Abstract. The possibility of predicting average summer-monsoon rainfall over North and South Assam in India has been analyzed in this paper through Artificial Neural Network models. In formulating the Artificial Neural Network based predictive model, three layered networks have been constructed with sigmoid non-linearity. The models under study are different in the number of input layers. After a thorough training and test procedure, neural net with two inputs is found to be the best predictive model both for North and South Assam. Finally, the results are compared with outputs of regression approach. After comparison it is found that for South Assam, Neural Network completely outperforms the regression. But in North Assam regression can be used as an alternative approach to Neural Network.

Full-text: PDF