{
"name":"AEF_II/Land_Cover_Africa_2016",
"title":"AEF_II/Land_Cover_Africa_2016",
"type":"Map Service",
"typeKeywords":["ArcGIS Server","Service","Map Service"],
"description":"The legend includes 10 generic classes that appropriately describe the land surface at 20m: \"trees cover areas\", \"shrubs cover areas\", \"grassland\", \"cropland\", \"vegetation aquatic or regularly flooded\", \"lichen and mosses / sparse vegetation\", \"bare areas\", \"built up areas\", \"snow and/or ice\" and \"open water\". It is a prototype built after reviewing various existing typologies, including LCCS and LCML, as well as global and national experiences (such as GLC-share, GlobeLand30, Global Surface Water product from JRC/EC, Global Human Settlement Layer from JRC/EC, Global Urban Footprint from DLR, Africover, and SERVIR-RMCD). The Random Forest (RF) and Machine Learning (ML) classification algorithms were also chosen to transform the cloud-free reflectance composites into a land cover map. The two maps resulting from both approaches were then combined either to select the best representation of a land cover class or, in case of unreliable LC class delineation, the reference layer (based on 1 year of Sentinel-2 A satellite observations from December 2015 to December 2016) is used to consolidate the land cover classification. ",
"extent":[[-857625.1912661069,9349495.606477242],[-2769420.9842649032,2939814.8705039932]],

"url":"https://wwfke-giscoe.wwfkenya.org/arcgis/rest/services/AEF_II/Land_Cover_Africa_2016/MapServer"
}