network and ARIMA techniques

Climate and rainfall are highly non-linear and complicated phenomena, which require sophisticated computer modelling and simulation for accurate prediction. An artificial intelligence technology allows knowledge processing and can be used.as forecasting tool. For example, the application of Artificial Neural Networks (ANN), to predict the behaviors of nonlinear systems has become an attractive alternative to traditional statistical methods. In this paper, we present tools for modeling and predicting the behavioral pattern in rainfall phenomena based on past observations. The paper introduces two fundamentally different approaches for designing a model, the statistical method based on autoregressive integrated moving average (ARIMA) and the emerging computationally powerful techniques based on ANN. In order to evaluate the prediction efficiency, we made use of 104 years of mean annual rainfall data from year 1901 to 2003 of Hyderabad region (India). The models were trained with 93 years of mean annual 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 10 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