Assessment the Performance of Support Vector Machine and Artificial Neural Network Systems for Regional Flood Frequency Analysis (A Case Study: Namak Lake Watershed)

Flood discharge estimation with different return periods is one of important factors for water structures design and installation. On the other hand, a lot of rivers existing in Iran watersheds have no complete and accurate hydrometric data. In these cases, one of the suitable solutions to estimate peak discharges with different return periods is the regional flood analysis. In this research, 55 hydrometric stations were used. For this purpose, at first, peak discharges in different return periods were estimated using the EasyFit software. Then, the effective variables on the peak discharges were collected and the input variables of the models were selected by using gamma test with the help of the WinGamma software. Finally, data modeling was performed using the support vector machine, artificial neural networks and nonlinear multivariate regression techniques. Quantitative and qualitative assessment of the results using various indices including Nash-Sutcliffe Efficiency Coefficient (NSC) showed that SVM modeling method had the most accuracy in comparison to the other two modeling methods to predict the peak discharges in the Namak Lake Watershed.