This study proposes a novel hybrid model for short-term urban water demand (UWD) forecasting in the Punjab region of India, coupling support vector regression (SVR) with wavelet transform (WT) and boosting ensemble techniques. The WTs are applied as a preprocessing step to decompose the water demand time series into multiple frequency components capturing both long-term trends and short-term variations. By integrating wavelet analysis with boosting ensemble, the accuracy and robustness of the SVR models were significantly improved. The model’s performance was assessed for lead times of 1, 3, and 5 days ahead using the coefficient of determination (R2), root mean square error, and mean absolute error. Results showed that boosting consistently enhanced the correlation between observed and predicted UWD values. Among the models evaluated, the wavelet-boosting SVR outperformed others, providing the most accurate forecasts. This highlights the potential of wavelet-based boosting techniques for improving UWD prediction and aiding in efficient water resource management.
Get full access to this article
View all access options for this article.
References
1.
AdamowskiJF. Peak daily water demand forecast modelling using artificial neural networks. J Water Resour Plann Manage, 2008; 134(2):119–128; doi: 10.1061/(ASCE)0733-9496(2008)134:2(119)
2.
Al-ZahraniMA, Abo-MonasarA. Urban residential water demand prediction based on artificial neural networks and time series models. Water Resour Manage, 2015; 29(10):3651–3662; doi: 10.1007/s11269-015-1021-z
3.
AminghafariM, PoggiJM. Forecasting time series using wavelets. Int J Wavelets Multiresolut Inf Process, 2007; 05(05):709–724; doi: 10.1142/S0219691307002002
4.
AntunesA, Andrade-CamposA, Sardinha-LourençoA, et al.Short-term water demand forecasting using machine learning techniques. J Hydroinform, 2018; 20(6):1343–1366; doi: 10.2166/hydro.2018.163
5.
BabelMS, ShindeVR. Identifying prominent explanatory variables for water demand prediction using artificial neural networks: A case study of Bangkok. Water Resour Manage, 2011; 25(6):1653–1676; doi: 10.1007/s11269-010-9766-x
6.
BaiY, WangP, LiC, et al.Dynamic forecast of daily urban water consumption using a variable-structure support vector regression model. J Water Resour Plann Manage, 2015; 141(3):1; doi: 10.1061/(ASCE)WR.1943-5452.0000457
7.
BataM, CarriveauR, TingDS. Short-term water demand forecasting using hybrid supervised and unsupervised machine learning model. Smart Water, 2020; 5(1); doi: 10.1186/s40713-020-00020-y
8.
BelaynehA, AdamowskiJ, KhalilB, et al.Coupling machine learning methods with wavelet transforms and the bootstrap and boosting ensemble approaches for drought prediction. Atmos Res, 2016; 172–173:37–47; doi: 10.1016/j.atmosres.2015.12.017
9.
BelaynehA, AdamowskiJ. Standard precipitation index drought forecasting using neural networks, wavelet neural networks, and support vector regression. Appl Comput Intell Soft Comput, 2012; 2012:1–13; doi: 10.1155/2012/794061
10.
BougadisJ, AdamowskiK, DiduchR. Short-term municipal water demand forecasting. Hydrol Process, 2005; 19(1):137–148; doi: 10.1002/hyp.5763
11.
CandelieriA, GiordaniI, ArchettiF, et al.Tuning hyperparameters of a SVM-based water demand forecasting system through parallel global optimization. Comput Oper Res, 2019; 106:202–209; doi: 10.1016/j.cor.2018.01.013
12.
Central Public Health and Environmental Engineering Organization (CPHEEO). Manual on water supply and treatment. Ministry of Urban Development, Government of India: New Delhi; 1999.
13.
ChevalierRF, HoogenboomG, McClendonRW, et al.Support vector regression with reduced training sets for air temperature prediction: A comparison with artificial neural networks. Neural Comput & Applic, 2011; 20(1):151–159; doi: 10.1007/s00521-010-0363-y
14.
DaiL, JiD, DaiH, et al.Spatiotemporal variability in the effect of the water supply from the Three gorges reservoir on dongting lake during the dry season. Environ Eng Sci, 2020; 37(12):815–825; doi: 10.1089/ees.2020.0135
15.
DawsonCW, AbrahartRJ, SeeLM. HydroTest: A web-based toolbox of evaluation metrics for the standardised assessment of hydrological forecasts. Environ Model Softw, 2007; 22(7):1034–1052; doi: 10.1016/j.envsoft.2006.06.008
16.
DonkorEA, MazzuchiTA, SoyerR, et al.Urban water demand forecasting: Review of methods and models. J Water Resour Plann Manage, 2014; 140(2):146–159; doi: 10.1061/(ASCE)WR.1943-5452.0000314
FungKF, HuangYF, KooCH. Coupling fuzzy–SVR and boosting–SVR models with wavelet decomposition for meteorological drought prediction. Environ Earth Sci, 2019; 78(24):1; doi: 10.1007/s12665-019-8700-7
19.
GhiassiM, ZimbraDK, SaidaneH. Urban water demand forecasting with a dynamic artificial neural network model. J Water Resour Plann Manage, 2008; 134(2):138–146; doi: 10.1061/(ASCE)0733-9496(2008)134:2(138)
20.
Gil-GamboaA, PanequeP, TrullO, et al.Medium-term water consumption forecasting based on deep neural networks. Expert Syst Appl, 2024; 247:123234; doi: 10.1016/j.eswa.2024.123234
21.
GunnSR. Support Vector Machines for Classification and Regression. Tech Rep, Image Speech and Intelligent Systems Research Group, University of Southampton; 1997.
22.
HerreraM, TorgoL, IzquierdoJ, et al.Predictive models for forecasting hourly urban water demand. J Hydrol, 2010; 387(1–2):141–150; doi: 10.1016/j.jhydrol.2010.04.005
23.
HodgsonB, SharvelleS, SilversteinJ, et al.Impact of water conservation and reuse on water systems and receiving water body quality. Environ Eng Sci, 2018; 35(6):545–559; doi: 10.1089/ees.2017.0157
24.
HuangH, ZhangZ, SongF. An ensemble-learning-based method for short-term water demand forecasting. Water Resour Manage, 2021; 35(6):1757–1773; doi: 10.1007/s11269-021-02808-4
25.
JainA, VarshneyAK, JoshiUC. Short-term water demand forecast modelling at IIT Kanpur using artificial neural networks. Water Resour Manag, 2001; 15:299; doi: 10.1023/A:1014415503476
26.
KisiO, CimenM. A wavelet-support vector machine conjunction model for monthly streamflow forecasting. J Hydrol, 2011; 399(1–2):132–140; doi: 10.1016/j.jhydrol.2010.12.041
27.
LiY, ChenW. A comparative performance assessment of ensemble learning for credit scoring. Math, 2020; 8(10):1756; doi: 10.3390/math8101756
28.
LiuJ, LiX, YangH, et al.The water–energy nexus of megacities extends beyond geographic boundaries: A case of Beijing. Environ Eng Sci, 2019; 36(7):778–788; doi: 10.1089/ees.2018.0553
29.
MayrA, BinderH, GefellerO, et al.The evolution of boosting algorithms. Methods Inf Med, 2014; 53(06):419–427; doi: 10.3414/ME13-01-0122
30.
Mousavi-MirkalaeiP, RoozbahaniA, BanihabibME, et al.Forecasting urban water consumption using Bayesian networks and gene expression programming. Earth Sci Inform, 2022; 15(1):623–633; doi: 10.1007/s12145-021-00733-z
31.
MsizaIS, NelwamondoFV, MarwalaT. Water demand prediction using artificial neural networks and support vector regression. JCP, 2008; 3(11):1; doi: 10.4304/jcp.3.11.1-8
32.
NouraniV, Hosseini BaghanamA, AdamowskiJ, et al.Applications of hybrid wavelet-artificial intelligence models in hydrology: A review. J Hydrol, 2014; 514:358–377; doi: 10.1016/j.jhydrol.2014.03.057
33.
QuiltyJ, AdamowskiJ. A stochastic wavelet-based data-driven framework for forecasting uncertain multiscale hydrological and water resources processes. Environ Model Softw, 2020; 130:104718; doi: 10.1016/j.envsoft.2020.104718
34.
RahmanATMS, HosonoT, QuiltyJM, et al.Advances in water resources multiscale groundwater level forecasting: Coupling new machine learning approaches with wavelet transforms. Adv Water Res, 2020; 141:103595; doi: 10.1016/j.advwatres.2020.103595
35.
RegneryJ, LeeJ, KitanidisP, et al.Integration of artificial recharge and recovery systems for impaired water sources in urban settings: Overcoming current limitations and engineering challenges. Environ Eng Sci, 2013; 30(8):409–420; doi: 10.1089/ees.2012.0186
36.
RezaaliM, QuiltyJ, KarimiA. Probabilistic urban water demand forecasting using wavelet-based machine learning models. J Hydrol, 2021; 600:126358; doi: 10.1016/j.jhydrol.2021.126358
37.
ShamsMY, ElsheweyAM, El-KenawyESM, et al.Water quality prediction using machine learning models based on grid search method. Multimed Tools Appl, 2023; 83(12):35307–35334; doi: 10.1007/s11042-023-16737-4
38.
TiwariMK, ChatterjeeC. A new wavelet-bootstrap-ANN hybrid model for daily discharge forecasting. J Hydroinform, 2011; 13(3):500–519; doi: 10.2166/hydro.2010.142
39.
TyralisH, PapacharalampousG. Boosting algorithms in energy research: A systematic review. Neural Comput & Applic, 2021; 33(21):14101–14117; doi: 10.1007/s00521-021-05995-8
40.
VaidyaR, BuehlmannPH, Salazar-BenitesG, et al.Pilot plant performance comparing carbon-based and membrane-based potable reuse schemes. Environ Eng Sci, 2019; 36(11):1369–1378; doi: 10.1089/ees.2018.0559
41.
VapnikV. The Nature of Statistical Learning Theory. Springer-Verlag: New York; 1995.
42.
XenochristouM, KapelanZ. An ensemble stacked model with bias correction for improved water demand forecasting. Urban Water J, 2020; 17(3):212–223; doi: 10.1080/1573062X.2020.1758164
43.
XuJ, LiY, HuangG. A hybrid interval–robust optimization model for water quality management. Environ Eng Sci, 2013; 30(5):248–263; doi: 10.1089/ees.2012.0083
44.
XuJ. Forecasting water demand with the long short-term memory deep learning model. Int J Inf Technol Syst Approach, 2024; 17(1):1–18; doi: 10.4018/IJITSA.338910
45.
ZhangG, PatuwoBE, HuM. Forecasting with artificial neural networks: The state of the art. Int J Forecasting, 1998; 14(1):35–62; doi: 10.1016/S0169-2070(97)00044-7
46.
ZhangGP. Avoiding pitfalls in neural network research. IEEE Trans Syst, Man, Cybern C, 2007; 37(1):3–16; doi: 10.1109/TSMCC.2006.876059
47.
ZhenJ, ZhangY, LiuX, et al.Optimization modeling for regional energy system management coupled with energy–water nexus and carbon emission reduction: A case study. Environ Eng Sci, 2023; 40(3):114–126; doi: 10.1089/ees.2022.0204
48.
ZubaidiSL, DooleyJ, AlkhaddarRM, et al.A novel approach for predicting monthly water demand by combining singular spectrum analysis with neural networks. J Hydrol, 2018; 561:136–145; doi: 10.1016/j.jhydrol.2018.03.047
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
