Machine Learning for Modeling Water Demand
Publication: Journal of Water Resources Planning and Management
Volume 145, Issue 5
Abstract
This work shows the application of machine learning (ML) methods to the modeling of water demand for the first time. Classification and regression trees (CART) and random forest (RF), a multivariate, spatially nonstationary and nonlinear ML approach, were used to build a predictive model of water demand in the city of Seville, Spain, at the census tract level. Regression trees (RT) allowed estimation of water demand with an error of and determination of the main driving variables. RF allowed estimation of water demand with error values ranging from 18.89 to . The RF method provided better predictions; however, the RT model facilitated better understanding of water demand. This research shows an alternative to the hitherto applied cluster and linear regression approaches for modeling water demand and paves the way for a new set of further scientific investigations based on ML methods.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability
The following data, models, or code generated or used during the study are available from the corresponding author by request: demographic, socioeconomic, and building variables and scripts for the application of random forest and CART models.
Acknowledgments
The second author is a Juan de la Cierva grant holder (reference FPDI-2013-17183). The authors are grateful for the financial support given by the Spanish MINECO (project BIA2013-43462-P). We acknowledge the data providers for the water consumption measurements and the sociodemographic and urban building information, EMASESA and IECA, respectively.
References
Agthe, D. E., and R. B. Billings. 1980. “Dynamic models of residential water demand.” Water Resour. Res. 16 (3): 476–480. https://doi.org/10.1029/WR016i003p00476.
Agthe, D. E., and R. B. Billings. 2002. “Water price influence on apartment complex water use.” J. Water Resour. Plann. Manage. 128 (5): 366–369. https://doi.org/10.1061/(ASCE)0733-9496(2002)128:5(366).
Alcamo, J., M. Flörke, and M. Märker. 2007. “Future long-term changes in global water resources driven by socio-economic and climatic changes.” Hydrol. Sci. J. 52 (2): 247–275. https://doi.org/10.1623/hysj.52.2.247.
Arbués, F., R. Barberán, and I. Villanúa. 2004. “Price impact on urban residential water demand: A dynamic panel data approach.” Water Resour. Res. 40 (11): 1–9. https://doi.org/10.1029/2004WR003092.
Archibald, S., D. P. Roy, B. W. van Wilgen, and R. J. Scholes. 2009. “What limits fire? An examination of drivers of burnt area in southern Africa.” Global Change Biol. 15 (3): 613–630. https://doi.org/10.1111/j.1365-2486.2008.01754.x.
AS (Ayuntamiento de Sevilla). 2016. Distritos de Sevilla. Sevilla, Spain: AS.
Baykan, N. A., and N. Yilmaz. 2010. “Mineral identification using color spaces and artificial neural networks.” Comput. Geosci. 36 (1): 91–97. https://doi.org/10.1016/j.cageo.2009.04.009.
Beal, C. D., R. A. Stewart, and K. Fielding. 2013. “A novel mixed method smart metering approach to reconciling differences between perceived and actual residential end use water consumption.” J. Cleaner Prod. 60: 116–128. https://doi.org/10.1016/j.jclepro.2011.09.007.
Benediktsson, J. A., and J. R. Sveinsson. 1997. “Feature extraction for multisource data classification with artificial neural networks.” Int. J. Remote Sens. 18 (4): 727–740. https://doi.org/10.1080/014311697218728.
Bhat, A., and W. Blomquist. 2004. “Policy, politics, and water management in the Guadalquivir River basin, Spain.” Water Resour. Res 40 (8): W08S071–W08S0711. https://doi.org/10.1029/2003WR002726.
Breiman, L. 1996. “Bagging predictors.” Mach. Learn. 24 (2): 123–140. https://doi.org/10.1007/BF00058655.
Breiman, L. 2001. “Random forests.” Mach. Learn. 45 (1): 5–32. https://doi.org/10.1023/A:1010933404324.
Breiman, L., J. Friedman, C. J. Stone, and R. A. Olshen. 1984. Classification and regression trees. Belmont, CA: Chapman and Hall/CRC.
Bue, B. D., and T. F. Stepinski. 2006. “Automated classification of landforms on Mars.” Comput. Geosci. 32 (5): 604–614. https://doi.org/10.1016/j.cageo.2005.09.004.
Campbell, H. E., R. M. Johnson, and E. H. Larson. 2004. “Prices, devices, people, or rules: The relative effectiveness of policy instruments in water conservation1.” Rev. Policy Res. 21 (5): 637–662. https://doi.org/10.1111/j.1541-1338.2004.00099.x.
Campbell, H. E., E. H. Larson, R. M. Johnson, and M. J. Watts. 1999. Some best bets in residential water conservation: Results of a multivariate regression analysis, City of Phoenix, 1990–1996. Phoenix, AZ: Morrison Institute for Public Policy.
Canty, M. J. 2009. “Boosting a fast neural network for supervised land cover classification.” Comput. Geosci. 35 (6): 1280–1295. https://doi.org/10.1016/j.cageo.2008.07.004.
CHG (Confederación Hidrográfica del Guadalquivir). 2016. S.A.I.H del Guadalquivir. Andalucía, Spain: CHG.
Coimbra, R., V. Rodriguez-Galiano, F. Olóriz, and M. Chica-Olmo. 2014. “Regression trees for modeling geochemical data—An application to Late Jurassic carbonates (Ammonitico Rosso).” Comput. Geosci. 73: 198–207. https://doi.org/10.1016/j.cageo.2014.09.007.
Conley, B. C. 1967. “Price elasticity of the demand for water in Southern California.” Ann. Reg. Sci. 1 (1): 180–189. https://doi.org/10.1007/BF01290019.
Corcoran, E., C. Nellemann, E. Baker, R. Bos, D. Osborn, H. Savelli, eds. 2010. Sick water? The central role of waste- water management in sustainable development. A rapid response assessment. Arendal, Norway: United Nations Environment Programme, UN-HABITAT, GRID-Arendal.
Dalhuisen, J. M., H. L. F. De Groot, C. A. Rodenburg, and P. Nijkamp. 2002. “Economic aspects of sustainable water use: Evidence from a horizontal comparison of European cities.” Int. J. Water 2 (1): 75–94. https://doi.org/10.1504/IJW.2002.002080.
Darling, E. S., L. Alvarez-Filip, T. A. Oliver, T. R. McClanahan, and I. M. Côté. 2012. “Evaluating life-history strategies of reef corals from species traits.” Ecol. Lett. 15 (12): 1378–1386. https://doi.org/10.1111/j.1461-0248.2012.01861.x.
De Nicolás, V. L., F. Laguna-Peñuelas, and P. Vidueira. 2014. “An energy optimization criterion for branched water networks.” Tecnologia y Ciencias del Agua 5 (6): 41–51.
Dixon, B. 2009. “A case study using support vector machines, neural networks and logistic regression in a GIS to identify wells contaminated with nitrate-N.” Hydrogeol. J. 17 (6): 1507–1520. https://doi.org/10.1007/s10040-009-0451-1.
Domene, E., and D. Saurí. 2006. “Urbanisation and water consumption: Influencing factors in the metropolitan region of Barcelona.” Urban Stud. 43 (9): 1605–1623. https://doi.org/10.1080/00420980600749969.
Dubois, M. K., G. C. Bohling, and S. Chakrabarti. 2007. “Comparison of four approaches to a rock facies classification problem.” Comput. Geosci. 33 (5): 599–617. https://doi.org/10.1016/j.cageo.2006.08.011.
EC (European Communities). 2000. Directive 2000/60/EC of the European Parliament and of the Council of 23 October 2000 establishing a framework for Community action in the field of water policy. Brussels, Belgium: ATBD X.X, European Communities.
EC (European Communities). 2003. Water for life. Office for Official Publications of the European Communities. Luxembourg: European Commission.
EEA (European Environment Agency). 2015. The European Environment—State and outlook 2015 Report. Copenhagen, Denmark: EEA.
EMASESA (Empresa Metropolitana de Abastecimiento y Saneamiento de Aguas de Sevilla). 2016. Área gestionada por EMASESA. Sevilla, Spain: EMASESA.
Fan, L., G. Liu, F. Wang, C. J. Ritsema, and V. Geissen. 2014. “Domestic water consumption under intermittent and continuous modes of water supply.” Water Resour. Manage. 28 (3): 853–865. https://doi.org/10.1007/s11269-014-0520-7.
Fielding, K. S., S. Russell, A. Spinks, and A. Mankad. 2012. “Determinants of household water conservation: The role of demographic, infrastructure, behavior, and psychosocial variables.” Water Resour. Res. 48 (10): W10510. https://doi.org/10.1029/2012WR012398.
Friedl, M. A., C. E. Brodley, and A. H. Strahler. 1999. “Maximizing land cover classification accuracies produced by decision trees at continental to global scales.” Geosci. Remote Sens. 37 (2): 969–977. https://doi.org/10.1109/36.752215.
Giansante, C., M. Aguilar, L. Babiano, A. Garrido, A. Gómez, E. Iglesias, W. Lise, L. Moral, and B. Pedregal. 2002. “Institutional adaptation to changing risk of water scarcity in the Lower Guadalquivir Basin.” Nat. Resour. J. 42 (3): 521–564.
Gislason, P. O., J. A. Benediktsson, and J. R. Sveinsson. 2006. “Random forests for land cover classification.” Pattern Recognit. Lett. 27 (4): 294–300. https://doi.org/10.1016/j.patrec.2005.08.011.
Gottlieb, M. 1963. “Urban domestic demand for water: A Kansas case study.” Land Econ. 39 (2): 204–210. https://doi.org/10.2307/3144756.
Hanke, S. H., and J. E. Flack. 1968. “Effects of metering urban water.” J. Am. Water Works Assoc. 60 (12): 1359–1366. https://doi.org/10.1002/j.1551-8833.1968.tb03685.x.
Howe, C. W., and F. P. Linaweaver. 1967. “The impact of price on residential water demand and its relation to system design and price structure.” Water Resour. Res. 3 (1): 13–32. https://doi.org/10.1029/WR003i001p00013.
IECA (Instituto de Estadística y Cartografía de Andalucía). 2016. Sistema de Información Multiterritorial de Andalucía (SIMA). Sevilla, Spain: Instituto de Estadística y Cartografía de Andalucía.
INE (Instituto Nacional de Estadística). 2016. Revisión del Padrón municipal 2009. Datos por municipios. Madrid, Spain: INE.
Inman, D., and P. Jeffrey. 2006. “A review of residential water conservation tool performance and influences on implementation effectiveness.” Urban Water J. 3 (3): 127–143. https://doi.org/10.1080/15730620600961288.
Khader, A. I., D. E. Rosenberg, and M. McKee. 2013. “A decision tree model to estimate the value of information provided by a groundwater quality monitoring network.” Hydrol. Earth Syst. Sci. 17 (5): 1797–1807. https://doi.org/10.5194/hess-17-1797-2013.
Larson, B. O., and H. E. Hudson. 1951. “Residential water use and family income.” J. Am. Water Works Assn. 43 (8): 603–611.
Leibovici, D. G., L. Bastin, and M. Jackson. 2011. “Higher-order co-occurrences for exploratory point pattern analysis and decision tree clustering on spatial data.” Comput. Geosci. 37 (3): 382–389. https://doi.org/10.1016/j.cageo.2010.06.006.
Lima, A. R., A. J. Cannon, and W. W. Hsieh. 2013. “Nonlinear regression in environmental sciences by support vector machines combined with evolutionary strategy.” Comput. Geosci. 50: 136–144. https://doi.org/10.1016/j.cageo.2012.06.023.
Loh, M. C. P. 2003. Domestic water use study in Perth, Western Australia 1998–2001. Perth, Australia.
Lopez-Gunn, E. 2009. “Agua para todos: A new regionalist hydraulic paradigm in Spain.” Water Altern. 2 (3): 370–394.
Mamade, A., D. Loureiro, D. Covas, S. T. Coelho, and C. Amado. 2014. “Spatial and temporal forecasting of water consumption at the DMA level using extensive measurements.” Procedia Eng. 70: 1063–1073. https://doi.org/10.1016/j.proeng.2014.02.118.
March, H., J. Perarnau, and D. Saurí. 2012. “Exploring the links between immigration, ageing and domestic water consumption: The case of the metropolitan area of Barcelona.” Reg. Stud. 46 (2): 229–244. https://doi.org/10.1080/00343404.2010.487859.
March, H., and D. Saurí. 2010. “The suburbanization of water scarcity in the Barcelona metropolitan region: Sociodemographic and urban changes influencing domestic water consumption.” Prof. Geogr. 62 (1): 32–45. https://doi.org/10.1080/00330120903375860.
Martinez-Espiñeira, R. 2002. “Residential water demand in the northwest of Spain.” Environ. Resour. Econ. 21 (2): 161–187. https://doi.org/10.1023/A:1014547616408.
Martínez-Espiñeira, R., and C. Nauges. 2004. “Is all domestic water consumption sensitive to price control?” Appl. Econ. 36 (15): 1697–1703. https://doi.org/10.1080/0003684042000218570.
Mas, J. F., and J. J. Flores. 2008. “The application of artificial neural networks to the analysis of remotely sensed data.” Int J. Remote Sens. 29 (3): 617–663. https://doi.org/10.1080/01431160701352154.
Mayer, P. W., W. B. DeOreo, E. M. Opitz, J. C. Kiefer, W. Y. Davis, B. Dziegielewski, and J. O. Nelson. 1999. Residential end uses of water, 352. Denver: American Water Works Association.
Mingers, J. 1989. “An empirical comparison of selection measures for decision-tree induction.” Mach. Learn. 3 (4): 319–342. https://doi.org/10.1007/BF00116837.
Mountrakis, G., J. Im, and C. Ogole. 2011. “Support vector machines in remote sensing: A review.” ISPRS J. Photogramm. Remote Sens. 66 (3): 247–259. https://doi.org/10.1016/j.isprsjprs.2010.11.001.
Murdock, S. H., D. E. Albrecht, R. R. Hamm, and K. Backman. 1991. “Role of sociodemographic characteristics in projections of water use.” J. Water Resour. Plann. Manage. 172 (2): 235–251. https://doi.org/10.1061/(ASCE)0733-9496(1991)117:2(235).
Odlare, M. 2014. “Introductory chapter for water resources.” In Reference module in earth systems and environmental sciences. New York: Elsevier.
OECD. 1999. The price of water. OECD.
Ojeda de la Cruz, A., C. R. Alvarez-Chavez, M. A. Ramos-Corella, and F. Soto-Hernandez. 2017. “Determinants of domestic water consumption in Hermosillo, Sonora, Mexico.” J. Cleaner Prod. 142: 1901–1910. https://doi.org/10.1016/j.jclepro.2016.11.094.
Oki, T., Y. Agata, S. Kanae, T. Saruhashi, and K. Musiake. 2003. “Global water resources assessment under climatic change in 2050 using TRIP.” In Proc., 280 of IAHS-AISH Publication, 124–133. Wallingford, Oxfordshire, UK: International Association of Hydrological Sciences.
Oki, T., and S. Kanae. 2006. “Global hydrological cycles and world water resources.” Science 313 (5790): 1068–1072. https://doi.org/10.1126/science.1128845.
Ouyang, Y., E. A. Wentz, B. L. Ruddell, and S. L. Harlan. 2014. “A multi-scale analysis of single-family residential water use in the phoenix metropolitan area.” JAWRA J. Am. Water Resour. Assoc. 50 (2): 448–467. https://doi.org/10.1111/jawr.12133.
Pal, M., and P. M. Mather. 2003. “An assessment of the effectiveness of decision tree methods for land cover classification.” Remote Sens. Environ. 86 (4): 554–565. https://doi.org/10.1016/S0034-4257(03)00132-9.
Pavel, M., J. D. Nelson, and R. Jonathan Fannin. 2011. “An analysis of landslide susceptibility zonation using a subjective geomorphic mapping and existing landslides.” Comput. Geosci. 37 (4): 554–566. https://doi.org/10.1016/j.cageo.2010.10.006.
Peters, J., B. De Baets, N. E. C. Verhoest, R. Samson, S. Degroeve, P. De Becker, and W. Huybrechts. 2007. “Random forests as a tool for ecohydrological distribution modelling.” Ecol. Modell. 207 (2–4): 304–318. https://doi.org/10.1016/j.ecolmodel.2007.05.011.
Petropoulos, G. P., C. Kalaitzidis, and K. Prasad Vadrevu. 2012. “Support vector machines and object-based classification for obtaining land-use/cover cartography from Hyperion hyperspectral imagery.” Comput. Geosci. 41: 99–107. https://doi.org/10.1016/j.cageo.2011.08.019.
Poyer, D. A., L. Henderson, and A. P. S. Teotia. 1997. “Residential energy consumption across different population groups: Comparative analysis for Latino and non-Latino households in USA.” Energy Econ. 19 (4): 445–463. https://doi.org/10.1016/S0140-9883(97)01024-4.
Qader, S. H., J. Dash, P. M. Atkinson, and V. Rodriguez-Galiano. 2016. “Classification of vegetation type in Iraq using satellite-based phenological parameters.” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 9 (1): 414–424. https://doi.org/10.1109/JSTARS.2015.2508639.
Qi, F., and A. X. Zhu. 2011. “Comparing three methods for modeling the uncertainty in knowledge discovery from area-class soil maps.” Comput. Geosci. 37 (9): 1425–1436. https://doi.org/10.1016/j.cageo.2010.10.016.
Quinlan, J. R. 1986. “Induction of decision trees.” Mach. Learn. 1 (1): 81–106. https://doi.org/10.1007/BF00116251.
Quinlan, J. R. 1993. C4.5 Programs for Machine Learning. San Francisco: Morgan Kaufmann.
Rodriguez-Galiano, V., M. P. Mendes, M. J. Garcia-Soldado, M. Chica-Olmo, and L. Ribeiro. 2014a. “Predictive modeling of groundwater nitrate pollution using random forest and multisource variables related to intrinsic and specific vulnerability: A case study in an agricultural setting (southern Spain).” Sci. Total Environ. 476: 189–206. https://doi.org/10.1016/j.scitotenv.2014.01.001.
Rodriguez-Galiano, V., M. Sanchez-Castillo, M. Chica-Olmo, and M. Chica-Rivas. 2015. “Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines.” Ore Geol. Rev. 71: 804–818. https://doi.org/10.1016/j.oregeorev.2015.01.001.
Rodriguez-Galiano, V. F., M. Chica-Olmo, F. Abarca-Hernandez, P. M. Atkinson, and C. Jeganathan. 2012a. “Random forest classification of Mediterranean land cover using multi-seasonal imagery and multi-seasonal texture.” Remote Sens. Environ. 121: 93–107. https://doi.org/10.1016/j.rse.2011.12.003.
Rodriguez-Galiano, V. F., M. Chica-Olmo, and M. Chica-Rivas. 2014b. “Predictive modelling of gold potential with the integration of multisource information based on random forest: A case study on the Rodalquilar area, southern Spain.” Int. J. Geogr. Inf. Sci. 28 (7): 1336–1354. https://doi.org/10.1080/13658816.2014.885527.
Rodriguez-Galiano, V. F., B. Ghimire, J. Rogan, M. Chica-Olmo, and J. P. Rigol-Sanchez. 2012b. “An assessment of the effectiveness of a random forest classifier for land-cover classification.” ISPRS J. Photogramm. Remote Sens. 67 (1): 93–104. https://doi.org/10.1016/j.isprsjprs.2011.11.002.
Rodriguez-Galiano, V. F., M. Sanchez-Castillo, J. Dash, P. M. Atkinson, and J. Ojeda-Zujar. 2016. “Modelling interannual variation in the spring and autumn land surface phenology of the European forest.” Biogeosciences 13 (11): 3305–3317. https://doi.org/10.5194/bg-13-3305-2016.
Rogan, J., J. Miller, D. Stow, J. Franklin, L. Levien, and C. Fischer. 2003. “Land-cover change monitoring with classification trees using landsat TM and ancillary data.” Photogramm. Eng. Remote Sens. 69 (7): 793–804. https://doi.org/10.14358/PERS.69.7.793.
Romano, G., N. Salvati, and A. Guerrini. 2014. “Estimating the determinants of residential water demand in Italy.” Forests 5 (9): 2929–2945. https://doi.org/10.3390/w6102929.
Sauvy, A. 1966. Théorie générale de la population. II, II. Paris: Presses Universitaires de France.
Sesnie, S. E., P. E. Gessler, B. Finegan, and S. Thessler. 2008. “Integrating Landsat TM and SRTM-DEM derived variables with decision trees for habitat classification and change detection in complex neotropical environments.” Remote Sens. Environ. 112 (5): 2145–2159. https://doi.org/10.1016/j.rse.2007.08.025.
Shandas, V., and G. H. Parandvash. 2010. “Integrating urban form and demographics in water-demand management: An empirical case study of Portland, Oregon.” Environ. Plann. B Plann. Des 37 (1): 112–128. https://doi.org/10.1068/b35036.
Shiklomanov, I. A. 2000. “Appraisal and assessment of world water resources.” Water Int. 25 (1): 11–32. https://doi.org/10.1080/02508060008686794.
Steele, B. M. 2000. “Combining multiple classifiers: An application using spatial and remotely sensed information for land cover type mapping.” Remote Sens. Environ. 74 (3): 545–556. https://doi.org/10.1016/S0034-4257(00)00145-0.
Suero, F. J., P. W. Mayer, and D. E. Rosenberg. 2012. “Estimating and verifying United States households’ potential to conserve water.” J. Water Resour. Plann. Manage. 138 (3): 299–306. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000182.
Tiwari, M. K., and J. F. Adamowski. 2015. “Medium-term urban water demand forecasting with limited data using an ensemble wavelet-bootstrap machine-learning approach.” J. Water Resour. Plann. Manage. 141 (2): 04014053. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000454.
Villarín, M. C. 2019. “Methodology based on fine spatial scale and preliminary clustering to improve multivariate linear regression analysis of domestic water consumption.” Appl. Geogr. 103: 22–39. https://doi.org/10.1016/j.apgeog.2018.12.005.
Vinuesa Angulo, J., and F. Zamora López. 1997. Demografía: análisis y proyecciones. Madrid, Spain: Editorial Síntesis.
Vörösmarty, C. J., P. Green, J. Salisbury, and R. B. Lammers. 2000. “Global water resources: Vulnerability from climate change and population growth.” Science 289 (5477): 284–288. https://doi.org/10.1126/science.289.5477.284.
Yan, S., and B. Minsker. 2011. “Applying dynamic surrogate models in noisy genetic algorithms to optimize groundwater remediation designs.” J. Water Resour. Plann. Manage. 137 (3): 284–292. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000106.
Yu, L., A. Porwal, E. J. Holden, and M. C. Dentith. 2012. “Towards automatic lithological classification from remote sensing data using support vector machines.” Comput. Geosci. 45: 229–239. https://doi.org/10.1016/j.cageo.2011.11.019.
Zuo, R., and E. J. M. Carranza. 2011. “Support vector machine: A tool for mapping mineral prospectivity.” Comput. Geosci. 37 (12): 1967–1975. https://doi.org/10.1016/j.cageo.2010.09.014.
Information & Authors
Information
Published In
Journal of Water Resources Planning and Management
Volume 145 • Issue 5 • May 2019
Copyright
©2019 American Society of Civil Engineers.
History
Received: Feb 12, 2018
Accepted: Oct 22, 2018
Published online: Mar 12, 2019
Published in print: May 1, 2019
Discussion open until: Aug 12, 2019
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.