NSE = 0.75–0.87 as compared with previous empirical equations. It can be concluded that the proposed LS-SVM model can be successfully applied to predict the DL for a wide range of river characteristics.