Global forest management data at a 100m resolution for the year 2015

We provide four data records:

1.The reference data set as a comma-separated file ("reference_data_set.csv") with the following attributes: 

“ID” is a unique location identifier 

“Latitude, Longitude” are centroid coordinates of a 100m x 100m pixel. 

“Land_use_ID “is a land use class: 

11 - Naturally regenerating forest without any signs of human activities, e.g., primary forests.  

20 - Naturally regenerating forest with signs of human activities, e.g., logging, clear cuts etc.  

31 - Planted forest.  

32 - Short rotation plantations for timber.  

40 - Oil palm plantations.  

53 - Agroforestry. 

“Flag” identifies a data origin:  1- the crowdsourced locations, 2- the control data set, 0 – the additional experts' classifications following the opportunistic approach.

2. The 100 m forest management map in a geoTiff format with the classes presented - "FML_v3.2.tif ".

3. The predicted class probability from the Random Forest classification in a geoTiff format - "ProbaV_LC100_epoch2015_global_v2.0.3_forest-management--layer-proba_EPSG-4326.tif"

4. Validation data set as a comma-separated file ("validation_data_set.csv) with the following attributes: 

“ID” is a unique location identifier 

“pixel_center_x” , “pixel_center_y ” are centroid coordinates of a 100m x 100m pixel  in lat/lon projection 

“first_landuse_class “is a land use class, as in (1). 

“second_landuse_class “is a second possible land use class, as in (1), identified in case it was difficult to assign one class with high confidence.