Publication sur data.gouv.fr
High Resolution Layer: Grassland 2018 (raster 100m), Aug. 2020
The HRL Grassland 2018 100 m aggregate raster product provides a basic land cover classification with two thematic classes (grassland / non-grassland) at 100m spatial resolution, covering the EEA38 area and the United Kingdom. The production of the High Resolution Grassland layers was coordinated by the European Environment Agency (EEA) in the frame of the EU Copernicus programme.
The main High Resolution Grassland product is the Grassland layer. This grassy and non-woody vegetation baseline product includes all kinds of grasslands: managed grassland, semi-natural grassland and natural grassy vegetation. It is a binary status layer for the 2015 reference year mapping grassland and all non-grassland areas in 20m and (aggregated) 100m pixel size and, for the 2018 reference year, in 10m and (aggregated) 100m pixel size.
The 100 meter aggregate raster is provided as a full EEA38 and United Kingdom mosaic (fully conformant with the EEA reference grid).
Origine de la donnée :
The primary grassland status layer at 10m spatial resolution was produced with a hierarchical spatio-temporal classification of time features derived from Sentinel-2A+B time series (Level-2A data) using a Random Forest (RF) classifier with 200 trees. The selected time window ranges from 01-02-2018 to 30-11-2018, adapted to regional conditions where needed. In total, 137 statistical time features have been calculated and more than 700,000 samples were automatically collected from the LUCAS 2018 database, various CLMS products and additional manual sampling. The final product will be accompanied by a series of expert and reference products (PLOUGH, GRAVPI, Confidence Layer).
Quality assurance follows the ISO 9001:2015 standards for Quality Management and comprises of dedicated procedures of quality checks (QA breakpoints) during implementation of the production chain, in order to keep persistent control over the various stages of production, assure fitness-for-purpose of the…
Objectif : non renseigné