Value and limits of GBIF botanical occurrence data in mapping mangrove cover via the KNN classification of Sentinel-2 images ; Valor y límites de los datos de registro botánico de la GBIF en el mapeo de la extensión de manglar mediante la clasificación KNN de imágenes de Sentinel-2

International audience ; In the current context, which emphasizes the importance of open-access data, this article aims to conduct the first evaluation of the effectiveness of the Global Biodiversity Information Facility’s (GBIF) database for training open-access multispectral satellite image classifiers to map mangrove extent. Six areas in Australia, Benin, Brazil, Colombia, Malaysia, and the USA were selected for their density of mangrove occurrence data and their proximity to other areas with wooded humid vegetation. Three open-access datasets were used: Sentinel-2 images, Google Earth’s high-resolution viewer, and occurrence data downloaded from the GBIF website. First, a k-nearest neighbors (KNN) algorithm was processed and trained with pixels surrounding the GBIF data. Then, the results were compared to those of an unsupervised classification (K-means). The accuracy of the two methods was assessed using error matrices from a double-blind photointerpretation of very high-resolution images obtained from Google Earth. The KNN algorithm achieved kappa indices ranging from 0.85 to 0.94, very similar to those of the unsupervised method (between 0.95 and 0.96). The GBIF possesses a suitable dataset for areas with information, which is why the community is encouraged to fill the main geographical gaps in its database ; En el contexto actual, que enfatiza la importancia de los datos de acceso abierto, este artículo busca realizar la primera evaluación de la efectividad de la base de datos de la Global Biodiversity Information Facility (GBIF) para entrenar clasificadores de imágenes satelitales multiespectrales de acceso abierto con el fin cartografiar la extensión de manglares. Se eligieron seis áreas en Australia, Benín, Brasil, Colombia, Malasia y EEUU por su densidad de datos de presencia de manglar y su proximidad con otras áreas de vegetación boscosa húmeda. Se utilizaron tres conjuntos de datos de acceso abierto: imágenes Sentinel-2, el visualizador de alta resolución de Google Earth y datos de presencia ...