Performance Evaluation of M5 Tree Model and Support Vector Regression Methods in Suspended Sediment Load Modeling

Sediment transport has always affected the river and civil structures and the lack of knowledge about its exact amount causes high damages. Therefore, it is very important to properly estimate the sediment load in rivers in terms of sediment, erosion and flood control. This study used two new data mining methods including M5 model tree and support vector regression comparing with the classic method of sediment rating curve to estimate the suspended sediment load in Aharchay River. To assess the performance of the used methods, three criteria including the correlation coefficient, root mean square error and mean absolute error were used. Analyzing the sensitivity of models to the input variables, it was found that the variable of flow discharge in the current month had the greatest effect on the amount of suspended sediment load. The results showed the high accuracy of new data mining methods in comparison with the sediment rating curve. Although, both considered data mining methods had more accuracy and less error compared to the conventional sediment rating curve, given the simple understandable linear relationships provided by the M5 model tree, this method is recommended for similar cases.