Monthly water demand forecasting by adaptive neuro-fuzzy inference system approach

Abstract

In this study, an adaptive Neuro-Fuzzy inference system (ANFIS) is used to forecast monthly water use from several socio-economic and climatic factors, which affect water use. Totally 108 data sets are collected and data sets are 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 ANFIS models in training and testing sets are compared with the observations and the best fit model forecasting model is identified. For this purpose, some criteria of performance evaluation such as, Root Mean Square Error (RMSE), efficiency (E) and correlation coefficient (CORR) are calculated for all models. Then, the best fit models are also trained and tested by Multiple Regression (MR). The results of models are compared to get more reliable comparison. The results indicated that ANFIS can be applied successfully for monthly water demand forecasting.