Model outputs and model code for a mining water-use model, 2020, United States excluding territories

Two machine learning (ML) models (random forest [RF] and light gradient boosting machine [LGB]) were developed to estimate water use for mining for all 50 States for each month of 2020. The two ML models were trained using water use data available from 2019 to 2020 for 30 states along with multiple predictor variables on energy resources, mineral production, and mining employment. The LGB models performed marginally better than the RF models at predicting the validation data, so only model outputs for the LGB models are included in this data release, but the model code included in this data release has functionality for running the RF models. This data release is comprised of four zipped archives: mi_model_code.zip contains the model code in R; mi_county_2020_mgd_outputs.zip contains mining water use estimates by county; mi_huc12a_2020_mgd_outputs.zip contains mining water use estimates by 12-digit hydrologic unit code (HUC12) watershed boundaries as defined in Luukkonen and others (2024); mi_huc12b_2020_mgd_outputs.zip contains HUC12 watershed boundaries as defined in Blodgett (2023). The HUC12 watershed boundaries, as defined in Luukkonen and others (2024) and referred to as “HUC12a” in this data release, are used for the USGS Water Availability and Use Science Program that published water-use estimates for public-supply, irrigation, and thermoelectric categories. The HUC12 watershed boundaries, as defined in Blodgett (2023) and referred to as “HUC12b” in this data release, are used for the USGS Integrated Water Availability Assessments (IWAAs). Within each zipped archive are a series of files described below. mi_model_code.zip – see the README for details on file structure and instructions on how to run the model. mi_county_2020_mgd_outputs.zip: mi_county_tot_2020_mgd.csv – a CSV file of monthly estimated mining total water-use for 2020 by county in million gallons per day. mi_county_gw_tot_2020_mgd.csv – a CSV file of monthly estimated mining groundwater-use for 2020 by county in million gallons per day. mi_county_gw_fr_2020_mgd.csv – a CSV file of monthly estimated mining fresh groundwater-use for 2020 by county in million gallons per day. mi_county_gw_sal_2020_mgd.csv – a CSV file of monthly estimated mining saline groundwater-use for 2020 by county in million gallons per day. mi_county_sw_tot_2020_mgd.csv – a CSV file of monthly estimated mining surface water-use for 2020 by county in million gallons per day. mi_county_sw_fr_2020_mgd.csv – a CSV file of monthly estimated mining fresh surface water-use for 2020 by county in million gallons per day. mi_county_sw_sal_2020_mgd.csv – a CSV file of monthly estimated mining saline surface water-use for 2020 by county in million gallons per day. mi_county_fr_tot_2020_mgd.csv – a CSV file of monthly estimated mining freshwater-use for 2020 by county in million gallons per day. mi_county_sal_tot_2020_mgd.csv – a CSV file of monthly estimated mining saline water-use for 2020 by county in million gallons per day. mi_huc12a_2020_mgd_outputs.zip: mi_huc12a_tot_2020_mgd.csv – a CSV file of monthly estimated mining total water-use for 2020 by HUC12a (Luukkonen and others, 2024) in million gallons per day. mi_huc12a_gw_tot_2020_mgd.csv – a CSV file of monthly estimated mining groundwater-use for 2020 by HUC12a (Luukkonen and others, 2024) in million gallons per day. mi_huc12a_gw_fr_2020_mgd.csv – a CSV file of monthly estimated mining fresh groundwater-use for 2020 by HUC12a (Luukkonen and others, 2024) in million gallons per day. mi_huc12a_gw_sal_2020_mgd.csv – a CSV file of monthly estimated mining saline groundwater-use for 2020 by HUC12a (Luukkonen and others, 2024) in million gallons per day. mi_huc12a_sw_tot_2020_mgd.csv – a CSV file of monthly estimated mining surface water-use for 2020 by HUC12a (Luukkonen and others, 2024) in million gallons per day. mi_huc12a_sw_fr_2020_mgd.csv – a CSV file of monthly estimated mining fresh surface water-use for 2020 by HUC12a (Luukkonen and others, 2024) in million gallons per day. mi_huc12a_sw_sal_2020_mgd.csv – CSV file of monthly estimated mining saline surface water-use for 2020 by HUC12a (Luukkonen and others, 2024) in million gallons per day. mi_huc12a_fr_tot_2020_mgd.csv – a CSV file of monthly estimated mining freshwater-use for 2020 by HUC12a (Luukkonen and others, 2024) in million gallons per day. mi_huc12a_sal_tot_2020_mgd.csv – CSV file of monthly estimated mining saline water-use for 2020 by HUC12a (Luukkonen and others, 2024) in million gallons per day. mi_huc12b_2020_mgd_outputs.zip: mi_huc12b_tot_2020_mgd.csv – a CSV file of monthly estimated mining total water-use for 2020 by HUC12b (Blodgett 2023) in million gallons per day. mi_huc12b_gw_tot_2020_mgd.csv – a CSV file of monthly estimated mining groundwater-use for 2020 by HUC12b (Blodgett 2023) in million gallons per day. mi_huc12b_gw_fr_2020_mgd.csv – a CSV file of monthly estimated mining fresh groundwater-use for 2020 by HUC12b (Blodgett 2023) in million gallons per day. mi_huc12b_gw_sal_2020_mgd.csv – a CSV file of monthly estimated mining saline groundwater-use for 2020 by HUC12b (Blodgett 2023) in million gallons per day. mi_huc12b_sw_tot_2020_mgd.csv – a CSV file of monthly estimated mining surface water-use for 2020 by HUC12b (Blodgett 2023) in million gallons per day. mi_huc12b_sw_fr_2020_mgd.csv – a CSV file of monthly estimated mining total fresh surface water-use for 2020 by HUC12b (Blodgett 2023) in million gallons per day. mi_huc12b_sw_sal_2020_mgd.csv – a CSV file of monthly estimated mining saline surface water-use for 2020 by HUC12b (Blodgett 2023) in million gallons per day. mi_huc12b_fr_tot_2020_mgd.csv – a CSV file of monthly estimated mining freshwater-use for 2020 by HUC12b (Blodgett 2023) in million gallons per day. mi_huc12b_sal_tot_2020_mgd.csv – a CSV file of monthly estimated mining saline water-use for 2020 by HUC12b (Blodgett 2023) in million gallons per day.

[
  "010:12"
]

{
  "fn": "Ryan R McShane",
  "@type": "vcard:Contact",
  "hasEmail": "mailto:rmcshane@usgs.gov"
}

[
  {
    "@type": "dcat:Distribution",
    "title": "Digital Data",
    "format": "XML",
    "accessURL": "https://doi.org/10.5066/P13CH3KR",
    "mediaType": "application/http",
    "description": "Landing page for access to the data"
  },
  {
    "@type": "dcat:Distribution",
    "title": "Original Metadata",
    "format": "XML",
    "mediaType": "text/xml",
    "description": "The metadata original format",
    "downloadURL": "https://data.usgs.gov/datacatalog/metadata/USGS.68a8ca58d4be0263357942d7.xml"
  }
]

[
  "USGS:68a8ca58d4be0263357942d7",
  "gradient boosting machine",
  "inlandWaters",
  "machine learning",
  "mining",
  "modeling",
  "random forest",
  "water availability",
  "water resources",
  "water supply and demand",
  "water use"
]

{
  "name": "U.S. Geological Survey",
  "@type": "org:Organization"
}

[
  "geospatial"
]