{D602E7C9-7F53-4C24-8237-746FD3A82CE8} 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 2025-02-13 ISO 19115 Geographic Information - Metadata ISO 19115:2003/Cor.1:2006(E) EnviroAtlas -- Green Bay, Wisconsin -- Meter-Scale Urban Land Cover (MULC) Data (2010) 2017-09-05 publication U.S. EPA Office of Research & Development (ORD) - National Exposure Research Laboratory (NERL) Research Triangle Park NC publisher US Environmental Protection Agency (US EPA) originator The Green Bay, WI Meter-Scale Urban Land Cover (MULC) dataset comprises 936 km2 around the city of Green Bay, surrounding towns, tribal lands and rural areas in Brown and Outagamie Counties. These leaf-on LC data and maps were derived from 1-m pixel, four-band (red, green, blue, and near-infrared) aerial photography acquired from the United States Department of Agriculture (USDA) National Agriculture Imagery Program (NAIP) on three dates in 2010: July 3, July 25, and August 5. LiDAR data collected on November 18, 2010 was integrated for the Brown County portion. Eight land cover classes were mapped: water, impervious surfaces, soil and barren land, trees and forest, grass and herbaceous non-woody vegetation, agriculture, and wetlands (woody and emergent). Wetlands were copied from the best available existing wetlands data. Analysis of a random sampling of 566 photo-interpreted land cover reference points yielded an overall user's accuracy (MAX) of 90.4% and a fuzzy user's accuracy (RIGHT) of 94.1%. 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). The purpose of the MULC data is to provide a detailed snapshot of the urban environment and ecosystem for analysis of multiple human and ecosystem health metrics and services. This analysis is performed typically by U.S. Census block group. Greenspace and impervious surface land cover classes figure prominently. Land cover maps are integral to sound, scientific decision making and effective stewardship. A high-resolution urban land cover (LC) map quantitatively and qualitatively represents the physical environment and ecosystem matrix of a city. Land cover varies at a fine scale in urban environments, and the existing NLCD (National Land Cover Database, www.mrlc.gov) land cover maps at 30 m spatial resolution are too coarse to measure many urban phenomena. There are many possible applications, for example: - Knowing the exact location and size of green and gray spaces; - Identifying highly impervious areas that would most benefit from additional trees and other vegetation to mitigate surface runoff and urban heat island effects; - Measuring the width of urban riparian buffers; - Locating potential wildlife corridors, gaps and linkages; - Planning park development for maximum benefits. 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 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 asNeeded Ecology Ecosystem Environment Health Impact Land theme EPA GIS Keyword Thesaurus Agriculture Biophysical Communities Ecosystem Services EnviroAtlas Environment Environmental Atlas Green Space Land Land Cover Surface Water Water Wetlands theme EnviroAtlas Wisconsin Green Bay, WI 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 environment geoscientificInformation imageryBaseMapsEarthCover -88.361895 -87.853055 44.342264 44.653172 2010-01-01 true Entity and Attribute Information Entity and Attribute Overview: For easier readability, this XML metadata can be opened in a text editor (e.g., Notepad). For more information about EnviroAtlas data, go to https://www.epa.gov/enviroatlas/enviroatlas-fact-sheets. The Green Bay, WI Meter-Scale Urban Land Cover (MULC) dataset includes data for the Green Bay Urban Statistical Area, as defined by the US Census Bureau, plus a 1-km buffer. The total area classified was 936 square kilometers, with approximately 75% of the study area in Brown County and 25% in Outagamie County. The area classified in Outagamie County includes the Oneida Nation of Wisconsin tribal lands. The land cover classification was developed using 42 Digital Orthophoto Quarter Quadrangle ("quarter quads") acquired from the United States Department of Agriculture (USDA) National Agriculture Imagery Program (NAIP). Each quarter quad included four bands (visible RGB plus near-infrared) with one-meter spatial resolution. The imagery data were collected on three dates during the summer of 2010: July 3 (30 quarter quads), July 25 (11 quarter quads), and August 5 (1 quarter quad). In addition to the NAIP imagery, LiDAR point cloud data were incorporated into the classification for 658 square kilometers, all in Brown County. This LiDAR data was collected by Aerometric, Inc. on November 18, 2010. The nominal pulse spacing was 1.2 m. Up to four returns were collected per pulse, and the points were pre-classified into the following categories: "water," "ground," and "unclassified." A 1km-by-1km grid was overlaid on the study area, with a total of 936 grid cells intersecting the study area. Land cover classification was performed for each of these intersecting grid cells. LiDAR data was used in classifying a grid cell if data were available for the entire grid. If any portion of the grid cell lacked LiDAR data, only the NAIP imagery was used in the classification. A total of 658 grid cells had complete LiDAR coverage. The grid cells with only NAIP imagery available were classified using five bands: the four original NAIP bands (red, green, blue, near-infrared) plus the normalized difference vegetation index, which was calculated using the NAIP red and near-infrared bands. The grid cells with both NAIP imagery and LiDAR data available were classified using the five bands derived from the NAIP imagery plus seven bands derived from the raw LiDAR point clouds. To derive these additional bands, the tiles in the LiDAR dataset were re-projected into the coordinate system of the NAIP imagery (NAD_1983_UTM_Zone_16N) and then clipped to the boundaries of the 658 grid cells. The LiDAR point data were then imported into ArcGIS and converted from vector to raster data. The first LiDAR-derived band was the mean intensity of LiDAR points falling within each 1m pixel. The second band was height-above-ground. A canopy surface model (CSM) was created by taking the maximum z-value in each 1m pixel. A bare-earth digital elevation model (DEM) was calculated by averaging the z-values of LiDAR points classified as "ground" in the dataset. NoData values in the CSM and DEM rasters were estimated using an inverse-distance weighted interpolation algorithm. The height-above-ground band was calculated by subtracting the canopy surface model from the bare-earth elevation model. The third LiDAR band was the percentage of points with non-last returns (return value < total number of returns for the pulse). Areas with high percentages of LiDAR points with non-last returns are highly correlated with trees and forest. The fourth band was the probability of being a pixel being water. Pixels that contained LiDAR points classified as "water" in the dataset were assigned a probability of one. Pixels with no LiDAR returns were assigned a probability based on the number of surrounding pixels that also had no LiDAR returns. Large areas with no LiDAR returns are highly correlated with bodies of water. The fifth band was distance to pixels with a high (> 50%) probability of being water. The sixth band was distance to pixels that contained LiDAR points classified as "ground" in the dataset. The seventh was a band with values corresponding to the LiDAR classifications of the points falling within that pixel (bit 0 assigned to 1 if the pixel contained a point classified as "ground"; bit 1 assigned to 1 if the pixel contained a point classified as "water"; bit 2 assigned to 1 if the pixel contained a point classified as "other"). After extracting the imagery and LiDAR data for the 936 analysis grid cells, the grid cells were aggregated into larger analysis areas based on the individual NAIP quarter quads that they intersected. Analysis grid cells that intersected multiple NAIP quarter quads were split into sections and then merged into the NAIP-specific analysis areas. Land cover classification was performed on the NAIP-specific analysis areas. A total of eight land use / land cover (LULC) classes were mapped: water, impervious surfaces, soil and barren, tree and forest, grass and herbaceous, agriculture, and woody and emergent wetlands. The first six were classified using GeniePro 2.4, a machine-learning classification software program. Different methods were used to map the LiDAR-available and non-LiDAR available areas. In the latter, areas where the predominant background features were agriculture, soil, and grass were defined using hand-digitization tools. Then, individual layers of water, tree, and impervious surfaces were superimposed on the background. These layers were created in GeniePro by selecting appropriate training pixels. Solution files were then created in GeniePro, which were then used to map the individual classes throughout the study area. For the LiDAR-available areas, a single classification of water, impervious, tree, and grass was created using Genie. Areas of agriculture and soil were then hand-digitized. In each classification, errors were corrected using hand-digitization tools. At the completion of the classification process, all the individual classifications were mosaicked together. Wetland data for the study area was acquired from the National Wetland Inventory. Polygons corresponding to woody or emergent wetlands were extracted. Classified pixels falling within the boundaries of these polygons were extracted from the 6-class classification. Pixels initially classified as "grass and herbaceous" were reclassified as "emergent wetlands"; pixels initially classified as "tree and forest" were reclassified as "woody wetlands." **12/2016 UPDATE The prior published Green Bay, WI MULC data included areas beyond the study area boundary. In 2016, this land cover product was clipped to match the 2010 US Census Urban Area boundary plus 1 km buffer. (https://www.epa.gov/enviroatlas/enviroatlas-spatial-extents). Please make sure to use the most up to date version of this land cover product. An accuracy assessment was performed on the 6-class classification (excluding the woody and emergent wetlands classes) on the area falling within the Green Bay Urban Statistical Area plus 1-km buffer. A random sample of 600 pixels was selected from the classification. An analyst who had not been involved in generating the land cover map performed photo interpretation for these 600 validation points. Using the NAIP imagery as well as ancillary imagery (e.g. Google Satellite and Street Views and Bing Aerial and Birdseye views), the photo-interpreter evaluated the land cover class of the random point plus the classes of its eight immediate neighbors. If the land cover class of the random point was not also the class of five of the eight neighboring pixels, then the area was considered to be insufficiently homogeneous and the random point was excluded from the accuracy assessment. A total of 34 points were excluded from the Green Bay accuracy assessment. For the remaining 566 points, the classification values were extracted from the 6-class classification map. The classification values and interpretation values were used to create the following confusion matrix. For easier readability, this XML metadata can be opened in a text editor (e.g., Notepad) and the confusion matrix may be copied from text editor to an Excel spreadsheet. Confusion matrices can also be viewed in original formatting by opening in ArcCatalog: RASTER_TXT Agricult Grass_Herb Impervious SoilBarren TreeForest Water N(n) Users Accuracy Errors of Commission Agricult 176 11 0 0 1 0 188 93.62 6.38 Grass_Herb 4 104 3 2 13 0 126 82.54 17.46 Impervious 0 3 56 1 0 0 60 93.33 6.67 SoilBarren 0 0 1 3 0 0 4 75.0 25.0 TreeForest 2 6 2 0 101 0 111 90.99 9.01 Water 0 0 0 0 0 77 77 100.0 0.0 N(n) 182 124 62 6 115 77 566 Producers Accuracy 96.7 83.87 90.32 50.0 87.83 100.0 Errors of Omission 3.3 16.13 9.68 50.0 12.17 0.0 OVERALL ACCURACY 91.34 The initial overall accuracy was 91.3%. The high accuracy was due in part to the fact that the agriculture class, comprising approximately 34% of the study area was digitized by hand. Moreover, the availability of LiDAR data helped improve the accuracy of some classes, especially water, trees, and impervious surfaces. The class with the lowest user's accuracy was soil and barren; however, the soil and barren class was quite small (representing <1% of the landscape) and only 4 of the 566 random points fell on pixels assigned to this class. Because this sample size does not yield a reliable estimate of the accuracy of the soil and barren class, an additional 50 soil points were chosen at random from the land cover classification. These were then evaluated using the photo-interpretation method described above. A total of 2 points of the 50 were excluded from the accuracy assessment on the grounds that the area was not sufficiently homogenous. The remaining 48 points were then included with the 566 others and a second confusion matrix was created. The final accuracy assessment resulted in confusion matrices for a non-fuzzy method (MAX) and a fuzzy method (RIGHT), both presented below. The fuzzy method allowed for uncertainty in the analyst's photo interpretation due to complex land cover characteristics. For example, for a point located within a pixel on land comprised of patchy grass and soil, the interpreter may have assigned a 4 for grass and a 3 for soil. This was accounted for by the RIGHT results, while MAX only accounted for the highest value recorded by the interpreter. The final error matrix (confusion matrix) below summarizes the results of the MAX accuracy assessment. Producer's and User's accuracies are reported, and the inter-class confusions are shown in the off-diagonal cells. For easier readability, this XML metadata can be opened in a text editor (e.g., Notepad) and the confusion matrix may be copied from text editor to an Excel spreadsheet. Confusion matrices can also be viewed in original formatting by opening in ArcCatalog. RASTER_TXT Agricult Grass_Herb Impervious SoilBarren TreeForest Water N(n) Users Accuracy Errors of Commission Agricult 176 11 0 0 1 0 188 93.62 6.38 Grass_Herb 4 104 3 2 13 0 126 82.54 17.46 Impervious 0 3 56 1 0 0 60 93.33 6.67 SoilBarren 0 4 7 41 0 0 52 78.85 21.15 TreeForest 2 6 2 0 101 0 111 90.99 9.01 Water 0 0 0 0 0 77 77 100.0 0.0 N(n) 182 128 68 44 115 77 614 Producers Accuracy 96.7 81.25 82.35 93.18 87.83 100.0 Errors of Omission 3.3 18.75 17.65 6.82 12.17 0.0 OVERALL USER'S ACCURACY 90.39 The error matrix (confusion matrix) below summarizes the results of the RIGHT accuracy assessment. Producer's and User's accuracies are reported, and the inter-class confusions are shown in the off-diagonal cells. For easier readability, this XML metadata can be opened in a text editor (e.g., Notepad) and the confusion matrix may be copied from text editor to an Excel spreadsheet. Confusion matrices can also be viewed in original formatting by opening in ArcCatalog. RASTER_TXT Agricult Grass_Herb Impervious SoilBarren TreeForest Water N(n) Users Accuracy Errors of Commission Agricult 179 8 0 0 1 0 188 95.21 4.79 Grass_Herb 0 111 3 2 10 0 126 88.1 11.9 Impervious 0 3 57 0 0 0 60 95.0 5.0 SoilBarren 0 2 0 50 0 0 52 96.15 3.85 TreeForest 1 4 2 0 104 0 111 93.69 6.31 Water 0 0 0 0 0 77 77 100.0 0.0 N(n) 180 128 62 52 115 77 614 Producers Accuracy 99.44 86.72 91.94 96.15 90.43 100.0 Errors of Omission 0.56 13.28 8.06 3.85 9.57 0.0 OVERALL FUZZY USER'S ACCURACY 94.14 References: Gopal, S. and Woodcock, C. 1994. Theory and Methods for Accuracy Assessment of Thematic Maps Using Fuzzy Sets. Photogrammetric Engineering and Remote Sensing 60(2), 181-188. 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/GBWI_MULC_tif.zip download Download The URL providing direct access to the downloadable dataset. download https://enviroatlas.epa.gov/arcgis/rest/services/Supplemental/Landcover_AllCommunities/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 are accurate to within 2-5 meters (EPA National Geospatial Data Policy [NGDP] Accuracy Tier 2). For more information, please see EPA's NGDP at https://www.epa.gov/geospatial/geospatial-policies-and-standards) 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 2010 4 band NAIP imagery of Green Bay, WI study area. Publisher: USDA-FSA-APFO Aerial Photography Field Office. Publication_Date: 20120130. Publication_Place: Salt Lake City, Utah. Link: http://www.fsa.usda.gov/FSA/apfoapp?area=home&subject=prog&topic=nai 2013-06-01T00:00:00 Acquired 2010 Brown County, WI LiDAR. Publisher: U. S. Geological Survey Earth Resources Observation and Science (EROS) Center. Publication Date: 2012. Publication Place: Sioux Falls, SD. Link: http://earthexplorer.usgs.gov 2013-06-01T00:00:00 See overview section for detailed processing workflow 2013-06-01T00:00:00 unknown 2029-02-13 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