Forecasting urban household water demand with statistical and machine learning methods using large space-time data: A Comparative study. (April 2018)

• Record Type: Journal Article
• Authors: Duerr, Isaac; Merrill, Hunter R.; Wang, Chuan; Bai, Ray; Boyer, Mackenzie; Dukes, Michael D.; Bliznyuk, Nikolay
• Is Part Of: Environmental modelling & software. Volume 102(2018)
• Page Start: 29
• Page End: 38
• Publication Date: 2018-04
• Subjects: Predictive modeling -- Spatial modeling -- Time series -- Tree-based methods -- Uncertainty quantification -- Urban water use; Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2018.01.002
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: Forecasts of water use are crucial to efficiently manage water utilities to meet growing demand in urban areas. Improved household-level forecasts may be useful to water managers in order to accurately identify, and potentially target for management and conservation, low-efficiency homes and relative high-demand customers. Advanced machine learning (ML) techniques are available for feature-based predictions, but many of these methods ignore multiscale spatiotemporal associations that may improve prediction accuracy. We use a large dataset collected by Tampa Bay Water, a regional water wholesaler in southwest Florida, to evaluate an array of spatiotemporal statistical models and ML algorithms using out-of-sample prediction accuracy and uncertainty quantification to find the best tools for forecasting household-level monthly water demand. Time series models appear to provide the best short-term forecasts, indicating that the temporal dynamics of water use are more important for prediction than any exogenous features. Highlights: We evaluate the household-level monthly water use forecasts produced by a suite of statistical and machine learning models. Traditional water use forecasting methods are improved upon using machine learning and spatio-temporal models. Autoregressive and spatio-temporal models are shown to be highly accurate for one-month ahead forecasts. Accurate forecasts produced by the methods studied may be used to identify and target inefficient homes and high-demand users.