River flow forecasting and estimation using different artificial neural network techniques

Abstract

This paper demonstrates the application of different artificial neural network (ANN) techniques for the estimation of monthly streamflows. In the first part of the study, three different ANN techniques, namely, feed forward neural networks (FFNN), generalized regression neural networks (GRNN) and radial basis ANN (RBF) are used in one-month ahead streamflow forecasting and the results are evaluated. Monthly flow data from two stations, Gerdelli Station on Canakdere River and Isakoy Station on Goksudere River, in the Eastern Black Sea region of Turkey are used in the study. Based on the results, the GRNN was found to be better than the other ANN techniques in monthly flow forecasting. The effect of periodicity on the model's forecasting performance was also investigated. In the second part of the study, the performance of the ANN techniques was tested for river flow estimation using data from the nearby river.