applying artificial neural network algorithms to estimate suspended sediment load (case study: kasilian catchment, iran)

estimate of sediment load is required in a wide spectrum of water resources engineering problems. the nonlinear nature of suspended sediment load series necessitates the utilization of nonlinear methods to simulate the suspended sediment load. in this study artificial neural networks (anns) are employed to estimate daily suspended sediment load. two different ann algorithms, multi layer perceptron (mlp) and radial basis functions (rbf) were used for this purpose. the neural networks are trained using water discharge and suspended sediment discharge data from the kasilian catchment, which is located in north of iran. in this research, daily water discharge and suspended sediment load data was collected for 41 years (1964-2005) period which includes 509 experimental data in total. from this set of data, 70% were used in the training phase, 20% for testing and remaining 10% were used in validation phase. the results showed that the rbf algorithm provided slightly better results than the mlp algorithm to estimate suspended sediment load.