2017–2018 Land Cover Map of Pyrénées-Atlantiques

This archive contains:<br> <br> -A land cover map of the French department Pyrénées-Atlantiques (64) based on Sentinel-2 (L2A level) satellite images performed with iota² chain (https://framagit.org/iota2-project/iota2/). The algorithm used is Random Forest. The time series used ranges from 2017 to 2018. Since the first version of this classification, the collection of additional training data on the photo-interpreted classes 'landes basses' (low heath shrublands), 'landes hautes' (high heath shrublands) and 'landes hautes avec arbres' (high heath shrublands with young-growth forest) has led to minor to no significant improvement of the F-scores on these classes. Some are still massively confused with other land covers like grasslands and broadleaf mature forests. However, the number of pixels of these classes has been remarkably increased (more than doubled) and with it the visual quality of the map. -The training and validation data set in its 2018 and 2019 versions. It is a combination of Corine Land Cover (Copernicus), BD TOPO (IGN), Registre Parcellaire Graphique (IGN) and self-performed photo interpretation. -The stratification layer. -The confusion matrix. <br> <br> -The land cover map after post-treatments in which some classes are grouped and others are divided based on topography. The algorithm used is available here https://framagit.org/Schwaab/projet_predateurs64/-/blob/main/scripts/ClassificationPostProcess.py<br> <br> -The Qgis style layers.