Forecasting monsoon precipitation using artificial neural networks

This paper explores the application of Artificial Intelligent (AI) techniqu es for climate forecast. It presents a study on modelling the monsoon preci pitation forecast by means of Artificial Neural Networks (ANNs). Using the historical data of the total amount of summer rainfall over the Delta Area of Yangtze River in China, three ANNs models have been developed to forecas t the monsoon precipitation in the corresponding area one year, five-year, and ten-year forward respectively. Performances of the models have been val idated using a 'new' data set that has not been exposed to the models durin g the processes of model development and test. The experiment results are p romising, indicating that the proposed ANNs models have good quality in ter ms of the accuracy, stability and generalisation ability.