Daily Runoff Forecasting using Artificial Neural Network

Rainfall-Runoff is the most important hydrological variables used in most of the water resources applications. Watershed based planning and management requires thorough understanding hydrological process and accurate estimation of runoff. An Artificial Neural Network (ANN) methodology was employed to forecast daily runoff for the Kadam watershed of G-5 sub-basin of Godavari river basin. On the contrary ANN can be deployed in cases where the available data is limited. The hydrologic variables used were eleven years’ rainfall and runoff data out of which 70% of the data is used for training, 15% for testing and the remaining 15% for validation, Runoff being the desired output for the years 2001 to 2011. Effect of number of layers in the network is also studied. The performance of ANN is evaluated based on the efficiency and the error. The results obtained in the present study have been able to demonstrate that the ANN models are able to provide a good representation of an event-based rainfall-runoff process.