Using artificial neural networks for rainfall runoff modeling

Rainfall Runoff modelling is essential for planning and management of water resources. In a catchment, modelling of runoff is a very complex process as it involves a large number of variables affecting the process which makes the process non linear in nature. Various cause and effect models have been used to model the relationship between the rainfall and runoff. This study was conducted in the Barakar river basin, the main basin of Damodar river. In the present study a time series approach combined with Artificial Neural Networks has been utilized to model the runoff of the Giridih watershed under Usri river stream of Barakar river basin in Jharkhand. Artificial Neural Networks which are capable of capturing nonlinearity in the data have been used and the input of the network is the time series data.