GSFC_AI4QC dataset

The dataset was used in the AI4QC project (Artificial Intelligence for Quality Control), in the context of cloud detection through semantic segmentation. It consists of a set of 27 reference cloud masks over NASA GSFC (coordinate reference system EPSG:32618) for various cloud conditions from September 2017 to November 2018. The cloud masks are associated to Sentinel-2 satellite data. The dataset is a smaller version of the GSFC dataset, where S2 L1C images were added, the cloud masks reclassified and rasterized (from Shapefiles to TiFF files). The new classes are the following: 0 - clear 1 - thick cloud 2 - thin cloud 3 - cloud shadow The "masks" folder contains the cloud masks. The folder "S2_images_true_color" contains RGB images combining the bands B04, B03 and B02 of Sentinel-2. These images have varying sizes with a resolution of 10m, matching the size and resolution of the corresponding cloud masks. The folder "S2_images_all_bands" contains one folder per Sentinel-2 band, itself containing the 27 scenes for that band. Their resolution follows the Sentinel-2 specifications: B02, B03, B04, B08: 10m B05, B06, B07, B8A, B11, B12: 20m B01, B09, B10: 60m The original GSFC dataset is available at https://data.mendeley.com/datasets/r7tnvx7d9g/1.