University of Vermont Spatial Analysis Laboratory 20201221 remote-sensing image High resolution land cover dataset for a multi-borough area in the outskirts of Pittsburgh, PA. Seven land cover classes were mapped: (1) tree canopy, (2) grass/shrub, (3) bare earth, (4) water, (5) buildings, (6) roads, and (7) other paved surfaces. The primary sources used to derive this land cover layer were 2015 LiDAR data and 2019 NAIP imagery. Ancillary data sources included GIS data provided by Pennsylvania Spatial Data Access (PASDA) or created by the UVM Spatial Analysis Laboratory. Object-based image analysis techniques (OBIA) were employed to extract land cover information using the best available remotely sensed and vector GIS datasets. OBIA systems work by grouping pixels into meaningful objects based on their spectral and spatial properties, while taking into account boundaries imposed by existing vector datasets. Within the OBIA environment a rule-based expert system was designed to effectively mimic the process of manual image analysis by incorporating the elements of image interpretation (color/tone, texture, pattern, location, size, and shape) into the classification process. A series of morphological procedures were employed to insure that the end product is both accurate and cartographically pleasing. Following the automated OBIA mapping a detailed manual review of the dataset was carried out at a scale of 1:2500 and all observable errors were corrected. This dataset was developed as part of the High Resolution Land Cover for Pittsburgh Watersheds project. As such, it represents a 'top down' mapping perspective in which tree canopy over hanging other features is assigned to the tree canopy class. At the time of its creation this dataset represents the most detailed and accurate land cover dataset for the area. This assessment was completed by the University of Vermont's Spatial Analysis Laboratory (SAL) with funding from CivicMapper. The methods used were developed by the SAL with funding from the USDA Forest Service for their Tree Canopy Assessment effort. Tree canopy assessments have been conducted for numerous communities throughout the U.S. where the results have been instrumental in helping to establishing tree canopy goals. Complete None planned -80.087437 -79.834921 40.459762 40.327552 None tree canopy Urban UTC Land cover ISO 19115 Topic Category imageryBaseMapsEarthCover None Pittsburgh Allegheny Pennsylvania None 2019 None None University of Vermont Spatial Analysis Laboratory Jarlath O'Neil-Dunne Director mailing and physical

Aiken Room 205

81 Carrigan Drive

Burlington VT 05405 US 802-656-3324 802-656-8683 joneildu@uvm.edu University of Vermont Spatial Analysis Laboratory in collaboration with CivicMapper. Esri ArcGIS 2.6.0.24783 No accuracy assessment was conducted, but the dataset was subject to a thorough manual quality control (QC). Accuracy assessments from previous UTC land cover datasets indicate that the use OBIA techniques in combination with a detailed QC yield an overall accuracy of 95% or better. Valid raster dataset. Complete coverage for the study area using the most recent boundary data. None Planimetric data Vector 12000 None NAIP None LiDAR Object based image analysis (OBIA) using a rule-based expert system Manual corrections to land cover classification Raster Pixel 0 0 landcover_2019_allegheny3rivers.tif UTC OID Internal feature number. ESRI Sequential unique whole numbers that are automatically generated. Count # pixels per land cover class Internal Value Land cover code UTC 2 Grass/Shrub 6 Road/Railroad 5 Building 4 Water 7 Other Paved Surfaces 3 Bare Soil 1 Tree Canopy Seven land cover classes were mapped: (1) tree canopy, (2) grass/shrub, (3) bare earth, (4) water, (5) buildings, (6) roads/railroads, and (7) other paved surfaces. 20201221 University of Vermont Spatial Analysis Laboratory Jarlath O'Neil-Dunne Director mailing and physical

81 Carrigan Drive

Aiken Center Room 205

Burlington VT 05405 US 802-656-3324 802-656-8683 joneildu@uvm.edu FGDC Content Standard for Digital Geospatial Metadata FGDC-STD-001-1998 local time