Investigation of factors affecting rural drinking water consumption using intelligent hybrid models

作     者：Alireza Mehrabani Bashar Hamed Nozari Safar Marofi Mohamad Mohamadi Ahad Ahadiiman Alireza Mehrabani Bashar;Hamed Nozari;Safar Marofi;Mohamad Mohamadi;Ahad Ahadiiman

作者机构：Department of Water Science and EngineeringFaculty of AgricultureBu-Ali Sina UniversityHamedan 65178-38695Iran University of KurdistanSanandaj 66177-15175Iran Sustainable Development Office of Hamedan Water and Wastewater CompanyHamedan 65159-14478Iran 

出 版 物：《Water Science and Engineering》 (水科学与水工程（英文版）)

年 卷 期：2023年第16卷第2期

页      面：175-183页

核心收录：

学科分类：081504[工学-水利水电工程] 08[工学] 0815[工学-水利工程] 

基　　金：Water and Wastewater Company of Hamedan Province 

主　　题：ANFIS Water distribution network Simulated annealing algorithm Support vector machine Adaptive neuro-fuzzy inference system 

摘      要：Identifying the factors affecting drinking water consumption is essential to the rational management of water resources and effective environment protection. In this study, the effects of the factors on rural drinking water demand were studied using the adaptive neuro-fuzzy inference system (ANFIS) and hybrid models, such as the ANFIS-genetic algorithm (GA), ANFIS-particle swarm optimization (PSO), and support vector machine (SVM)-simulated annealing (SA). The rural areas of Hamadan Province in Iran were selected for the case study. Five drinking water consumption factors were selected for the assessment according to the literature, data availability, and the characteristics of the study area (such as precipitation, relative humidity, temperature, the number of subscribers, and water price). The results showed that the standard errors of ANFIS, ANFIS-GA, ANFIS-PSO, and SVM-SA were 0.669, 0.619, 0.705, and 0.578, respectively. Therefore, the hybrid model SVM-SA outperformed other models. The sensitivity analysis showed that of the parameters affecting drinking water consumption, the number of subscribers significantly affected the water consumption rate, while the average temperature was the least significant factor. Water price was a factor that could be easily controlled, but it was always one of the least effective parameters due to the low water fee.