ForestPaths: European tree genus map
Abstract This dataset provides an early access version of the European tree genus map at 10 m resolution for the year 2020, derived from Sentinel-1 and Sentinel-2 satellite data. The map distinguishes eight classes (Larix, Picea, Pinus,
Abstract
This dataset provides an early access version of the European tree genus map at 10 m resolution for the year 2020, derived from Sentinel-1 and Sentinel-2 satellite data. The map distinguishes eight classes (Larix, Picea, Pinus, Fagus, Quercus, other needleleaf, other broadleaf, and no trees) and is distributed as Cloud Optimized GeoTIFFs (COGs) over a 100 km grid in EPSG:3035 (ETRS89 / LAEA Europe).
The map was generated using a CatBoost model trained on forest plot inventories, citizen science observations, orthophoto interpretation, and LUCAS data, with additional features from DEM and climate datasets. Labels were filtered and aggregated to genus level to reduce noise.
Early access notice
This release is provided as an early access version. The map is still undergoing validation and fine-tuning, and a formal publication is planned. Updates and improvements may therefore be made in future releases.
We welcome feedback and contributions of additional training data to further improve the map.
Dataset description
- Resolution: 10m
- Format: Cloud Optimized GeoTIFFs (COGs)
- Tiling: 100km grid
- Coordinate reference system: EPSG: 3035 (ETRS89 / LAEA Europe)
Legend
0 – Larix
1 – Picea
2 – Pinus
3 – Fagus
4 – Quercus
5 – Other needleleaf
6 – Other broadleaf
7 – No trees
Methodology summary
The classification was performed using a CatBoost model trained on diverse reference sources [1-10]:
– National and regional plot inventories
– Citizen science observations
– Orthophoto interpretation
– LUCAS data
Training labels were filtered to reduce noise and aggregated to genus level. Predictor variables include annual statistics from Sentinel-1 and Sentinel-2, combined with auxiliary datasets on altitude (DEM) and climate.
Further details on the methodology will be made available in the product publication, which will follow this early access release.
Usage Notes
- CRS: EPSG:3035 (ETRS89 / LAEA Europe). Reprojection may be required for use with other datasets.
- Tiling scheme: Provided as 100 km × 100 km COG tiles. Users may mosaic tiles if needed.
- Classes: See legend above. Class 7 (“No trees”) includes cropland, grassland, built-up, and other non-tree areas.
- Early acce
📤 Share this page
Found this useful? Share it with your network.
Files are hosted on the source repository. Click download to access the full dataset.