论文部分内容阅读
A hybrid rainfall-runoff model that integrates artificial neural networks (ANNs) with Xinanjiang (XAJ) model was proposed in this study.We extracted the digital drainage network and sub-catchments from DEM data considering the spatial distribution of rain-gauge stations.And then the semi-distributed XAJ model was established based on DEM.Considering the runoff routing cannot be calculated by the linear superposition of the route runoff from all sub-catchments, artificial neural networks as effective tools in nonlinear mapping are employed to explore nonlinear transformations of the runoff generated from the individual sub-catchments into the total runoff at the entire watershed outlet.The integrated approach has been demonstrated feasible and was applied successfully in the Dapoling watershed, the upper tributary of Huaihe river basin.And the results indicated that the approach of integrating BP ANN with semi-distributed XAJ model may achieve the promising results with acceptable accuracy for flood events simulation and forecast.