Dataset / Tabular

Reunion island - 2018, Land cover map (Pleiades) - 0.5m: La Réunion - Carte d'occupation du sol 2018 (Pleiades) - 0.5m

author(s) Dupuy, Stéphane - Gaetano, Raffaele
from French Agricultural Research Centre for International Development (CIRAD)
permalink open
themes
regions
  • Eastern Africa
  • Sub-Saharan Africa
  • Africa
  • World
citation

Pour utiliser ou référencer cette ressource préciser les mentions suivantes : <br>
<b>Dupuy, Stéphane; Gaetano, Raffaele, 2019, "Reunion island - 2018, Land cover map (Pleiades) - 0.5m", doi:10.18167/DVN1/WKAJZO, CIRAD Dataverse, V1 </b>

Publications and datasets provided via GARDIAN

Abstract

CIRAD's TETIS research unit is developing an automated mapping method based on the Moringa chain that minimizes interactions with users by automating most image analysis and processing.
<br>
The methodology uses jointly a Very High Spatial Resolution image (Spot6/7 or Pleiades) and one or more time series of High Spatial Resolution optical images such as Sentinel-2 and Landsat-8 for a classification combining segmentation and object classification (use of the Random Forest algorithm) driven by a learning database constituted from in situ collection and photo-interpretation.
<br>
The land use maps are produced as part of the GABIR project (Gestion Agricole des Biomasses à l'échelle de l'Ile de la Réunion) and are downloadable below or on CIRAD's spatial data catalogue in Réunion: <a href="http://aware.cirad.fr">http://aware.cirad.fr/</a&gt;
<br>
This Dataverse entry concerns the maps produced, for the year 2018, using a mosaic of Pleiades images to calculate segmentation (extraction of homogeneous objects from the image). We use a field database with a nested nomenclature with 3 levels of accuracy allowing us to produce a classification by level. The most detailed <b>level 3</b> distinguishing crop types has an overall accuracy of 87% and a Kappa index of 0.85. <b>Level 2</b>, distinguishing crop groups, has an overall accuracy of 92% and a Kappa index of 0.90. <b>Level 1</b>, distinguishing major land use groups, has an overall accuracy of 97% and a Kappa index of 0.95. A detailed sheet presenting the validation method and results is available for download.

Open original