Evaluating the Performance of Decision Tree Model in Estimating the Suspended Sediments of river (A case study on the Basin of Meimeh River)

Understanding and determining the amount of carried sediment by river have been considered by experts because of the importance and the role of sediment transfer in water-shed basins subject , among them is rivers organizing that carry out for erosion and sedimentation control or river-bed stabilization and flood eject. The current study aims at determining the efficiency of decision tree model in estimating suspended sediment of Meimeh river. The data used in the study includes sediment ,water , rain fall , and daily discharges related to the statistic periods from 1967-68 to 2009-2010. After data processing 554 records with accessible statistic discharges and their corresponding sediment were chosen and the obtained results were compared using sediment rating curve. To this aim, statistical criteria of R2 , RMSE, MAT , R and Bias were applied. To investigate, the rain fall effects and daily discharges on precise measuring of sediment by tree model, the data related to the rain fall and daily discharges were added to the model. The results showed that the decision tree model has presented reasonable results for the simulation of the suspended load in the present study station. So that based on criteria RMSE, MAE, r2 and Bias decision tree with less error than the sediment rating curve deposits is estimated. The results did not change much and sediment discharge rate is most correlated with the corresponding discharge of sediment.