CESBIO ALCD Snow masks

"CNES ALCD Snow masks" is a reference dataset for snow masks based on Sentinel-2 (L1C) images.

This dataset has been generated with the Active Learning for Cloud Detection (ALCD) software developed by CNES/Cesbio, that enables to generate any kind of reference mask using satellite images.

This procedure involves between 1 or 2 hours of work to generate each reference image : create reference points on the image ( land, cloud, snow...) manually, do the training (based on Random Forest of OTB) and prediction with ALCD, add new reference points for the most problematic areas, repeat new training/predictions as many times as necessary (usually 3-5 iterations), and finally, do a manual correction of persistent errors.

The dataset contains 10 folders each containing 1 geotiff file (scene) at 20m resolution for 110kmx110km size, 1 quicklook of the scene before and 1 quicklook after classification.

The content of pixels of the geotiff files follows the following naming rule :

     0 = nodata; 3 = Cloud; 5 = Land;  7 = Snow

Format of folder names:

      {location}_{tile}_{YYYMMDD} 

Where tile = reference Sentinel 2 tile (Cesbio post) , YYYYMMDD = date of Sentinel 2 acquisition, location = name of the site (ex: "PYR" = Pyrenees)

Example: PYR_31TCH_20191117