Author(s): Minh Duc Bui; Keivan Kaveh; Peter Rutschmann
Linked Author(s): Peter Rutschmann
Keywords: Artificial Neural Network; Sediment transport; Hydromorphological modeling
Abstract: One of the weakest points of hydromorphological models is to use empirical formulae for calculating sediment transport rates, which are of limited generality. In many cases, unreasonable morphological changes are predicted and the results of the different formulae often vary strongly. The reasons are assumed in the complexity of the interaction between flow and sediment transport and in limitations of the nonlinear regression applied in these methods. In contrast to most traditional empirical methods, which need prior knowledge about the nature of the relationships among the data, the methods of artificial neural networks (ANN) learn from data examples presented to them in order to capture the subtle functional relationships among the data even if the underlying relationships are unknown or the physical meaning is difficult to explain. Additionally ANN has proven a high tolerance against data sample errors. These attributes make the utilization of ANN for sediment transport predictions very promising. In this paper an optimal ANN model has been selected, which is integrated into a hydromorphological model system and could adequately predict the morphological changes in a straight alluvial channel under steady flow discharge. For this purpose the capability and accu racy of numerous ANN models designed with different structures and trained with different learning rules has been analyzed. To evaluate the prediction qualities of the designed networks, a comparative study has been carried out for these models by evaluating several statistical parameters that describe the errors associated with the model in terms of statistical measures of goodness-of-fit between the estimated bed change and analytical approximation.