You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Jun 18, 2023. It is now read-only.
Make the multitemporal masking more configurable by doing the following:
Parameterize the span of multitemporal cloud filtering when using smooth_mask / lowess filtering.
Allow the critical values to be specific to the green & swir bands
User can pass a float or a tuple; float transformed to tuple of (float, float)
Allow the critical values to be data-driven
Example, 2 * np.std(y) where y is the green or swir1 bands
Blocker: I have no idea how to be clever about passing and evaluating a str containing a mathematical formula (Patsy won't cover all of the maths we might want to do)
The text was updated successfully, but these errors were encountered:
Make the multitemporal masking more configurable by doing the following:
span
of multitemporal cloud filtering when usingsmooth_mask
/lowess
filtering.2 * np.std(y)
wherey
is the green or swir1 bandsstr
containing a mathematical formula (Patsy won't cover all of the maths we might want to do)The text was updated successfully, but these errors were encountered: