Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

A novel methodology to predict monthly municipal water demand based on weather variables scenario

Zubaidi, S, Hashim, KS, Ethaib, S, Al-Bdairi, N, Al-Bugharbee, H and Gharghan, SK (2022) A novel methodology to predict monthly municipal water demand based on weather variables scenario. Journal of King Saud University, Engineering Sciences, 34 (3). pp. 163-169. ISSN 1018-3639

1-s2.0-S1018363920303111-main.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (932kB) | Preview


This study provides a novel methodology to predict monthly water demand based on several weather variables scenarios by using combined techniques including discrete wavelet transform, principal component analysis, and particle swarm optimisation. To our knowledge, the adopted approach is the first technique to be proposed and applied in the water demand prediction. Compared to traditional methods, the developed methodology is superior in terms of predictive accuracy and runtime. Water consumption coupled with weather variables of the Melbourne City, from 2006 to 2015, were obtained from the South East Water retail company. The results showed that using data pre-processing techniques can significantly improve the quality of data and to select the best model input scenario. Additionally, it was noticed that the particle swarm optimisation algorithm accurately predicts the constants of the suggested model. Furthermore, the results confirmed that the proposed methodology accurately estimated the monthly data of municipal water demand based on a range of statistical criteria.

Item Type: Article
Subjects: T Technology > TD Environmental technology. Sanitary engineering
Divisions: Civil Engineering (merged with Built Env 10 Aug 20)
Publisher: Elsevier
Date Deposited: 23 Sep 2020 11:16
Last Modified: 22 Aug 2022 11:00
DOI or ID number: 10.1016/j.jksues.2020.09.011
URI: https://researchonline.ljmu.ac.uk/id/eprint/13710
View Item View Item