A non-linear combination of the forecasts of rainfall-runoff models by thefirst-order Takagi-Sugeno fuzzy system

With a plethora of watershed rainfall-runoff models available for flood for ecasting and more than adequate computing power to operate a number of such models simultaneously, we can now combine the simulation results from the different models to produce the combination forecasts. In this paper, the f irst-order Takagi-Sugeno fuzzy system is introduced and explained as the fo urth combination method (besides other three combination methods tested ear lier, i.e, the simple average method (SAM), the weighted average method (WA M), and the neural network method (NNM)) to combine together the simulation results of five different conceptual rainfall-runoff models in a Bead fore casting study on eleven catchments. The comparison of the forecast simulati on efficiency of the first-order Takagi-Sugeno combination method with the other three combination methods demonstrates that the first-order Takagi-Su geno method is just as efficient as both the WAM and the NNM in enhancing t he flood forecasting accuracy. Considering its simplicity and efficiency, t he first-order Takagi-Sugeno method is recommended for use as the combinati on system for flood forecasting. (C) 2001 Elsevier Science B.V. All rights reserved.