Author(s): Sungwon Kim

Linked Author(s):

Keywords: Radial Basis Function; K-Means clustering algorithm; Gaussian Kernel Function; Centers; Widths; Flood Forecasting

Abstract: In this study, Radial Basis Function (RBF) Neural Networks Model, a kind of Hybrid Neural Networks, was applied to hydrological forecasting in small watershed. RBF Neural Networks Model has four kinds of parameters in it and consists of supervised and unsupervised training patterns. And, Gaussian Kernel Function (GFK) was used among many kinds of Radial Basis Functions (RBFs). K-Means clustering algorithm was applied to optimize centers and widths of GFK parameters. The parameters of RBF Neural Networks Model such as centers, widths, weights, and biases were determined by the training procedures of RBF Neural Networks Model. And, with these parameters, the validation procedures of RBF Neural Networks Model were carried out. RBF Neural Networks Model was applied to Wi-Stream basin that is one of the IHP Representative basins in South Korea. 10 storm cases were selected for training and validation of RBF Neural Networks Model. The results of RBF Neural Networks Model were compared with those of Elman BackPropagation (EBP) Neural Networks Model. EBP Neural Networks Model is composed of One Step Secant BackPropagation (OSSBP) and Resilient BackPropagation (RBP) algorithms. RBF Neural Networks Model shows better results than EBP Neural Networks Model. RBF Neural Networks Model spent less time for the training of model and can be easily used by the hydrologists with little background knowledge of RBF Neural Networks Model.

DOI:

Year: 2005