A Wavelet Support Vector Machine Combination Model for Daily Suspended Sediment Forecasting

Abstract

Abstract In this study, wavelet support vector machine (WSWM) model is proposed for daily suspended sediment (SS) prediction. The WSVM model is achieved by combination of two methods; discrete wavelet analysis and support vector machine (SVM). The developed model was compared with single SVM. Daily discharge (Q) and SS data from Yadkin River at Yadkin College, NC station in the USA were used. In order to evaluate the model, the root mean square error (RMSE), correlation coefficient (R) and coefficient of determination (R2) were used. Results demonstrated that WSVM with RMSE =3294.6, R =0.9211 and R2 =0.838 were more desired than the other model with RMSE =6719.7, R=0.589 and R2=0.327. Comparisons of these models revealed that, mean of error and error standard deviation for WSVM model were about 66% and 50% less than SVM model in test period.