With the rapid development of society and economy of China, the imbalance between supply and demand is becoming increasingly conspicuous and toward further worsening. Therefore, the forecast of water demand is rather important for the reasonable planning and optimum distribution of water resources. There are various forecast methods for water demand. For a different city or region, a different and proper forecast method should be selected for the forecast. We take Yangquan City of Shanxi as the modeling object and respectively adopt grey forecast GM (1,1) model and RBF neural network model to forecast the water demand of Yangquan City in 1998, 1999 and 2000. For the grey forecast GM (1,1), the maximum relative error is -19.50%, the mean relative error is -13.85%.For the RBF neural network model, the maximum relative error is 2.29% and the mean relative error is 2.01%. The result indicates that the forecast precision of the RBF neural network model is better than that of the grey forecast GM (1,1) model and the forecast period is longer than that of the grey forecast GM (1,1) model. If both compared, the RBF neural network is more applicable for the forecast of the water demand of Yangquan City.
The hydrological system is a system of high nonlinearity. Runoff is the result from the comprehensive action of climate conditions and drainage area underlying surface. The support vector machine (SVM) is a new machine learning method based on the statistical learning theory and it can solve the high nonlinearity, regression, etc in the sample space and also can be used as the hydrological system identification tool. By means of phase space reconstruction, it establishes the SVM model input/output samples; with small sample runoff series, it sets up SVM predicting models. The prediction results show that SVM model has strong generalization ability and very satisfactory prediction results. It effectively solves such problems as small samples, over-learning, high dimension, local minimum, etc. The prediction of the future runoff evolution trend with this model will provide the basis for water regulation and water resources reasonable configuration.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.