MONTHLY RAINFALL QUANTITIES FORCASTING USING NARX NETWORK

Abstract

An accurate precipitation forecast can reflect positive impact in several areas. It provides helpful data in hydrological projects designs, such as constructing dams, reservoirs, rainfall networks, as well as takes some precautionary measures that can overcome the flooding problems. This paper proposes a monthly quantitative precipitation forecasting model that covers the total land area of Iraq. The model is based on the use of Nonlinear AutoRegressive with eXogenous input neural network (NARX). This type of network is considered as one of the most important dynamic networks that can deal with time series data. It is a type of recurrent networks with feedback connections between its layers and a tapped delay lines. The data used to train and test the network are real data obtained by NASA GES DISC which represent monthly quantitative precipitation of more than 1350 site uniformly distributed to cover the land of Iraq for a historical period of ten years. The designed forecasting network model showed good performance, in which the total calculated MSE for the testing data set is about (2.8×10-3), and the its correlation coefficient R is about (0.95). The correlation of the predicted error with time has been checked also; it showed that almost all the autocorrelation function values are fall within the bound of the confidence interval.