Correct estimation of discharge and sediment volume being carried by a river is very important for many water resources projects. Conventional rating curves, however, are not able to provide sufficiently accurate results. This study aims to investigate the potential of employing a radial basis function (RBF) type neural network for modeling stage-discharge-sediment relationships at gauging stations. The ANN approach is used to establish an integrated stage-discharge- sediment concentration relation for two sites on the Mississippi River. Based on the comparison of the results for two gauging sites, it is shown that the RBF results are much closer to the observed values than the conventional technique and multi-layer feed-forward ANN. The results are promising and suggest that the approach is highly viable.
展开▼
