Daily Rainfall Prediction Using Artificial Neural Network (ANN) for Monsoon Season

In the present study an attempt has been made to develop ANN models for prediction of daily rainfall for monsoon season at Pantnagar (Uttarakhand), India. Feed-forward neural network with backpropagation algorithm was used for aggregation of daily monsoon rainfall. Sigmoid function was used as transfer function in the hidden and output layers. The monsoon season data (1st June to 30th September) of years 1985–1992 and 1994–2007 were used for training and remaining data (2008–2011) were used for testing of the developed models. The performance of models was evaluated qualitatively by visual observation and quantitatively by using different statistical and hydrological indices viz. mean square error, correlation coefficient, coefficient of efficiency and volumetric error. It was found that the models are capable to predict the rainfall with adequate accuracy.