Author(s): A. J. Abebe; R. K. Price
Linked Author(s):
Keywords: Complementary model; Neural networks; Average mutual information
Abstract: This article presents an approach that uses latest observations and errors in runoff forecasts from a conceptual watershed model with a neural network model to increase the quality of the runoff forecasts. The two complementary models are used in such a way that errors of a conceptual model are forecasted by a neural network model so that runoff forecasts can be improved as new observations come in. The approach is applied to a conceptual rainfall-runoff model of the Sieve basin in Italy. The results show that there is a substantial improvement in the accuracy of the forecasts when complementary models are applied on top of the conceptual forecast model compared to the results of the conceptual model alone.
Year: 2002