Cloud Masking in Sentinel-3 SLSTR data
14 Jul 2020





Columns left to right: Sentinel-3 SLSTR images. Predicted probability that a particular pixel is cloud. Binary cloud mask.​​

Collaborating Facility: RAL Space

This project aims to use a machine learning approach to help alongside existing cloud masking approaches for the SLSTR to produce a high quality, versatile cloud mask. Such a mask will perform well in difficult images where the identification of cloudy pixels is complicated by other phenomena such as sea ice, snow, aerosols, sun glint etc. The project also aims to validate its approach against the retrieval of climate variables from satellite scenes, with the hope of showing increased performance in practical applications. ​

Contact: Jackson, Samuel (STFC,RAL,SC)