Behaviorally informed modeling of daily urban water demand: integrating environmental drivers, mobility, and online search activity

Abstract

Forecasting urban water demand requires approaches that account for both environmental variability and human behavior. Traditional models rely primarily on climatic drivers and assume stable consumption patterns, overlooking the rapid behavioral shifts triggered by social events, consumers’ attention, and environmental stress. The objective of this study is to develop and evaluate a behaviorally informed, event-aware framework for short-term urban water demand forecasting that explicitly integrates physical and social drivers. The proposed framework utilizes data from weather records, Meta mobility distributions, Google Trends search activity, and demand records from the North Okanagan Valley in British Columbia, Canada. By coupling data-driven modeling with interpretable Machine Learning (ML), the framework identifies environmental thresholds and behavioral triggers influencing consumption. The results underscore that integrating digital behavior indicators with climate ones improves forecasting performance, increasing R² from 0.79 to 0.85, while behavioral indicators alone achieve an R² of 0.70, highlighting their independent explanatory power. These findings emphasize the value of integrating real-time behavioral proxies into operational forecasting models, supporting more adaptive and socially aware water resource management. The framework is demonstrated using a real-world case study and is designed to be transferable to other urban systems where human activity strongly influences short-term demand dynamics.

Keywords

Attention informed modeling / Behavioral proxies / Google Trends / Urban water demand

References

[1] Hussen B, Mekonnen A, Pingale SM. Integrated water resources management under climate change scenarios in the sub-basin of Abaya–Chamo, Ethiopia. Model Earth Syst Environ, 2018, 4: 221-240

[2] House-Peters LA, Chang H. Urban water demand modeling: review of concepts, methods, and organizing principles. Water Resour Res, 2011

[3] Earth Tech Canada Inc, Sadiq WA, Karney B, University of Toronto (2005) Modeling water demand considering impact of climate change – a Toronto case study. J Water Manag Model 13:R223–06. https://www.chijournal.org/R223-06

[4] Niva V, Cai J, Taka M, Kummu M, Varis O. China’s sustainable water–energy–food nexus by 2030: impacts of urbanization on sectoral water demand. J Clean Prod, 2020, 251: 119755

[5] Fang X, Liu J, Zhou M, Zhang H, Zhao J. Review of the mechanism and methodology of water demand forecasting in the socio-economic system. Water, 2024, 16: 1631

[6] Kamyab H, Khademi T, Chelliapan S, SaberiKamarposhti M, Rezania S, Yusuf M, et al.. The latest innovative avenues for the utilization of artificial intelligence and big data analytics in water resource management. Results Eng, 2023, 20: 101566

[7] Taloma RJL, Cuomo F, Comminiello D, Pisani P. Machine learning for smart water distribution systems: exploring applications, challenges and future perspectives. Artif Intell Rev, 2025, 58: 120

[8] Pagano M, Santonastaso GF, Di Nardo A, Cuomo S, Schiano Di Cola V. Machine learning model for battle of water demand forecasting. Eng Proc, 2024, 69: 37

[9] Cominola A, Preiss L, Thyer M, Maier HR, Prevos P, Stewart RA, et al.. The determinants of household water consumption: a review and assessment framework for research and practice. npj Clean Water, 2023, 6: 11

[10] Di Mauro A, Cominola A, Castelletti A, Di Nardo A. Urban water consumption at multiple spatial and temporal scales: a review of existing datasets. Water, 2020, 13: 36

[11] Wiechman A, Alonso Vicario S, Anderies JM, Garcia M, Azizi K, Hornberger G. Institutional dynamics impact the response of urban socio-hydrologic systems to supply challenges. Water Resour Res, 2024, 60: 2023WR035565

[12] Alvisi S, Franchini M, Marsili V, Mazzoni F, Salomons E, Housh M, et al.. Battle of water demand forecasting. J Water Resour Plann Manage, 2025, 151: 04025049

[13] Zubaidi SL, Al-Bugharbee H, Alattabi AW, Ridha HM, Hashim K, Al-Ansari N, et al.. Forecasting urban water demand using hybrid metaheuristic algorithms for extracting artificial neural network hyperparameters. Sci Rep, 2024, 14: 24042

[14] Samuelsson O, Lindblom EU, Djupsjö K, Kanders L, Corominas L. Mobility data for reduced uncertainties in model-based WWTP design. Water Res X, 2025, 29: 100418

[15] Filho JV, Scortegagna A, Vieira APDSD, Jaskowiak PA. Machine learning for water demand forecasting: case study in a Brazilian coastal city. Water Pract Technol, 2024, 19: 1586-1602

[16] Wilby RL, Murphy C, O’Connor P, Thompson JJ, Matthews T. Google Trends indicators to inform water planning and drought management. Geogr J, 2024, 190: 12567

[17] Kam J, Stowers K, Kim S. Monitoring of drought awareness from Google Trends: a case study of the 2011–17 California drought. Weather Clim Soc, 2019, 11: 419-429

[18] Data for Good at Meta (2025) Data for Good at Meta. https://dataforgood.facebook.com. Accessed 7 April 2026

[19] Varol C, Hayrullahoglu G, Soylemez E, Sat NA, Varol E, TunarOzcan N. The movement pattern changes of population following a disaster: example of the Aegean Sea earthquake of October 2020. Int J Disaster Risk Reduct, 2024, 112: 104743

[20] Angın M, Bircan T, Korkmaz EE (2023) Earthquake in Turkey and its impact on business: an analysis of Facebook/Meta data. Oxford Centre for Technology and Development (OCTD) Earthquake Analysis Reports. https://kobocat.unhcr.org/media/original?media_file=imturkey%2Fattachments%2F0a03b9467be64673b19fc7c13fab7df5%2Ff41bcb58-4bba-4764-9b85-739516fd73d9%2FOCTD_-_Earthquake-Analysis-Reports-Turkey-compressed-10_42_25.pdf. Accessed 7 April 2026

[21] Ghannam S, Hussain F. Short-term water demand forecasting: a review. Australas J Water Resour, 2024, 28(1): 1-19

[22] Gössling S, Peeters P, Hall CM, Ceron JP, Dubois G, Lehmann LV, et al.. Tourism and water use: supply, demand, and security – an international review. Tourism Manag, 2012, 33(1): 1-15

[23] Maußner C, Oberascher M, Autengruber A, Kahl A, Sitzenfrei R. Explainable artificial intelligence for reliable water demand forecasting to increase trust in predictions. Water Res, 2025, 268: 122779

[24] Choudhary R, Kumar A, CP, Naik MM, Choudhury M, Khan NA (2025) Predicting water quality index using stacked ensemble regression and SHAP-based explainable artificial intelligence. Sci Rep 15:31139. https://doi.org/10.1038/s41598-025-09463-4

[25] Lundberg S, Lee SI (2017) A unified approach to interpreting model predictions. Preprint at https://arxiv.org/abs/1705.07874

[26] Google Maps (2024) Greater Vernon water service area and infrastructure map. https://www.google.com/maps. Accessed 7 Apr 2026

[27] Environment and Climate Change Canada (2026) Historical climate data. https://climate.weather.gc.ca. Accessed 7 April 2026

[28] Google Trends (2026) Google Trends. https://trends.google.com. Accessed 7 April 2026

Funding

Natural Sciences and Engineering Research Council (NSERC Canada) (ALLRP 570897-21)

Telus Inc.

RIGHTS & PERMISSIONS

The Author(s)