Public supply water use reanalysis for the 2000-2020 period by HUC12, month, and year for the conterminous United States

The U.S. Geological Survey is developing national water-use models to support water resources management in the United States. Model benefits include a nationally consistent estimation approach, greater temporal and spatial resolution of estimates, efficient and automated updates of results, and capabilities to forecast water use into the future and assess model uncertainty. This data release contains data used in a machine learning model to estimate monthly water use for communities that are supplied by public-supply water systems in the conterminous United States for 2000-2020. This data release also contains associated scripts used to produce input features as well as model output values by 12-digit hydrologic unit code (HUC12).

This page includes the following files:
PS_HUC12_Tot_2000_2020.csv - a csv file with monthly public supply reanalysis of withdrawals from 2000-2020 by HUC12.
PS_HUC12_GW_2000_2020.csv -a csv file with estimated monthly public supply groundwater use for 2000-2020 by HUC12
PS_HUC12_SW_2000_2020.csv - a csv file with estimated monthly public supply surface water use for 2000-2020 by HUC12
     Note: 1) Groundwater and surface water fractions were determined using source counts as described in the 'R code that determines groundwater and surface water source fractions for public-supply water service areas, counties, and 12-digit hydrologic units' child item. 2) Some HUC12s have estimated water use of zero because no public-supply water service areas were modeled within the HUC.

The data release is organized into these items:
1. Machine learning model that estimates public supply deliveries for domestic and other use types - The public supply delivery model estimates total delivery of domestic, commercial, industrial, institutional, and irrigation (CII) water use for public supply water service areas within the conterminous United States. This item contains model input datasets, code used to build the delivery machine learning model, and output predictions.
2. Machine learning model that estimates total monthly and annual per capita public supply withdrawals - The public supply water use model estimates total monthly water withdrawals for 12-digit hydrologic units within the conterminous United States. This item contains model input datasets, code used to build the water use machine learning model, and output predictions.
3. National watershed boundary (HUC12) dataset for the conterminous United States, retrieved 10/26/2020 - Spatial data consisting of a shapefile with 12-digit hydrologic units for the conterminous United States retrieved 10/26/2020.
4. Python code used to determine average yearly and monthly tourism per 1000 residents for public-supply water service areas - This code was used to create a feature for the public supply model that provides information for areas affected by population increases due to tourism.
5. Python code used to download gridMET climate data for public-supply water service areas - The climate data collector is a tool used to query climate data which are used as input features in the public supply models.
6. Python code used to download U.S. Census Bureau data for public-supply water service areas - The census data collector is a geographic based tool to query census data which are used as input features in the public supply models.
7. R code that determines buying and selling of water by public-supply water service areas - This code was used to create a feature for the public supply model that indicates whether public-supply systems buy water, sell water, or neither buy nor sell water.
8. R code that determines groundwater and surface water source fractions for public-supply water service areas, counties, and 12-digit hydrologic units - This code was used to determine source water fractions (groundwater and/or surface water) for public supply systems and HUC12s.