2017–2019 Land Cover Map of Pyrénées-Atlantiques
Description
This archive contains a land cover map of the French department Pyrénées-Atlantiques (64) based on Sentinel-2 satellite images performed with iota² chain (https://framagit.org/iota2-project/iota2/). The algorithm used is a Random Forest performed on all L3A images of the 2017–2019 time period. The training and validation data that we used is a combination of Corine Land Cover (Copernicus), BD TOPO (IGN), Registre Parcellaire Graphique (IGN) and self performed photo-interpretation.
It is part of a work in progress and the comparison between different time series and preprocessing levels still need to be completed. Also, the lack of training data for the photo-interpreted classes 'landes basses' (low heath shrublands), 'landes hautes' (high heath shrublands) and 'landes à dynamique de boisement' (young-growth forest) leads to significantly lower results for these classes. They are still massively confused with other land covers like grasslands and broadleaf mature forests. Have a look at the confusion matrix provided in the archive. It is performed on a different dataset than the one used for training. We are looking forward to improving these results in the upcoming months.
The archive also contains a text file with the nomenclature and the Qgis style layer.
Files
classification_v1_64.zip
Files
(9.4 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:3742fa7d49b07c9ed0143f730dab9ed1
|
9.4 MB | Preview Download |