This work presents an innovative yet simple idea to very effectively interpolate the rainfall values at the locations of no observations using Artificial Neural Network (ANN). The method has been demonstrated in the Tamaravarani basin of Tamil Nadu where rain gauge information for 18 rain gauge stations is available. With the help of land use map of the basin and also the distance proximity of rain gauge stations to each other of the neighbouring stations, the most appropriate variables are designed and used for estimating rainfall in the unknown stations. The results from ANN model are compared with traditional Kriging approach. The results show that the proposed approach is very promising as the results are found to be far better than Kriging approach, which is very time consuming.
