{"accessLevel": "public", "bureauCode": ["010:12"], "contactPoint": {"@type": "vcard:Contact", "fn": "Claudine Tobalske", "hasEmail": "mailto:claudine.tobalske@umontana.edu"}, "description": "This landcover raster was generated through a Random Forest predictive model developed in R using a combination of image-derived and ancillary variables, and field-derived training points grouped into 18 classes. Overall accuracy, generated internally through bootstrapping, was 72.7%. A series of post-modeling steps brought the final number of land cover classes to 28.", "distribution": [{"@type": "dcat:Distribution", "accessURL": "https://doi.org/10.5066/P14RKP3P", "description": "Landing page for access to the data", "format": "XML", "mediaType": "application/http", "title": "Digital Data"}, {"@type": "dcat:Distribution", "description": "The metadata original format", "downloadURL": "https://data.usgs.gov/datacatalog/metadata/USGS.22075a47-b3fb-4582-9b38-ca6941cefe5b.xml", "format": "XML", "mediaType": "text/xml", "title": "Original Metadata"}], "identifier": "http://datainventory.doi.gov/id/dataset/USGS_22075a47-b3fb-4582-9b38-ca6941cefe5b", "keyword": ["CMR", "Charles M. Russell National Wildlife Refuge", "Landcover", "Landsat Imagery", "Montana", "USGS:22075a47-b3fb-4582-9b38-ca6941cefe5b", "environment", "external research support", "geospatial datasets", "imageryBaseMapsEarthCover", "remote sensing"], "modified": "2026-08-11T00:00:00Z", "publisher": {"@type": "org:Organization", "name": "U.S. Geological Survey"}, "spatial": "-109.2871, 47.1575, -106.3538, 48.3324", "theme": ["geospatial"], "title": "Charles M. Russell National Wildlife Refuge Landsat 8 Landcover Classification in Relation to Greater Sage Grouse"}