Water End-Use Disaggregation for Six Nonresidential Facilities in Logan, Utah

Abstract

Most urban water-use monitoring, modeling, and conservation research has focused on a large but relatively homogenous group of residential water users. Commercial, industrial, and institutional (CII) facilities use large volumes of water, but their diversity in amounts, timing, locations, and other use factors makes them difficult to monitor and study. We monitored water use at four manufacturing and two assisted-care facilities in Logan, Utah, at 5-min and 5-s frequencies for up to 1 year. We used the data to disaggregate and quantify the temporal signature of end uses that included toilets, showers, landscape irrigation, industrial processes, and humidifiers. We also quantified variability in volume, duration, frequency, and timing of end uses, variability across facilities, and average water use per end use. Results identified water-use events both specific to CII users and in common with residential users. We shared findings with participating business representatives, who verified that results matched their understanding of water-use behaviors within their facilities.

Comparative Analysis of Supervised Classification Algorithms for Residential Water End Uses

“…This outcome is notably consistent with findings from broader studies, such as the one conducted by Attallah et al. (2023), which assessed the efficacy of multiple machine learning models across a wider range of households, further implying the generalizability of RF's superior performance in the context of residential water end‐use data. The decision tree‐based nature of the RF model contributes significantly to its adaptability and accuracy in classifying diverse water end uses, making it a dependable choice for utility managers and researchers aiming for precision in water use monitoring and conservation strategies.…”

“…To overcome this limitation, water consumption has been investigated at finer spatiotemporal resolutions (P. W. Mayer et al., 1999; P. Mayer et al., 2004; Roberts, 2005; Mead, 2008; González et al., 2008; Willis et al., 2010; Cominola et al., 2018; Bethke et al., 2021). Progress in smart water metering technology has improved the availability of water consumption data at fine resolutions (up to seconds), revealing considerable benefits for water demand modeling (Attallah et al., 2023; Cominola et al., 2015). Yet, despite the advantages of end‐use water consumption data, collecting and efficiently processing residential water consumption data remains challenging (Fagiani et al., 2015; Mazzoni et al., 2022).…”

Social barriers to open (water) data

“…This poses a major barrier to needed research about urban water consumption and the water-energy nexus at scales larger than individual water utilities or individual regions (Chini & Stillwell, 2017). Commercial and industrial water use data can be even more difficult to obtain than residential (Attallah et al, 2021). As presented in a typology of social water science data by Flint et al (2017), other categories of water data where use and access rules may pose a barrier to making them open are institutional water use data (e.g., the individual residential buildings of a university); water pricing data (as from municipal water providers); water quality incident data; and GIS shapefiles of a municipality's stormwater infrastructure.…”