The paper presents a harmonised pan-European forest/non-forest map based on Landsat imagery. This high resolution forest map is aimed to be consistent over Europe, independent of national borders, and it can be used for European level forest resource and spatial pattern analysis. The applied fully automatic forest mapping methodology employs publicly available Landsat satellite images and Corine Land Cover 2000 data. The classification process was carried out on a scene-by-scene basis for the target year 2000. The image analysis consisted of several steps such as image segmentation, cloud masking, clustering, adaptive spectral representative analysis, and supervised classification.
The methodology proved to be applicable for different bio-geographical regions and ecological conditions. Preliminary validation results state that the classification accuracy is at the level of 90% in central European conditions.
PEKKARINEN Anssi;
REITHMAIER Lucia;
STROBL Peter;
2009-01-07
Millpress
JRC43725
https://publications.jrc.ec.europa.eu/repository/handle/JRC43725,
| Name | Country | City | Type |
|---|
This document is only visible at the Commission level.
You are not authorized to publish or distribute it outside the European Commission.
This is a public document. You can share this publication.
Datasets
| ID | Title | Public URL |
|---|
Dataset collections
| ID | Acronym | Title | Public URL |
|---|
Scripts / source codes
| Description | Public URL |
|---|
Additional supporting files
| File name | Description | File type |
|---|