Archana Chowdhary and R K Shrivastava
Keywords: Artificial neural network, radial basis function, regression analysis.
Abstract: The research described in this article investigates the utility of Artificial Neural Networks (ANNs) for predicting the daily river discharge. The work explores the capabilities of ANNs and compares the performance of Feed Forward Neural Network (FFNNS) and Radial Basis Function (RBF) network. Perceived strengths of ANNS are the capability for representing complex, non linear relationships as well as being able to model interaction effects. The application of the ANN approach is to a portion of Seonath River in Chhattisgarh and forecasting was conducted using daily records. ANN technique shows an enhancement of prediction capabilities & reduces the over fitting problem of neural networks. The results show that the ANN technique can be used to extract information from the data & to describe the non-linearity of river discharge.
[View Complete Article]