Generalized regression neural networks for municipal water consumption prediction

摘要

In this study, the applicability of generalized regression neural networks (GRNN) is investigated to predict the monthly use of water from several socio-economic and climatic factors that affect water use. A dataset including a total of 108 data records is divided into two subsets: training and testing. The models consisting of the combination of the independent variables are constructed and the best-fit input structure is investigated. The performance of GRNN models in training and testing sets are compared with the observations and the best-fit prediction model is identified. For this purpose, several criteria such as normalized root mean square error, efficiency (E) and correlation coefficient (CORR) are calculated. Then, the best-fit model is also trained and tested by multiple linear regression in order to get a more reliable evaluation. The results indicated that the GRNN can be applied successfully for monthly water consumption prediction.