2018 Forest Type (current)
This dataset presents a remote sensing-based approach for a countrywide mapping of the Dominant Leave Type (DLT) with the two classes broadleaved and coniferous in Switzerland. The spatial resolution is 10 m with the fraction of the class broadleaved. The classification approach incorporates a random forest classifier, explanatory variables from freely available Copernicus multispectral Sentinel-2, multi-temporal Sentinel-1 data and a Digital Terrain Model (DTM) based on Airborne Laser Scanning (ALS) (SwissAlti3D) data. The models were calibrated using digitized training polygons and independently validated data from the National Forest Inventory (NFI). Whereas high model overall accuracies (0.97) and kappa (0.96) were achieved, the comparison of the tree type map with independent NFI data revealed deviations in mixed stands.
Data 'Forest Type NFI 2018' available on request (lars.waser@wsl.ch).
Additional Information
| Field | Value |
|---|---|
| Metadata last updated | May 6, 2021 |
| Data last updated | April 23, 2021 |
| Created | April 23, 2021 |
| Format | GeoTIFF |
| License | Other (Specified in the description) |
| DOI | 10.16904/1000001.6 |
| Access Restriction | Level: Restricted to Same Organization Members |
| Publication State | |
| Size | 182.20 MB |