Estimation of Suspended Sediment Yield using Artificial Neural Network Model

Abstract

Estimation of the suspended sediment yield is important for the planning and management of water resources and protection of the environment. Environmental change influences sediment generation and the transport and the consequent sediment load in river. In this study, artificial intelligence-based technique like the artificial neural network (ANN) is proposed for sediment yield estimation in the Godavari river basin, India. The ANN is one of the appropriate data-mining techniques that help model the complex phenomenon of sedimentation. In this study the prediction of the suspended sediment load is done using the ANN techniques by using the water discharge and water level data from 1970 to 2015 as inputs at Polavaram gauge station in Godavari river basin, India. The results demonstrate that the ANN shows a satisfactory performance based on the root mean squared error (RMSE), mean square error (MSE), mean absolute error (MAE) and correlation coefficient (r) error statistics and provided more accurate results.