An areal rainfall forecasting method based on fuzzy optimum neural network and Geography Information System

Abstract

An areal rainfall is important basic data in a real time flood warning system. Good areal rainfall calculation means we can forecast flood more accurately and in time. Here, we propose an areal rainfall forecasting methodology integrated fuzzy optimized neural network with Geography Information System (GIS) methods. GIS has an advantage of processing spatial information. Using many models and methods provided by CIS software, we obtain more accurate areal rainfalls of a catchment. Then, these outputs of the CIS software are taken as the expected output of the fuzzy optimized neural network, and the network is trained to find the mapping between the areal rainfalls and observed rainfalls of all gauge stations. Finally, with the mapping, new observed values are taken as input of the network, and we can obtain the catchment areal rainfall in time.