Up to journal
for Research & Developement
Journal of Materials Science: Materials in Electronics
Impact Factor
0/000
Available
2000 - 2020
Volumes
15
Issues
54
Articles
865
Open Access
532


Iranian Water Researches Journal
Evaluation of Wavelet Regression and Neuro-Fuzzy Models for Estimating Urban Water Consumption (Case Study: Kerman City)


 submission: 14/08/2019 | acception: 23/12/2019 | publication: 07/09/2020

DOI 

Authors
Masoud Reza Hessami Kermani1*, Reza Valiparast Farkhani2

1-Shahid Bahonar University of Kerman،hessami@uk.ac.ir

2-Shahid Bahonar University of Kerman،r.valiparast@gmail.com



0 Downloads

Abstract

Predicting water consumption in urban areas is of key importance for water supply management. Predictive modeling for water consumption can be used for both planning water supply and expanding infrastructure for new developments and to improve the control and operation of the water resources systems. In this research, the performance of Multi Linear Regression (MLR), Adaptive Neuro-Fuzzy Inference System (ANFIS), Wavelet MLR (WR) and Wavelet ANFIS (WANFIS) were evaluated in predicting water demand in Kerman City. For this purpose, weekly time series of water consumption and meteorological parameters including weekly time series of maximum temperature and weekly time series of total precipitation were used to predict weekly water consumption based on ۱۲ years data from ۲۰۰۶ to ۲۰۱۷. Data from ۲۰۰۶ to ۲۰۱۴ (۴۶۹ weeks) were considered as training and data from ۲۰۱۵ to ۲۰۱۷ (۱۵۷ weeks) as a simulation for modeling. In WR and WANFIS models (wavelet-based models), the weekly time series of water consumption, maximum temperature and precipitation are decomposed by discrete wavelet transformation to sub-series of approximations and details at various levels which are used as inputs of wavelet based models. In this comparative study, the performance of all predictive models was evaluated by statistical indices including coefficient of correlation (R), coefficient of determination (R۲), root mean square error (RMSE) and mean absolute error (MAE). The obtained results from this study suggest that the WR model (R۲ = ۰.۹۲) and the WANFIS (R۲ = ۰.۹۴) have much higher performance compared to the MLR and ANFIS models.




Keywords

Discrete Wavelet Transformation  Urban Water demand  Prediction  Linear Regression  Neuro Fuzzy 



Download fulltext PDF


It's not open access



Citation





References





Announcements  

  •  No announces available
Indexes  

 


ISC
magiran
Civilica
SID
nali