Suspended Sediment Analysis Based on Artificial Neural Network in Neka Basin

The neural networks are trained using daily water discharge and suspended sediment discharge data belonging to Neka Catchment in IRAN. In the first part of the study, combinations of daily water discharge and suspended sediment discharge are used as inputs to the artificial neural network. In the second part of the study, the potential of the two different artificial neural networks (ANN) techniques, namely, radial basis function neural network (RBFNN) and multi-layer perceptron (MLP) is compared. The mean squared error is used as comparison criteria. The comparison results reveal that the radial basis function neural network (RBFNN) is found significantly superior to multi-layer perceptron (MLP) in suspended sediment estimation.

کلیدواژه ها:

Artificial neural networks ، Suspended sediment ، Radial Basis Function ، Multi-Layer Perceptron (MLP)