396BB64F-7E84-4874-B9E0-426B4619A980 eng utf8 dataset dataset Anne Neale U.S. Environmental Protection Agency, Office of Research and Development-Sustainable and Healthy Communities Research Program, Nation Atlas for Sustainability Geospatial Data Owner (919) 541-3832 (919) 541-4329 109 T.W. Alexander Drive E243-05 Research Triangle Park NC 27709 neale.anne@epa.gov https://www.epa.gov/aboutepa/about-office-research-and-development-ord website information pointOfContact EnviroAtlas Coordinator U.S. Environmental Protection Agency, Office of Research and Development - Center for Public Health and Environmental Assessment (CPHEA), EnviroAtlas Geospatial Data Owner (919) 541-3832 109 T.W. Alexander Drive Research Triangle Park NC 27709 EnviroAtlas@epa.gov https://www.epa.gov/enviroatlas pointOfContact 2025-07-23 ISO 19139 Geographic Information - Metadata - Implementation Specification 2007 geometryOnly composite 82915 102039 Esri 8.1.2 EnviroAtlas - Percent Potential Wetland Area by 12-digit HUC for the Conterminous United States 2024-07-30 publication U.S. Environmental Protection Agency (U.S. EPA) originator U.S. EPA Office of Research and Development (ORD) - Center for Public Health and Environmental Assessment (CPHEA) Research Triangle Park, NC publisher mapDigital The Percentage Potential Wetland Area by HUC-12 (Pct_PWA) layer shows areas where conditions may be suitable for wetland restoration or creation at a 10-m resolution. Since the 1600's, an estimated 53% of wetlands in the Conterminous United States have been lost, with many areas being converted for agricultural or urban use. The ecosystems services provided by wetlands are extremely valuable, providing flood attenuation, water filtration, nutrient sequestration, vital habitat, and many others. Wetland restoration or creation can help restore these benefits for the surrounding community. There are several government and community projects that can utilize these data to assist in site selection for wetland restoration projects. This layer was created using the Random Forest (RF) machine learning algorithm in Google Earth Engine (GEE). The RF model utilized 17 data inputs to identify areas where attributes on the landscape are similar to the attributes found in existing wetlands. The input data for this layer fall into three categories: topographic variables, soils, and satellite imagery. Topographic - DEM's sourced from USGS 3D Elevation Program (10-m) -Elevation -Aspect -Slope -Compound Topographic Index (CTI) -Vertical Overland Flow Distance (VOFD) -Horizontal Overland Flow Distance (HOFD) -Pythagoras Overland Flow Distance (POFD) -Soils - Natural Resource Conservation Service's gNATSGO and gSSURGO products · Potential Wetland Soils (PWS) -European Space Agency's Sentinel-1 Synthetic Aperture Radar (10-m) Using these variables, the Random Forest model was run for each 2 digit Hydrologic Unit Code (HUC) in Google Earth Engine. The model used wetlands from the National Wetland Inventory (NWI) to create training data, masking out deep water areas such as the centers of lakes and rivers, and excluding estuarine and marine wetlands. For each HUC an equal number of wetland an non-wetland training points proportional to the size of the HUC were generated, with 30% of those points being reserved for accuracy assessment. The model results were then summarized to calculate the areal coverage of PWA within each HUC-12 watershed in the United States. This dataset was produced by the US EPA to support research and online mapping activities related to EnviroAtlas. EnviroAtlas (https://www.epa.gov/enviroatlas) allows the user to interact with a web-based, easy-to-use, mapping application to view and analyze multiple ecosystem services for the contiguous United States. The dataset is available as downloadable data (https://edg.epa.gov/data/Public/ORD/EnviroAtlas) or as an EnviroAtlas map service. Additional descriptive information about each attribute in this dataset can be found in its associated EnviroAtlas Fact Sheet (https://www.epa.gov/enviroatlas/enviroatlas-fact-sheets). This data layer summarizes areas on the contiguous United States that have biophysical characteristics that may support wetland habitat by area coverage within 12-digit hydrologic unit codes (HUC-12). The overall goal of EnviroAtlas is to employ and develop the best available science to map indicators of ecosystem services production, demand, and drivers for the nation. completed Anne Neale U.S. Environmental Protection Agency, Office of Research and Development-Sustainable and Healthy Communities Research Program, Nation Atlas for Sustainability Geospatial Data Owner (919) 541-3832 (919) 541-4329 109 T.W. Alexander Drive E243-05 Research Triangle Park NC 27709 neale.anne@epa.gov https://www.epa.gov/aboutepa/about-office-research-and-development-ord website information pointOfContact EnviroAtlas Coordinator U.S. Environmental Protection Agency, Office of Research and Development - Center for Public Health and Environmental Assessment (CPHEA), EnviroAtlas Geospatial Data Owner publisher asNeeded U.S. Environmental Protection Agency (U.S. EPA) originator Alabama Arizona Arkansas California Colorado Connecticut Delaware Florida Georgia Idaho Illinois Indiana Iowa Kansas Kentucky Louisiana Maine Maryland Massachusetts Michigan Minnesota Mississippi Missouri Montana Nebraska Nevada New Hampshire New Jersey New Mexico New York North Carolina North Dakota Ohio Oklahoma Oregon Pennsylvania Rhode Island South Carolina South Dakota Tennessee Texas United States Utah Vermont Virginia Washington Washington DC West Virginia Wisconsin Wyoming place EPA Place Names 2015-01-31 publication 12-digit HUCs Ecosystem Services EnviroAtlas Environment Environmental Atlas Land Cover Wetlands theme User 2022-01-11 publication Ecology Ecosystem Environment Water theme EPA GIS Keyword Thesaurus 2007-11-02 publication 020:072 020:121 theme Federal Program Inventory 2013-09-16 publication None. Please check sources, scale, accuracy, currency and other available information. Please confirm that you are using the most recent copy of both data and metadata. Acknowledgement of the EPA would be appreciated. EPA Public Domain License licenseUnrestricted https://edg.epa.gov/EPA_Data_License.html unclassified https://project-open-data.github.io/schema/#accessLevel vector eng utf8 Microsoft Windows 10 Version 10.0 (Build 22621) ; Esri ArcGIS 13.1.0.41833 true -128.007244 -65.25485 22.868654 51.64959 2016-01-01T00:00:00 2021-12-31T00:00:00 This dataset can be joined to the EnviroAtlas feature class NHDPlusV2_WBDSnapshot_EnviroAtlas_CONUS using the field 'HUC_12.' File Geodatabase Feature Class https://enviroatlas.epa.gov/download/CONUS_metrics_FGDB.zip download download https://enviroatlas.epa.gov/download/CONUS_metrics_CSV.zip download download https://www.epa.gov/enviroatlas/enviroatlas-data information information https://www.epa.gov/enviroatlas information information https://enviroatlas-epa.hub.arcgis.com/search?tags=EA-PWA information information dataset Tests for integrity have not been performed. EPA National Geospatial Data Policy Features have been reviewed by U.S. EPA EnviroAtlas Project Managers for public release. true Features represented have not been tested for completeness EPA National Geospatial Data Policy Features have been reviewed by U.S. EPA EnviroAtlas Project Managers for public release. true Nationwide digital elevation model (DEM) data were sourced from the U.S. Geological Survey (USGS) at 1/3 arc-second resolution from the agency’s 3D Elevation Program (3DEP). This product has an overall vertical accuracy of 0.82 m (root mean square error), with variance across the dataset (Stoker and Miller 2022). Missing data (‘NoData’) in DEM tiles were interpolated using the GDAL fillnodata Python script with a max distance of 15 pixels (GDAL/OGR contributors 2022). DEM tiles were mosaicked, projected to Albers Equal Area Projection at 10-m resolution, and clipped to a modified version of the U.S. Census Bureau’s 2021 U.S. state boundaries to include all available DEM data. The modified DEM data were used to calculate the Compound Topographic Index (CTI), the vertical component of the overland flow distance to channel (VOFD), the horizontal component of the overland flow distance to channel (HOFD) to channel, and the Pythagoras (i.e., straight line) component of the overland flow distance to channel (POFD) using Terrain Analysis Using Digital Elevation Models (TauDEM 5.3.7) Toolbox (Tarboton 2005). 2021-09-01T00:00:00 USGS 3DEP 10m National Map Download all states gSSURGO and gNATSGO files. Merge Component tables for all states to create CONUS product. Merge all Valu1 tables for CONUS. Merge all 10-m Mapunit rasters for gNATSGO and gSSURGO. Recode column "drainagecl" to: 1 - "Very poorly drained" and "Poorly Drained", 0 - all other classes. Recode column "hydricrating" to: 1 - "Yes", 0 - "No" or null. Create a new column where either recoded drainagecl or hydricrating are 1, then 1, else 0. Create another new column in which the comppct_r is multiplied by the binary drainagecl/hydricrating column. Summarize the Component table by mukey to Sum the percentage of component coverage (comppct_r) by Mapunit (mukey). Merge the resulting percentage coverage of qualifying drainagecl and hydricrating components by Mapunit Key to the Valu1 added table. Create a new column where if the drainagecl/hydricrating column had 0 but the pwsl1pomu column is greater than 0, input the pwsl1pomu value, else use the drainagecl/hydricrating percent coverage. Join the resulting table with percentage of wetland soils per mapunit to the CONUS 10-m mapunit raster. 2021-10-01T00:00:00 NRCS SSURGO and NATSGO Created Random Forest training dataset from the October 2021 National Wetland Inventory (NWI). Each state was downloaded and merged to produce a NWI product for the whole conterminous United States (CONUS). The following codes were assigned by wetland subclass: 1 - M1, M2, E1, E1; 2 - PE, PS, PR, PM, PF, PE, PA, Pf, L2, R4, Lh, Lc; 5 - R1, R2, R3, R5, L1, L. The feature class was converted to raster using Polygon to Raster, and the cell size was set to 10m. The raster was then reclassified to binary where the aforementioned classes were used - value 1 = non-wetland (0), value 2 = wetland (1), and value 5 = masked (NoData). 2021-10-30T00:00:00 National Wetland Inventory Access USGS 3DEP DEM resource on Google Earth Engine and use built-in tools to calculate elevation, aspect, and slope. 2021-11-30T00:00:00 USGS 3DEP 10m National Map Seamless Sentinel-1 images from January 1, 2016, through December 31, 2021 were composited and 10th, 50th, and 90th percentiles of those stacks for the VV, VH, and band ratio (VV/VH) were calculated in Google Earth Engine. 2021-11-30T00:00:00 Sentinel-1 SAR GRD: C-band Synthetic Aperture Radar Ground Range Detected Random Forest algorithm applied by 18 regional watersheds in U.S. Training and testing data points were generated randomly in Google Earth Engine, and used to train the Random Forest. The number of training points generated were based on 1 point per 475km2 per HUC-2. Equal number of points for the wetland and non-wetland classes were included. 70% of the training data were used to train the model and 30% were reserved for testing. 2022-01-31T00:00:00 ee.Classifier.smileRandomForest Each HUC-2 Random Forest model results were exported from Google Earth Engine, and loaded into ArcGIS Pro 2.8. The 18 regional watershed models were mosaicked into a single conterminous U.S. 10m product (Potential Wetland Areas, PWA). 2022-06-01T00:00:00 The resulting mosaicked model results (Potential Wetland Area, PWA) was then summarized by area coverage within each subwatershed in the U.S. (hydrologic unit code 12, HUC-12) using the ArcGIS Pro Zonal Statistics as Table tool. The SUM (total number of pixels with value = 1) was divided by the total count of HUC-12 pixels. 2022-08-01T00:00:00 EnviroAtlas_WBD_CONUS_AK_HI_PRVI asNeeded