monthly runoff forecasting by means of artificial neural networks (anns)

over the last decade or so, artificial neural networks (anns) have become one of the most promising tools formodelling hydrological processes such as rainfall runoff processes. however, the employment of a single model doesnot seem to be an appropriate approach for modelling such a complex, nonlinear, and discontinuous process thatvaries in space and time. for this reason, this study aims at decomposing the process into different clusters based onself-organizing map (som) ann approach, and thereafter modelling different clusters into outputs using separatefeed-forward multilayer perceptron (mlp) and supervised self-organizing map (ssom) ann models. specifically,three different som models have been employed in order to cluster the input patterns into two, three, and fourclusters respectively so that each cluster in each model corresponds to certain physics of the process underinvestigation and thereafter modelling of the input patterns in each cluster into corresponding outputs using feedforwardmlp and ssom ann models. the employed models were developed on two different watersheds, iranianand canadian. it was found that although the idea of decomposition based on som is highly persuasive, our resultsindicate that there is a need for more principled procedure in order to decompose the process. moreover, according tothe modelling results the ssom can be considered as an alternative approach to the feed-forward mlp.