Forecasting River Flow in the USA: A Comparison between Auto-Regression and Neural Network Non-Parametric Models

Abstract: This paper provides a solution to the forecasting problem of the river flow for two well known rivers in USA. They are the Black Water River and the Gila River. Feed-forward Neural Network and the Linear Auto-Regressive (AR) models were used to model the flow dynamics. The performance of the two proposed model were compared in both training and testing cases. The model performances were computed in each case. NN model showerd a better modeling capability compared to the AR model