Simulation of Seasonal precipitation using ANN and ARIMA Models:

Accurate rainfall prediction is of great interest for water management and flood control. In reality, physical processes influencing the occurrence of rainfall are highly complex, uncertain and nonlinear. In this paper, we present tools for modeling and predicting the behavioral pattern in rainfall phenomena based on past observations. The aim of this paper is to predict the seasonal rainfall of (Iran) khozestan using artificial neural network (ANN) and autoregressive integrated moving average (ARIMA) models. In order to evaluate the prediction efficiency, we made use of 33 years of seasonal rainfall data from year 1976 to 2008 of Khozestan Province (Iran). The models were trained with 28 years of seasonal rainfall data. The ANN and the ARIMA approaches are applied to the data to derive the weights and the regression coefficients respectively. The performance of the model was evaluated by using remaining 5 years of data. The study reveals that ANN model can be used as an appropriate forecasting tool to predict the rainfall, which out performs the ARIMA model.

ARIMA model,Neural Networks,Rainfall forecast, Time series