Urban Water Demand Modeling Using Machine Learning Techniques: Case Study of Fortaleza, Brazil
Publication: Journal of Water Resources Planning and Management
Volume 147, Issue 1
Abstract
Despite recent efforts to apply machine learning (ML) for water demand modeling, overcoming the black-box nature of these techniques to extract practical information remains a challenge, especially in developing countries. This study integrated random forest (RF), self-organizing map (SOM), and artificial neural network (ANN) techniques to assess water demand patterns and to develop a predictive model for the city of Fortaleza, Brazil. We performed the analysis at two spatial scales, with different level of information: census tracts (CTs) at the fine scale, and census blocks (CBs) at the coarse scale. At the CB scale, demand was modeled with socioeconomic, demographic, and household characteristics. The RF technique was applied to rank these variables, and the most relevant were used to cluster census blocks with SOMs. RFs and ANNs were used in an iterative approach to define the input variables for the predictive model with minimum redundancy. At the CT scale, demand was modeled using HDI and per capita income. Variables which assess the education level and economic aspects of households demonstrated a direct relationship with water demand. The analysis at the coarse scale provided more insight into the relationship between the variables; however, the predictive model performed better at the fine scale. This study demonstrates how data-driven models can be helpful for water management, especially in environments with strong socioeconomic inequalities, where urban planning decisions should be integrated and inclusive.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
All code used in this study is available online at https://github.com/taiscarvalho/ml_waterdemand. The water demand data were provided by a third party. Direct requests for these data may be made to the Water and Wastewater Company of Ceará (CAGECE).
Acknowledgments
The research was supported by grants from the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior—Brasil (CAPES) and the Conselho Nacional de Desenvolvimento Científico e Tecnológico—Brasil (CNPq).
References
Adamowski, J., and C. Karapataki. 2010. “Comparison of multivariate regression and artificial neural networks for peak urban water-demand forecasting: Evaluation of different ANN learning algorithms.” J. Hydrol. Eng. 15 (10): 729–743. https://doi.org/10.1061/(ASCE)HE.1943-5584.0000245.
Altunkaynak, A., and T. A. Nigussie. 2017. “Monthly water consumption prediction using season algorithm and wavelet transform–based models.” J. Water Resour. Plann. Manage. 143 (6): 04017011. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000761.
Apley, D. W., and J. Zhu. 2016. “Visualizing the effects of predictor variables in black box supervised learning models.” Preprint, submitted December 27, 2016. https://arxiv.org/abs/1612.08468.
Barreto, F. A. F. D., and A. S. B. Menezes. 2014. Desenvolvimento Econômico do Ceará: Evidências Recentes e Reflexões. Fortaleza, Brazil: Instituto de Pesquisa e Estratégia Econômica do Ceará.
Bata, M. H., R. Carriveau, and S.-K. D. Ting. 2020. “Short-term water demand forecasting using nonlinear autoregressive artificial neural networks.” J. Water Resour. Plann. Manage. 146 (3): 04020008. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001165.
Bennett, C., R. A. Stewart, and C. D. Beal. 2013. “ANN-based residential water end-use demand forecasting model.” Expert Syst. Appl. 40 (4): 1014–1023. https://doi.org/10.1016/j.eswa.2012.08.012.
Biau, G., and E. Scornet. 2016. “A random forest guided tour.” Test 25 (2): 197–227. https://doi.org/10.1007/s11749-016-0481-7.
Bishop, C. M. 1995. Neural networks for pattern recognition. Oxford, UK: Oxford University Press.
Bolorinos, J., N. K. Ajami, and R. Rajagopal. 2020. “Consumption change detection for urban planning: Monitoring and segmenting water customers during drought.” Water Resour. Res. 56 (3): e2019WR025812. https://doi.org/10.1029/2019WR025812.
Breiman, L. 2001. “Random forests.” Mach. Learn. 45 (1): 5–32. https://doi.org/10.1023/A:1010933404324.
Brentan, B. M., E. Luvizotto Jr., M. Herrera, J. Izquierdo, and R. Pérez-García. 2017. “Hybrid regression model for near real-time urban water demand forecasting.” J. Comput. Appl. Math. 309 (Jan): 532–541. https://doi.org/10.1016/j.cam.2016.02.009.
Cardell-Oliver, R., J. Wang, and H. Gigney. 2016. “Smart meter analytics to pinpoint opportunities for reducing household water use.” J. Water Resour. Plann. Manage. 142 (6): 04016007. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000634.
Chang, H., G. H. Parandvash, and V. Shandas. 2010. “Spatial variations of single-family residential water consumption in Portland, Oregon.” Urban Geogr. 31 (7): 953–972. https://doi.org/10.2747/0272-3638.31.7.953.
Chaudhary, V., R. S. Bhatia, and A. K. Ahlawat. 2014. “A novel Self-Organizing Map (SOM) learning algorithm with nearest and farthest neurons.” Alexandria Eng. J. 53 (4): 827–831. https://doi.org/10.1016/j.aej.2014.09.007.
Chen, G., T. Long, J. Xiong, and Y. Bai. 2017. “Multiple random forests modelling for urban water consumption forecasting.” Water Resour. Manage. 31 (15): 4715–4729. https://doi.org/10.1007/s11269-017-1774-7.
Cominola, A., K. Nguyen, M. Giuliani, R. A. Stewart, H. R. Maier, and A. Castelletti. 2019. “Data mining to uncover heterogeneous water use behaviors from smart meter data.” Water Resour. Res. 55 (11): 9315–9333. https://doi.org/10.1029/2019WR024897.
Cominola, A., E. S. Spang, M. Giuliani, A. Castelletti, J. R. Lund, and F. J. Loge. 2018. “Segmentation analysis of residential water-electricity demand for customized demand-side management programs.” J. Cleaner Prod. 172 (Jan): 1607–1619. https://doi.org/10.1016/j.jclepro.2017.10.203.
Dias, T. F., A. Kalbusch, and E. Henning. 2018. “Factors influencing water consumption in buildings in southern Brazil.” J. Cleaner Prod. 184 (May): 160–167. https://doi.org/10.1016/j.jclepro.2018.02.093.
Duerr, I., H. R. Merrill, C. Wang, R. Bai, M. Boyer, M. D. Dukes, and N. Bliznyuk. 2018. “Forecasting urban household water demand with statistical and machine learning methods using large space-time data: A Comparative study.” Environ. Modell. Software 102 (Apr): 29–38. https://doi.org/10.1016/j.envsoft.2018.01.002.
Dunn, J. C. 1974. “Well-separated clusters and optimal fuzzy partitions.” J. Cybern. 4 (1): 95–104. https://doi.org/10.1080/01969727408546059.
Firat, M., M. A. Yurdusev, and M. E. Turan. 2008. “Evaluation of artificial neural network techniques for municipal water consumption modeling.” Water Resour. Manage. 23 (4): 617–632. https://doi.org/10.1007/s11269-008-9291-3.
Galelli, S., and A. Castelletti. 2013. “Tree-based iterative input variable selection for hydrological modeling.” Water Resour. Res. 49 (7): 4295–4310. https://doi.org/10.1002/wrcr.20339.
Garcia, J., L. R. Salfer, A. Kalbusch, and E. Henning. 2019. “Identifying the drivers of water consumption in single-family households in Joinville, Southern Brazil.” Water 11 (10): 1990. https://doi.org/10.3390/w11101990.
Garmany, J. 2011. “Situating Fortaleza: Urban space and uneven development in northeastern Brazil.” Cities 28 (1): 45–52. https://doi.org/10.1016/j.cities.2010.08.004.
Genuer, R., J.-M. Poggi, and C. Tuleau-Malot. 2010. “Variable selection using random forests.” Pattern Recognit. Lett. 31 (14): 2225–2236. https://doi.org/10.1016/j.patrec.2010.03.014.
Gharabaghi, S., E. Stahl, and H. Bonakdari. 2019. “Integrated nonlinear daily water demand forecast model (case study: City of Guelph, Canada).” J. Hydrol. 579 (Sep): 124182. https://doi.org/10.1016/j.jhydrol.2019.124182.
Gonzales, P., and N. Ajami. 2017. “Social and structural patterns of drought-related water conservation and rebound.” Water Resour. Res. 53 (12): 10619–10634. https://doi.org/10.1002/2017WR021852.
Grande, M. H., C. O. Galvão, L. I. B. Miranda, and L. D. G. Sobrinho. 2016. “The perception of users about the impacts of water rationing on their household routines.” Ambiente Sociedade 19 (1): 163–182. https://doi.org/10.1590/1809-4422asoc150155r1v1912016.
Gulis, G. 2000. “Life expectancy as an indicator of environmental health.” European J. Epidemiol. 16 (2): 161–165. https://doi.org/10.1023/A:1007629306606.
Guo, G., S. Liu, Y. Wu, J. Li, R. Zhou, and X. Zhu. 2018. “Short-term water demand forecast based on deep learning method.” J. Water Resour. Plann. Manage. 144 (12): 04018076. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000992.
Guyon, I., and A. Elisseeff. 2003. “An introduction to variable and feature selection.” J. Mach. Learn. Res. 3 (Mar): 1157–1182. https://doi.org/10.5555/944919.944968.
Haque, M. M., A. de Souza, and A. Rahman. 2017. “Water demand modelling using independent component regression technique.” Water Resour. Manage. 31 (1): 299–312. https://doi.org/10.1007/s11269-016-1525-1.
Haselbeck, V., J. Kordilla, F. Krausea, and M. Sauterb. 2019. “Self-organizing maps for the identification of groundwater salinity sources based on hydrochemical data.” J. Hydrol. 576 (Sep): 610–619. https://doi.org/10.1016/j.jhydrol.2019.06.053.
Hastie, T., R. Tibshirani, and J. Friedman. 2009. The elements of statistical learning: Data mining, inference, and prediction. New York: Springer Science & Business Media.
Hemati, A., M. A. Rippy, S. B. Grant, K. Davis, and D. Feldman. 2016. “Deconstructing demand: The anthropogenic and climatic drivers of urban water consumption.” Environ. Sci. Technol. 50 (23): 12557–12566. https://doi.org/10.1021/acs.est.6b02938.
Herrera, M., L. Torgo, J. Izquierdo, and R. Pérez-García. 2010. “Predictive models for forecasting hourly urban water demand.” J. Hydrol. 387 (1–2): 141–150. https://doi.org/10.1016/j.jhydrol.2010.04.005.
House-Peters, L. A., and H. Chang. 2011. “Urban water demand modeling: Review of concepts, methods, and organizing principles.” Water Resour. Res. 47 (5): 351–360. https://doi.org/10.1029/2010WR009624.
House-Peters, L. A., B. Pratt, and H. Chang. 2010. “Effects of urban spatial structure, sociodemographics, and climate on residential water consumption in Hillsboro, Oregon.” J. Am. Water Resour. Assoc. 46 (3): 461–472. https://doi.org/10.1111/j.1752-1688.2009.00415.x.
Hussien, W. A., F. A. Memon, and D. A. Savic. 2016. “Assessing and modelling the influence of household characteristics on per capita water consumption.” Water Resour. Manage. 30 (9): 2931–2955. https://doi.org/10.1007/s11269-016-1314-x.
IBGE (Instituto Brasileiro de Geografia e Estatística). 2010. “Censo Demográfico de 2010” [2010 Demographic Census]. Accessed November 17, 2018. https://censo2010.ibge.gov.br/.
IPLANFOR (Instituto de Planejamento de Fortaleza). 2015. Fortaleza 2040. Fortaleza, Brazil: Prefeitura Municipal de Fortaleza.
Kalteh, A. M., P. Hjorth, and R. Berndtsson. 2008. “Review of the self-organizing map (SOM) approach in water resources: Analysis, modelling and application.” Environ. Modell. Software 23 (7): 835–845. https://doi.org/10.1016/j.envsoft.2007.10.001.
Kohonen, T. 1982. “Self-organized formation of topologically correct feature maps.” Biol. Cybern. 43 (1): 59–69. https://doi.org/10.1007/BF00337288.
Kohonen, T. 2014. MATLAB implementations and applications of the self-organizing map. Helsinki, Finland: Unigrafia Oy.
Lee, D., and S. Derrible. 2020. “Predicting residential water demand with machine-based statistical learning.” J. Water Resour. Plann. Manage. 146 (1): 04019067. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001119.
Li, T., G. Sun, C. Yang, K. Liang, S. Ma, and L. Huang. 2018. “Using self-organizing map for coastal water quality classification: Towards a better understanding of patterns and processes.” Sci. Total Environ. 628–629 (Jul): 1446–1459. https://doi.org/10.1016/j.scitotenv.2018.02.163.
Lindsay, J., A. J. Dean, and S. Supski. 2017. “Responding to the millennium drought: comparing domestic water cultures in three Australian cities.” Reg. Environ. Change 17 (2): 565–577. https://doi.org/10.1007/s10113-016-1048-6.
Lippmann, R. 1987. “An introduction to computing with neural nets.” IEEE ASSP Mag. 4 (2): 4–22. https://doi.org/10.1109/MASSP.1987.1165576.
Liu, Y., J. Zhao, and Z. Wang. 2015. “Identifying determinants of urban water use using data mining approach.” Urban Water J. 12 (8): 618–630. https://doi.org/10.1080/1573062X.2014.923920.
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.
Matos, C., C. A. Teixeira, R. Bento, J. Varajão, and I. Bentesa. 2014. “An exploratory study on the influence of socio-demographic characteristics on water end uses inside buildings.” Sci. Total Environ. 466–467 (Jan): 467–474. https://doi.org/10.1016/j.scitotenv.2013.07.036.
Molnar, C. 2019. “Interpretable machine learning.” Accessed May 20, 2019. https://christophm.github.io/interpretable-ml-book.
Montgomery, M. A., and M. Elimelech. 2007. “Water and sanitation in developing countries: Including health in the equation.” Environ. Sci. Technol. 41 (1): 17–24. https://doi.org/10.1021/es072435t.
Msiza, I. S., F. V. Nelwamondo, and T. Marwala. 2007. “Artificial neural networks and support vector machines for water demand time series forecasting.” In Proc., 2007 IEEE Int. Conf. on Systems, Man and Cybernetics, 638–643. New York: IEEE.
Musolesi, A., and M. Nosvelli. 2007. “Dynamics of residential water consumption in a panel of Italian municipalities.” Appl. Econ. Lett. 14 (6): 441–444. https://doi.org/10.1080/13504850500425642.
Nawaz, R., P. Rees, S. Clark, G. Mitchell, A. McDonald, M. Kalamandeen, C. Lambert, and R. Henderson. 2019. “Long-term projections of domestic water demand: A case study of London and the Thames Valley.” J. Water Resour. Plann. Manage. 145 (11): 05019017. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001088.
Olmstead, S. M., and R. N. Stavins. 2009. “Comparing price and nonprice approaches to urban water conservation.” Water Resour. Res. 45 (4): W04301. https://doi.org/10.1029/2008WR007227.
Ouyang, Y., E. A. Wentz, B. L. Ruddell, and S. L. Harlan. 2013. “A multi-scale analysis of single-family residential water use in the Phoenix metropolitan area.” J. Am. Water Resour. Assoc. 50 (2): 448–467. https://doi.org/10.1111/jawr.12133.
Padulano, R., and G. Giudice. 2018. “A mixed strategy based on self-organizing map for water demand pattern profiling of large-size smart water grid data.” Water Resour. Manage. 32 (11): 3671–3685. https://doi.org/10.1007/s11269-018-2012-7.
Papacharalampous, G. A., and H. Tyralis. 2018. “Evaluation of random forests and prophet for daily streamflow forecasting.” Adv. Geosci. 45: 201–208. https://doi.org/10.5194/adgeo-45-201-2018.
PNUD (Programa das Nações Unidas para o Desenvolvimento), IPEA (Instituto de Pesquisa Econômica Aplicada), and FJP (Fundação João Pinheiro). 2014. “Atlas do desenvolvimento humano nas regiões metropolitanas” [Atlas of human development in metropolitan regions]. Accessed November 18, 2018. https://atlasbrasil.org.br.
Polebitski, A. S., and R. N. Palmer. 2010. “Seasonal residential water demand forecasting for census tracts.” J. Water Resour. Plann. Manage. 136 (1): 27–36. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000003.
Pulido-Calvo, I., P. Montesinos, J. Roldán, and F. Ruiz-Navarro. 2007. “Linear regressions and neural approaches to water demand forecasting in irrigation districts with telemetry systems.” Biosyst. Eng. 97 (2): 283–293. https://doi.org/10.1016/j.biosystemseng.2007.03.003.
Qi, J., H. Liu, X. Liu, and Y. Zhang. 2019. “Spatiotemporal evolution analysis of time-series land use change using self-organizing map to examine the zoning and scale effects.” Comput. Environ. Urban Syst. 76 (Jul): 11–23. https://doi.org/10.1016/j.compenvurbsys.2019.03.002.
Quesnel, K. J., and N. K. Ajami. 2017. “Changes in water consumption linked to heavy news media coverage of extreme climatic events.” Sci. Adv. 3 (10): e1700784. https://doi.org/10.1126/sciadv.1700784.
Rasifaghihi, N., S. S. Li, and F. Haghighat. 2020. “Forecast of urban water consumption under the impact of climate change.” Sustainable Cities Soc. 52 (Jan): 101848. https://doi.org/10.1016/j.scs.2019.101848.
Reed, R., and R. J. Marksii. 1999. Neural smithing: Supervised learning in feedforward artificial neural networks. Cambridge, MA: Massachusetts Institute of Technology Press.
Romano, G., N. Salvati, and A. Guerrini. 2014. “Estimating the determinants of residential water demand in Italy.” Water 6 (10): 2929–2945. https://doi.org/10.3390/w6102929.
Rousseeuw, P. J. 1987. “Silhouettes: A graphical aid to the interpretation and validation of cluster analysis.” J. Comput. Appl. Math. 20 (Nov): 53–65. https://doi.org/10.1016/0377-0427(87)90125-7.
Rumelhart, D. E., G. E. Hinton, and R. J. Williams. 1986. “Learning representations by back-propagating errors.” Nature 323 (6088): 533–536. https://doi.org/10.1038/323533a0.
Sant’Ana, D., and P. Mazzega. 2018. “Socioeconomic analysis of domestic water end-use consumption in the Federal District, Brazil.” Sustainable Water Resour. Manage. 4 (4): 921–936. https://doi.org/10.1007/s40899-017-0186-4.
Sauri, D. Forthcoming. “The decline of water consumption in Spanish cities: Structural and contingent factors.” Int. J. Water Resour. Dev. https://doi.org/10.1080/07900627.2019.1634999.
Schleich, J., and T. Hillenbrand. 2009. “Determinants of residential water demand in Germany.” Ecol. Econ. 68 (6): 1756–1769. https://doi.org/10.1016/j.ecolecon.2008.11.012.
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.
Solomatine, D., L. M. See, and R. J. Abrahart. 2009. “Data-driven modelling: Concepts, approaches and experiences.” In Practical hydroinformatics, 17–30. Berlin: Springer.
Souza, S., and F. de C. Neves. 2002. Seca [Drought]. Fortaleza, Brazil: Edições Demócrito Rocha.
Tyralis, H., G. Papacharalampous, and A. Langousis. 2019. “A brief review of random forests for water scientists and practitioners and their recent history in water resources.” Water 11 (5): 910–947. https://doi.org/10.3390/w11050910.
UNESCO. 2018. Nature-based solutions for water: Development report. Paris: UNESCO.
UNESCO-WWAP (World Water Assessment Programme). 2019. The United Nations world development report 2019: Leaving no one behind. Paris: UNESCO.
Vesanto, J., and E. Alhoniemi. 2000. “Clustering of the self-organizing map.” IEEE Trans. Neural Networks 11 (3): 586–600. https://doi.org/10.1109/72.846731.
Vijai, P., and P. B. Sivakumar. 2018. “Performance comparison of techniques for water demand forecasting.” Procedia Comput. Sci. 143: 258–266. https://doi.org/10.1016/j.procs.2018.10.394.
Villarin, M. C., and V. F. Rodriguez-Galiano. 2019. “Machine learning for modeling water demand.” J. Water Resour. Plann. Manage. 145 (5): 04019017. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001067.
Witten, I. H., and E. Frank. 2016. Data mining: Practical machine learning tools and techniques. Burlington, MA: Morgan Kaufmann.
Xiao, Y., L. Fang, and K. W. Hipel. 2018. “Agent-based modeling approach to investigating the impact of water demand management.” J. Water Resour. Plann. Manage. 144 (3): 04018006. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000907.
Yajima, H., and J. Derot. 2017. “Application of the Random Forest model for chlorophyll- forecasts in fresh and brackish water bodies in Japan, using multivariate long-term databases.” J. Hydroinf. 20 (1): 206–220. https://doi.org/10.2166/hydro.2017.010.
Yousefi, P., S. Shabani, H. Mohammadi, and G. Naser. 2017. “Gene expression programing in long term water demand forecasts using wavelet decomposition.” Procedia Eng. 186: 544–550. https://doi.org/10.1016/j.proeng.2017.03.268.
Ziegler, A., and I. R. König. 2014. “Mining data with random forests: current options for real-world applications.” Wiley Interdiscip. Rev.: Data Min. Knowl. Discovery 4 (1): 55–63. https://doi.org/10.1002/widm.1114.
Information & Authors
Information
Published In
Journal of Water Resources Planning and Management
Volume 147 • Issue 1 • January 2021
Copyright
© 2020 American Society of Civil Engineers.
History
Received: Oct 7, 2019
Accepted: Aug 7, 2020
Published online: Oct 31, 2020
Published in print: Jan 1, 2021
Discussion open until: Mar 31, 2021
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.