We have a cloud mask but we don't have reference data set to assess its accuracy. Without generating a reference dataset by ourselves is it possible to assess the cloud mask's accuracy?? For example; can we compare the spectral signatures of the rasters which were taken a cloud-free day and the mask applied raster? or can we look the spectral signature values correlation between 2 raster? (one is cloud-free, second is the mask applied raster?

1 Answer 1


As far as Sentinel-2 is concerned (as suggested by the tags), reference cloud masks exist. See for instance https://zenodo.org/record/1460961#.YSyWLkw69aQ

Still with Sentinel-2, it is also possible to compare two different cloud masks methodologies by comparing the smoothness of reflectance time series. We used such a criterion to compare options in atmospheric correction in the following reference .

  • I read almost all your papers since I was trying to compare the performance MAJA with an AI and deep learning based algorithm for my study. I was asked if there are no reference masks how can we assess the performance of MAJA masks? Can we still use the smoothness of reflectance time series for MAJA masked image and cloud-free RGB Sentinel-2 L1C(if it is available)?
    – RS_girl
    Aug 31, 2021 at 14:22
  • I'm sorry, I don't come often to stack exchange. please contact me via email, you'll find my adress in my papers.
    – O. Hagolle
    Nov 7, 2021 at 18:36

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.