Computational Rainfall Forecasting Models

Rainfall forecasting has great significance in planning and understanding the rainfall variability that helps the agricultural management in decision-making process. Forecasting Rainfall is a major scientific issue in the field of meteorology. Many researchers have attempted to establish linear models to predict the rainfall, but with the discovery of nonlinearity in the nature of weather data, the focus has shifted towards the nonlinear prediction of rainfall. The neural networks can automatically develop a forecasting model through a simple process of the historic data. Such training process enables the neural system to capture the complex and non-linear relationships that are not easily analyzed by using conventional methods. Neural networks are an emerging and challenging computational technology and they offer a new avenue to explore the dynamics of a variety of hydrological applications. An Artificial Neural Network (ANN) is a massively parallel-distributed information processing system with highly flexible configuration and therefore has excellent nonlinearity capturing ability. Artificial Neural Networks with one hidden layer are commonly used in hydrologic modeling. In this research article, the traditional data pre-processing technique, Moving Average (MA) was coupled with Artificial Neural Network as MA – ANN model to improve the prediction of rainfall in Tamilnadu. The experimental results show that the MA – ANN hybrid model is a better tool than the Moving Average and ANN models, if they applied separately.