10.5281/zenodo.3884602
https://zenodo.org/records/3884602
oai:zenodo.org:3884602
Adrià, Descals
Descals
Adrià
0000-0003-1644-3036
CREAF
Serge, Wich
Wich
Serge
School of Biological and Environmental Sciences
Erik, Meijaard
Meijaard
Erik
Borneo Futures
David, Gaveau
Gaveau
David
Center for International Forestry Research
Stephen, Peedell
Peedell
Stephen
Joint Research Centre
Zoltan, Szantoi
Szantoi
Zoltan
Joint Research Centre
High resolution global industrial and smallholder oil palm map for 2019
Zenodo
2020
industrial
smallholder
oil palm
deep learning
global
2020-06-08
10.5281/zenodo.3884601
v0
Creative Commons Attribution 4.0 International
The data set contains 622 images of 100x100 km and covers the areas where oil palm plantations were detected at the global scale. The classification of oil palm plantations was firstly applied over a larger area where oil palm can potentially grow. The file 'grid.shp' contains the grid that covers the potential distribution of oil palm. The current data set, however, only contains the images where the presence of oil palm was confirmed. The file 'grid_withOP.shp' shows the 100x100 grid squares with presence of oil palm plantations. The classification images (in geotiff format) are the output of a convolutional neural network that takes Sentinel-1 and Sentinel-2 half-year composites as input data. The images have a spatial resolution of 10 meters and show three classes: 1) Industrial mature oil palm plantations, 2) Smallholder mature oil palm plantations, and 3) other land uses that are not mature oil palm. The file ‘Validation_points_GlobalOilPalmLayer_2019.shp’ includes the 13,252 points that were used to validate the product. Each point includes the attribute ‘Class’, which is the class assigned by visual interpretation, and the attribute ‘predClass, which reflects the predicted class.