A 10 m resolution urban green space map for major Latin American cities from Sentinel-2 remote sensing images and OpenStreetMap

Here we produced the first 10 m resolution urban green space (UGS) map for the main urban clusters across 371 major Latin American cities as of 2017. Our approach applied a supervised classification of Sentinel-2 satellite imagery and UGS samples derived from OpenStreetMap (OSM). The overall accuracy of this UGS map in 11 randomly selected cities was 0.87, evaluated by independently collected validation samples (‘ground truth’). We further improved mapping quality through a visual inspection and additional sample collection. The resulting UGS map enables studies to measure area, spatial configuration, and human exposures to UGS, facilitating studies about the relationship between UGS and human exposures to environmental hazards, public health outcomes, and environmental justice issues in Latin American cities.
UGS in this map series includes grass, shrub, forest, and farmland, and non-UGS included buildings, pavement, roads, barren land, and dry vegetation.
The UGS map series includes three sets of files: 
(1) binary UGS maps at 10 m spatial resolution in GEOTIFF format (UGS.zip), with each of the 371 cities being an individual map. Mapped value of 1 indicates UGS, 0 indicates non-UGS, and no data (with value of -32768) indicates areas outside the mapped boundary or water bodies; 
(2) a shapefile of mapped boundaries (Boundaries.zip). The boundary file contains city name, country name and its ISO-2 country code, and an ID field linking each city's boundary to the corresponding UGS map.
(3)  .prj files containing projection information for the binary UGS maps and boundary shapefile. The binary UGS maps are projected with World Geodetic System (WGS) 84 / Pseudo-Mercator projected coordinate system (EPSG: 3857), and the boundary shapefile is projected with WGS 1984 geographic coordinate system (EPSG: 4326)