Search

The water service area dataset, derived from the National Boundary Dataset for public‐supply water systems in the United States, offers a detailed resolution surpassing county‐level assessments, emphasizing water‐centric land use. Crucial for linking populations and infrastructure to system withdrawals, it supports the creation of a national public‐supply water‐use model, enhancing accuracy in estimating water use and distinguishing between publicly supplied and self‐supplied domestic water use. Integrating tabular water system data strengthens the national water‐use model by enabling tracking of withdrawal locations, source water, and water quality. Evaluated against U.S. Census‐derived population datasets, 16 state‐provided water service area datasets, and two national land use datasets, the study covers 22,849 community water systems, excluding most small systems serving fewer than 1000 people. Robust correlations between water service areas (WSAs) and satellite‐sourced urban and exurban land use types facilitate tracking changes over time. A comparison of state and national datasets for population and WSAs reveals discrepancies ranging from 5% to 73% in state‐level populations and 0% to 167% in state‐level WSAs. Significant differences can be attributed to the exclusion of sizable incorporated and unincorporated areas in the state‐based datasets. Additional comparisons of major metropolitan areas exhibit differences ranging from 2% to 56%. [ABSTRACT FROM AUTHOR]

Estimation of human water withdrawals is more important now than ever due to uncertain water supplies, population growth, and climate change. Fourteen percent of the total water withdrawal in the United States is used for public supply, typically including deliveries to domestic, commercial, and occasionally including industrial, irrigation, and thermoelectric water withdrawal. Stewards of water resources in the USA require estimates of water withdrawals to manage and plan for future demands and sustainable water supplies. This study compiled the most comprehensive conterminous United States water withdrawal data set to date and developed a machine learning framework for estimating public supply withdrawals and associated uncertainty for the period 2000–2020. The modeling approach provides service area resolution estimates to allow for annual and monthly water withdrawal estimation while incorporating a complex array of driving factors that include hydroclimatic, demographic, socioeconomic, geographic, and land use factors. Model results reveal highly variable and lognormally distributed per‐capita water withdrawal, spanning from 30 to 650 gallons per capita per day (GPCD), across community, regional, and national scales, with pronounced seasonal variations. Analysis of estimated withdrawal trends indicates that the national annual average withdrawal experienced a decline at a rate of 0.58 GPCD/year during the period from 2000 to 2020. Model interpretation reveals a complex interplay between public supply withdrawal and key predictors, including population size, warm‐season precipitation, counts of large buildings and houses, and areas of urban and commercial land use. The developed models can forecast future public supply driven by various climate, demographic, and socioeconomic scenarios. Key Points: Consistent, reproducible estimates of monthly water withdrawals were generated at the spatial resolution of USA water service areasSpatial and temporal variability of public supply withdrawal is driven by a complex array of explanatory featuresAn operational machine learning framework was developed to estimate water withdrawals, prediction uncertainty, and feature importance [ABSTRACT FROM AUTHOR]