Fuzzy Neural Network Model for Hydrologic Flow Routing

Abstract

This paper presents a new approach to river flow prediction using a fuzzy neural network (FNN) model. An FNN combines the learning ability of artificial neural networks with the merits of fuzzy logic. The FNN model is found to be highly adaptive and efficient in investigating nonlinear relationships among different variables. The model displays the stored knowledge in terms of fuzzy linguistic rules, which allows the model decision-making process to be examined and understood in detail. The FNN model is tested on the river Brahmaputra using flow data at various gauged sites in India. The advantages of using the FNN model in river flow prediction are discussed using the case study.