Suspended Sediment Estimation and Forecasting using Artificial Neural Networks


Abstract: The methods available in the literature for sediment concentration estimation are complicated and time consuming and necessitate cumbersome parameter estimation procedures. In this study, artificial neural networks (ANNs) are used to forecast and estimate sediment concentration values. The forecasting results obtained using previously observed sediment values were close to the real ones. The sediment concentration estimation, on the other hand, using only observed river flow values and the previous sediment value in a nearby river as input, provided realistic approximations in terms of mean squared error (MSE) and total sediment amount. The ANN estimates are compared also with corresponding classical regression ones and found to be significantly superior.

Keywords: Suspended sediment, Forecasting, River flow

Full Text: PDF