{4c37f02a-0c91-49b2-b7df-82ea4a6b9750} eng; USA utf8 dataset EnviroAtlas Coordinator U.S. Environmental Protection Agency, Office of Research and Development-Sustainable and Healthy Communities Research Program, 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 2025-07-24 ISO 19115 Geographic Information - Metadata ISO 19115:2003/Cor.1:2006(E) EnviroAtlas - Estimated floodplain map for the Conterminous United States 2018-08-27 publication U.S. EPA Office of Research & Development (ORD) - National Exposure Research Laboratory (NERL) Research Triangle Park NC publisher U.S. Environmental Protection Agency (US EPA) originator Understanding the relationship between flood inundation and floodplains is critical for ecosystem and community health and well-being, as well as targeting floodplain and riparian restoration. Many communities in the United States, particularly those in rural areas, lack inundation maps due to the high cost of flood modeling. Only 60% of the conterminous United States has Flood Insurance Rate Maps (FIRMs) through the U.S. Federal Emergency Management Agency (FEMA). This EnviroAtlas dataset provides an estimate of the 100-year floodplain for the conterminous United States at 30-meter resolution to fill the gaps in the FIRM. The model hit rate for the CONUS was 0.79 compared to the FIRM, indicating that the model captured 79% of the 100-year floodplain identified by FEMA. This product provides complete coverage for the CONUS by identifying floodplains in areas without FIRMs, while also identifying floodplains in tributaries sometimes excluded by FEMA. More information can be found in the journal article (https://doi.org/10.1016/j.scitotenv.2018.07.353). 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 dataset is useful for evaluating the potential value of ecosystem services provided by floodplains. 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. These data are not meant to replace or supplement FEMA Flood Insurance Rate Maps. completed EnviroAtlas Coordinator U.S. Environmental Protection Agency, Office of Research and Development-Sustainable and Healthy Communities Research Program, 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 NOTPLANNED Ecosystem Environment theme EPA GIS Keyword Thesaurus Ecology Ecosystem Ecosystem Services EnviroAtlas Environment Environmental Atlas Exposure Hazards Surface Water Water theme EnviroAtlas 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 None https://edg.epa.gov/EPA_Data_License.html otherRestrictions Use Constraints: 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. otherRestrictions Access Constraints: None PUBLIC https://project-open-data.github.io/schema/#accessLevel Standard Technical Controls eng; USA climatologyMeteorologyAtmosphere elevation environment geoscientificInformation -128.02839229 -65.20336449 22.7348894 51.6773602 2018-06-04 true Entity and Attribute Information Entity and Attribute Overview: This spatially complete estimate of 100-year floodplain for the conterminous United States was developed using random forest classification with nationally available biophysical datasets. Four biophysical datasets were acquired (NLCD, DEM, SSURGO/STATSGO2, FEMA FIRM). Ten derivatives of these datasets were used as explanatory variables: overland flow distance, vertical overland flow distance, horizontal overland flow distance, vertical distance to channel, flood frequency class, fluvial class, NLCD, 5x5 DEM (5 by 5 moving window standard deviation of DEM), slope, and compound topographic index. The response variable was a binary raster of the FEMA FIRM zones. Zones [A, A99, AE, AH, AO, Open Water, V, VE] were classified as 1 (in the 100-year floodplain), zone X was classified as 0 (not in 100-year floodplain), and zones D and "area not included" were classified as NoData. All data were spatially aligned to match the extent and resolution (30-meter) of NLCD. A random forest model was trained for each hydrologic unit code level four (HUC-4) in the CONUS using 500,000 random pixels as samples. A sampling strategy was used to ensure that at minimum 20% of the samples in each HUC-4 were from the minority class (i.e., areas within the 100-year floodplain). Two HUC-4s had no FEMA FIRM coverage; therefore, models could not be developed. Models from adjacent HUC-4s were applied and the average result for each pixel from those models was used. All HUC-4 models were mosaiced to form a spatially complete national 100-year floodplain prediction. Following model training, an additional 500,000 random validation pixels were selected to assess the accuracy of our models (i.e., we used the FIRM as both a training and a validation dataset). The primary objective was to correctly classify pixels within the floodplain. Therefore, we examined the classification accuracy using precision (P), recall (R), and F1 score of the floodplain. Overall for the CONUS, precision was 0.78, recall was 0.79, and F1 was 0.78. These numbers varied geographically with typically better performance in the Eastern, Midwest, and Northwest US and poorest performance in the Southwest. This map completes floodplain coverage of the CONUS for quantifying ecosystems services provided by floodplains. These data are not meant to replace or supplement FEMA Flood Insurance Rate Maps. Entity and Attribute Detail Citation: https://www.epa.gov/enviroatlas/enviroatlas-fact-sheets EnviroAtlas Coordinator U.S. Environmental Protection Agency, Office of Research and Development-Sustainable and Healthy Communities Research Program, 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 distributor https://enviroatlas.epa.gov/download/Estimated_floodplain_CONUS.zip download Download The URL providing direct access to the downloadable dataset. download https://enviroatlas.epa.gov/arcgis/rest/services/Supplemental/Estimated_floodplain_CONUS_WM/ImageServer ESRI:ArcGIS API The endpoint of a web service to access the dataset (REST endpoint, WMS GetCapabilities URL, or a SOAP WSDL endpoint). webMapService https://www.epa.gov/enviroatlas/enviroatlas-data information Documentation URL for accessing related documents such as data dictionary, technical information about a dataset, developer documentation, etc. information https://www.epa.gov/enviroatlas information Home Page Alternative landing page used to redirect user to a contextual, Agency-hosted "homepage" for the Dataset or API information dataset Horizontal Positional Accuracy Report Data were collected using methods that have unknown accuracy (EPA National Geospatial Data Policy [NGDP] Accuracy Tier 10). For more information, please see EPA's NGDP at https://www.epa.gov/geospatial/epa-national-geospatial-data-policy Features represented have not been tested for completeness Features represented have not been tested for completeness Tests for integrity have not been performed. This lineage was generated by the FGDC CSDGM to 19139 transformation Acquired National Land Cover Database (NLCD) 2011. Publisher: U.S. Geological Survey. Publication_Date: 2015. Publication_Place: Sioux Falls, SD. Link: https://www.mrlc.gov/nlcd2011.php 2016-10-03T00:00:00 Acquired National Elevation Dataset (NED). Publisher: U.S. Geological Survey. Publication_Date: 1999. Publication_Place: Sioux Falls, SD. Link: https://nationalmap.gov/3DEP/ 2016-10-03T00:00:00 Acquired Soil Survey Geographic Database (SSURGO). Publisher: U.S. Department of Agriculture, Natural Resources Conservation Service. Link: https://websoilsurvey.nrcs.usda.gov/ 2016-10-03T00:00:00 Acquired U.S. General Soil Map (STATSGO2). Publisher: U.S. Department of Agriculture Natural Resources Conservation Service. Link: https://websoilsurvey.nrcs.usda.gov/ 2016-10-03T00:00:00 Acquired National Flood Hazard Layer (NFHL). Publisher: Federal Emergency Management Agency. Publication_Date: 20170313. Publication_Place: Washington, D.C. Link: https://www.fema.gov/national-flood-hazard-layer-nfhl 2017-06-27T00:00:00 Acquired compound topographic index (CTI), a 30m raster depicting an estimate of wetness, calculated by Tetra Tech for the EPA. 2016-10-03T00:00:00 Acquired National Watershed Boundary Dataset - 22 Mar 2011 version. Publisher: U.S. Geological Survey. Publication_Date: 2011. Publication_Place: Reston, VA Link: https://nhd.usgs.gov/wbd.html 2016-10-03T00:00:00 Using SAGA GIS 2.2.5, sinks were filled in the digital elevation model (DEM) from NED using the Planchon/Darboux method with a minimum slope of 0.01 degrees. 2016-10-13T00:00:00 A flow accumulation raster was created from the filled DEM and a threshold of 5,000 30m x 30m cells was used to define channels. Additionally, the DEM in coastal areas was extended by a single pixel and identified as a channel. That is we used the DEM to define the coastline. 2016-10-13T00:00:00 Using SAGA GIS 2.2.5 four distance to channel values (overland flow distance, vertical overland flow distance, horizontal overland flow distance, vertical distance to channel) were calculated using the filled DEM and derived channels for each HUC-4 plus a 5,000-meter buffer. A buffer was used around each HUC-4 to improve distance calculations along edges. Each variable was clipped to original HUC-4 boundary and a national mosaic was created. 2016-11-01T00:00:00 Flood frequency classes from soils data were categorized as a six-class 30-meter raster with classes of none, very rare, rare, occasional, frequent, and very frequent. SSURGO was used where available with STATSGO2 used elsewhere. 2016-12-22T00:00:00 The taxonomic subgroup of soils data were used to identify fluvial soils. A three-class 30-meter raster with classes of non-fluvial soils, soils of fluvial origin, and water was created. SSURGO was used where available with STATSGO2 used elsewhere. 2016-12-22T00:00:00 NLCD classes were reclassified to six classes: water, developed, forest, planted/cultivated, wetlands, and an additional class that included barren, shrub/scrub, grassland/herbaceous, and pasture/hay 2016-12-14T00:00:00 Using ArcGIS Desktop 10.4, a 5x5 focal standard deviation of the DEM was calculated. 2016-12-14T00:00:00 Using ArcGIS Desktop 10.4, slope in degrees was calculated. 2016-12-14T00:00:00 Converted FEMA Flood Insurance Rate Maps (FIRM) polygons to two-class 30-meter raster with classes of not in 100-year floodplain and 100-year floodplain. 2017-06-27T00:00:00 Using Python 2.7 and ArcPy, each national, explanatory variable (overland flow distance, vertical overland flow distance, horizontal overland flow distance, vertical distance to channel, flood frequency, fluvial, NLCD, 5x5 DEM, slope, compound topographic index) along with the response variable (FEMA) were clipped by HUC-4 and spatially aligned with the NLCD. 2017-12-18T00:00:00 Using H2O.ai 3.10.4.8 distributed random forest, a random forest algorithm was developed using 500,000 random samples of the 10 explanatory variables along with the response variable as training for each HUC-4. Default settings were used with the exception of mtries=4, max_depth=12, Ntrees=51, and a sampling strategy was used to ensure that at minimum 20% of the samples were from the minority class (i.e., area in 100-year floodplain). 2018-04-05T00:00:00 The random forest algorithm was applied to the explanatory variables to predict a spatially complete 100-year floodplain for each HUC-4. 2018-04-05T00:00:00 Two HUC-4s had no FEMA FIRM coverage. Models were calculated from all adjacent HUC-4s and the average result for each pixel from those models was used. 2018-04-14T00:00:00 Using ArcGIS Desktop 10.4 HUC-4 models were mosaiced to form a spatially complete national 100-year floodplain prediction. 2018-04-15T00:00:00 unknown 2029-07-23 This metadata was automatically generated from the FGDC Content Standard for Digital Geospatial Metadata standard (version FGDC-STD-001-1998) using the 2024-02-09T11:11:00 version of the FGDC CSDGM to ISO 19139 transform. EnviroAtlas Coordinator U.S. Environmental Protection Agency, Office of Research and Development-Sustainable and Healthy Communities Research Program, 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