Bedload computation in rivers

Sediment in streams occurs as bedload when particles move by rolling, sliding, and saltation at or near the streambed, or as suspended load when particles are maintained in the water by turbulence. In this study, bedload sediment transport in rivers is modeled using artificial neural networks (ANN). Bedload sediment in rivers is the function of river morphological hydrometrics and physiological factors. In the literature for estimating bedload sediment transport, a lot of methods have been improved in this hydraulic state. All of these methods well work only for limited discharge and material data. It is difficult to know the transport mode of bedload material. Bedload sediment measurement also is so difficult. Recently, among the soft computational methods Artificial Neural Networks (ANN) approach have been used extensively in hydrology and hydraulic engineering. ANN and some regression methods have been used for estimating bedload sediment in rivers. In this study, these methods have been used to estimate bedload sediment for 27 pieces Rivers and compared to each other. The results of ANN models have shown that ANN can be applied successfully and provides high accuracy and reliability for bedload sediment prediction.