Zubaidi, S, Ortega Martorell, S, Kot, P, Al Khaddar, RM, Abdellatif, M, Gharghan,
S, Ahmed, M and Hashim, KS
A Method for Predicting Long-term Municipal Water Demands Under Climate
Change
http://researchonline.ljmu.ac.uk/id/eprint/12067/
Article
LJMU has developed LJMU Research Online for users to access the research output of the
University more effectively. Copyright © and Moral Rights for the papers on this site are retained by
the individual authors and/or other copyright owners. Users may download and/or print one copy of
any article(s) in LJMU Research Online to facilitate their private study or for non-commercial research.
You may not engage in further distribution of the material or use it for any profit-making activities or
any commercial gain.
The version presented here may differ from the published version or from the version of the record.
Please see the repository URL above for details on accessing the published version and note that
access may require a subscription.
For more information please contact researchonline@ljmu.ac.uk
http://researchonline.ljmu.ac.uk/
Citation (please note it is advisable to refer to the publisher’s version if you
intend to cite from this work)
Zubaidi, S, Ortega Martorell, S, Kot, P, Al Khaddar, RM, Abdellatif, M,
Gharghan, S, Ahmed, M and Hashim, KS (2020) A Method for Predicting
Long-term Municipal Water Demands Under Climate Change. Water
Resources Management, 34. pp. 1265-1279. ISSN 0920-4741
LJMU Research Online
1
A Method for Predicting Long-term Municipal Water Demands
1
Under Climate Change
2
Salah L. Zubaidi
a
, Sandra Ortega-Martorell
b
, Patryk Kot
c
, Rafid M. Alkhaddar
c
,
3
Mawada Abdellatif
c
, Sadik K. Gharghan
d
, Maytham S. Ahmed
e
, Khalid Hashim
c
4
a
Department of Civil Engineering, University of Wasit, Wasit, Iraq
5
b
Department of Applied Mathematics, Liverpool John Moores University, Liverpool, UK
6
c
Department of Civil Engineering, Liverpool John Moores University, Liverpool, UK
7
d
Department of Medical Instrumentation Techniques Engineering, Electrical Engineering
8
Technical College Middle Technical University (MTU), Al Doura, Baghdad 10022, Iraq.
9
e
General Directorate of Electrical Energy Production-Basrah, Ministry of Electricity, Basrah
10
61001, Iraq
11
Abstract
12
The accurate forecast of water demand is challenging for water utilities, specifically when
13
considering the implications of climate change. As such, this is the first study that focuses on
14
finding associations between monthly climate factors and municipal water consumption, using
15
baseline data collected between 1980 and 2010. The aim of the study was to investigate the
16
reliability and capability of a combination of techniques, including Singular Spectrum Analysis
17
(SSA) and Artificial Neural Networks (ANNs), to accurately predict long-term, monthly water
18
demands. The principal findings of this research are as follows: a) SSA is a powerful method
19
when applied to remove the impact of socio-economic variables and noise, and to determine a
20
2
stochastic signal for long-term water consumption time series; b) ANN performed better when
21
optimised using the Lightning Search Algorithm (LSA-ANN) compared with other approaches
22
used in previous studies, i.e. hybrid Particle Swarm Optimisation (PSO-ANN) and
23
Gravitational Search Algorithm (GSA-ANN); c) the proposed LSA-ANN methodology was
24
able to produce a highly accurate and robust model of water demand, achieving a correlation
25
coefficient of 0.96 between observed and predicted water demand when using a validation
26
dataset, and a very small root mean square error of 0.025.
27
Keywords
28
Artificial Neural Network, climate change, Lightning Search Algorithm, Singular Spectrum
29
Analysis and water prediction
30
1 Introduction
31
Nowadays, many countries face numerous concurrent challenges in the management of, and
32
access to, potable water. The authors in UNDP (2013), Ferguson et al. (2013) and Hossain et
33
al. (2018), among many others, have identified the impact of global warming and related
34
climate change, such as an increased frequency and severity of drought and flooding as one of
35
the most significant impacts on our aquatic environment. As a result, considerable pressure is
36
being placed on water infrastructures. It has also been reported that global warming generates
37
considerable uncertainties on the long-term planning projections of water demand in urban
38
areas (Urich and Rauch (2014). These uncertainties can lead to significant problems in other
39
related areas such as supply, operation and cost, which traditional planning methods cannot
40
solve.
41
3
The aforementioned increasing concerns about the impact of climate change have led to the
42
need to plan and manage water in advanced, to guarantee meeting municipal water demand to
43
the satisfaction of the consumer (Zhang et al., 2019). This type of strategic planning, as
44
conveyed by Cutore et al. (2008), means planning now for an uncertain future. However, since
45
conventional models are no longer adequate to predict urban water consumption under the
46
pressure of climate change in the future, several researchers have been investigating and
47
improving various mathematical models to develop techniques to better estimate essential
48
parameters and better model forecast uncertainties (Marlow et al., 2013).
49
The accurate water demand prediction can play an important role in optimising the design,
50
operation and management of municipal water supply infrastructures (Pacchin et al., 2019).
51
This can also minimise the uncertainty that results from a rapid increase in water demand due
52
to the impact of climatic factors (Bougadis et al., 2005). Previous studies such as Gato et al.
53
(2007), Tian et al. (2016) and Brentan et al. (2017), have established that water consumption
54
is affected by weather variables throughout the year. In this area of research, Artificial Neural
55
Networks (ANNs) have been developed and compared with various traditional statistical
56
models, the results indicating that ANN techniques offer better forecasting models such as
57
those in Sebri (2013), Behboudian et al. (2014), Mouatadid and Adamowski (2016) and Guo
58
et al. (2018).
59
The need for increased reliability, capability and accuracy regarding data-driven techniques
60
has motivated the development of hybrid models, which would integrate two or more
61
techniques with the aim of outperforming the capability of single models. In these hybrid
62
approaches, typically one of the techniques would be deemed as the primary one, and the others
63
would work as pre-processing or post-processing methods (Araghinejad, 2014). Recently,
64
4
several hybrid techniques have been applied to predict water demand, for example Anele et al.
65
(2017), Altunkaynak and Nigussie (2018) and Seo et al. (2018).
66
Although previous studies have recognised the impact of weather factors, research has yet to
67
thoroughly and systematically investigate the effect of these factors in terms of using adequate
68
data pre-processing to remove the impact of socio-economic factors, which are insensitive to
69
climate change, and to apply a powerful and effective forecasting technique on a systematic
70
basis, instead of a commonly used trial and error approach. As such, studies to date have not
71
been able to detect to what extent climate factors have driven municipal water demands, the
72
debate continuing about the best strategies for the management of municipal water demand,
73
under the impact of climate change.
74
Previous research on the influence of climate change on municipal water demand using a
75
recommended baseline period has not been properly conducted. These studies have suffered
76
from inadequate sample size, the mixing of evidence for climate change impact with
77
socioeconomic factors and several conceptual and methodological weaknesses.
78
Various optimisation approaches can be adopted to handle a range of issues for different
79
application domains. The goal of the optimisation algorithm is to determine the best parameter
80
values of the system under different conditions (Ahmed et al., 2016). Recently, the gravitational
81
search algorithm (GSA) proposed by Rashedi et al. (2009) has been applied to tackle various
82
optimisation issues such as unconstrained global optimisation problems (García-Ródenas et al.,
83
2019), hydrology (Karami et al., 2019) and in the geothermal power plant optimisation
84
(Özkaraca and Keçebaş, 2019). Particle Swarm Optimisation (PSO) algorithm has been used
85
in different fields such as sediment yield forecasting (Meshram et al., 2019), operation rule
86
