Estimation of suspeded sediment using decision tree method and copmarision the results with rating curve method (Case study: Rivers in Lorestan Province)

Awareness of the amount of suspended sediment yield is an important factor to estimating erosion and also making decisions about the construction of hydraulic structures on rivers. Estimating suspended sediment load of the river with regard to the damage caused by it, is one of the most important and most difficult studies of sediment transport and river engineering. So finding new models that could be useful in this regard has extraordinary significance. The purpose of this study was to estimating suspended sediment using Decision Tree with CART algorithm, and compare the results with different sediment rating curves including: seasonal, monthly, Mean load within discharge classes and linear. To attain this, the sediment discharge and the corresponding water discharge data for ten hydrometric stations of Lorestan province of Iran were used. In next step, different methods of sediment rating curves along with different correction factors, a total of 20 methods were applied to data. Results showed among examined methods, monthly rating curve with MUVE correction factor has minimum mean square error and maximum accuracy index. After applying the appropriate correction factor of sediment rating curves, the results of estimating sediment load by using sediment rating curve, were compared with the results of the Decision Tree. Mean-square error, MAE, P and the correlation coefficient were applied to select more appropriate method. The results showed the suitability of the sediment rating curves in compare with Decision Tree.