Contribution of Sentinel-2 satellite images for habitat mapping of the Natura 2000 site 'Estuaire de la Loire' (France)

Habitat mapping is an essential tool to implement the European Habitats Directive 92/43/EEC and to manage the Natura 2000 protected areas network. However, their elaboration is most often based on field surveys, which are time-consuming and expensive when dealing with large areas. In this study, we aimed to evaluate the contribution of Sentinel-2 satellite images for mapping habitats of the Natura 2000 site 'Estuaire de la Loire'. We used 1,248 phytosociological plots to establish a complete typology of the study site's habitats. Locating these plots led us to select training areas that characterize 39 habitats to calibrate the Random Forest algorithm. We classified 11 single-date images spread evenly over a year and performed a multi-date classification of 9 images. We obtained high overall accuracy between 76.47% and 87.28% for the single-date image classifications and 98.7% for multi-date image classification. Our results demonstrate that Sentinel-2 images are appropriate for accurate habitat mapping and constitute a relevant tool to identify and conserve habitats of community interest.