Comparison and evaluation of intelligent models for river suspended sediment estimation (case study: Kakareza River, Iran)

Sediment transport constantly influences river and civil structures and the lack of information about its exact amount makes management efforts less effective. Hence, achieving a proper procedure to estimate the sediment load in rivers is important. We used support vector machine model to estimate the sediments of the Kakareza River in Lorestan Province and the results were compared with those obtained by gene expression programming. The parameter of flow discharge for input in different time lags and the parameter of sediment for output during 1992-2012 were considered. Criteria including correlation coefficient, root mean square error and mean absolute error were used to evaluate and also compare the performance of models. With regards to accuracy, the support vector machine model showed the highest correlation coefficient (0.994), minimum root mean square error (0.001 ton/day) and the mean absolute error (0.001 ton/day) which was initiated at verification stage. The results also showed that the support vector machine has great capability to estimate the minimum and maximum values for sediment discharge.