AI4Copernicus - Harmonization of pre-processed Time Series of Sentinel-2 data
The sercvice is focused on the production of monthly composites for agronomical time series of Sentinel-2 images. One of the challenges of crop type mapping at large scale is the definition of a regular temporal sampling grid to perform analysis in a standardized manner.
Harmonization of pre-processed Time Series of Sentinel-2 data: This pipeline processes an agronomic year of Sentinel-2 acquisition to extract 12 monthly composites based on the median of the spectral signature of the samples considered, allowing the definition of a harmonized time series reprojected on a standardized temporal grid.
- Creation of 12 monthly composites for an agronomical year or 1 monthly composite for a selected month.
- Mitigates the cloud coverage problem.
- Provides 12 tif images for each Sentinel-2 tile specified in the inputs.
- Code packaged in a Docker image and the service can be used as a Docker container.