Fuzzy Nonlinear Function Approximation (FNLLA) Model for River Flow Forecasting

It is well understood that the limitations of hydrological measurement techniques warrants for modeling of hydrological processes in a basin. However, most hydrologic systems are extremely complex and modeling them with the available limited measurements is a difficult task. The basic purpose of a model is to simulate and predict the operation of the system that is unduly complex, and also to predict the effect of changes on this operation. It is well known, of various hydrological processes, the rainfall-runoff process is the most complex hydrologic phenomenon to comprehend due to tremendous spatial and temporal variability of basin characteristics and rainfall patterns, as well as a number of other variables associated in modeling the physical processes (Tokar and Markus, 2000). The transformation from rainfall to basin runoff involves many hydrologic components that are believed to be highly nonlinear, time varying, spatially distributed, and not easily described by simple models. The artificial neural network (ANN) and Fuzzy Inference System (FIS) approaches are becoming increasingly popular in the context rainfall-runoff modeling due to their various advantages. This Chapter discusses an effective integration of these two models in a different manner.