Mask out clouds

The Mask out clouds block removes images from the image collection that contain more than the specified percentage of clouds. 

You can change the maximum cloud cover percentage from the default of 40%.

This block is only used with optical datasets. It isn't needed for radar datasets that can 'see' through clouds.

Default method

Removes all image scenes with more than the specified percentage of cloud cover.

Custom method (Sentinel 2 Cloud Score+)

Cloud Score+ is a machine learning algorithm used to find clouds / shadows and create an image mask for the Sentinel-2 Multispectral dataset.

Launched in 2023, Cloud Score+ provides a per-pixel “usability” score that can be used to mask or weight observations based on their overall quality.

To use Cloud Score+ when using the Sentinel-2 Multispectral dataset, select cloud_score_plus in the Method dropdown. 

The threshold determines the minimum “usability” score a pixel must have to be included. Any pixel with a score below this threshold is masked out (and therefore not included in the analysis). 

A score of 100 would indicate completely clear reference conditions, whereas a pixel with a score of 0 would be deemed to be fully occluded by cloud and therefore less usable.

Learn more: Create a cloud-free image of your area of interest