Skip to content

Forest loss driver: new round of Peru annotation#271

Open
favyen2 wants to merge 2 commits intomasterfrom
favyen/20260121-forest-loss-peru
Open

Forest loss driver: new round of Peru annotation#271
favyen2 wants to merge 2 commits intomasterfrom
favyen/20260121-forest-loss-peru

Conversation

@favyen2
Copy link
Collaborator

@favyen2 favyen2 commented Jan 21, 2026

This adds code that was used to populate a new Studio project for a new round of annotation of forest loss driver examples in Peru.

rslp/forest_loss_driver/scripts/peru_20260112/README.md documents the steps and what the various scripts do.

There is also a small fix to vessel attribute transform to work with recent rslearn API changes.

Copy link
Collaborator

@yawenzzzz yawenzzzz left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM! Just two minor comments.


Based on predictions in Peru over five-year period:
- Select 100 for each of logging/burned/none/river/airstrip
- Select 500 where max(probs) < 0.5
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggestion: add "from other categories" so that it's clear that they're targeting different categories

best_feat = candidate
best_distance = distance

if best_feat is None or best_distance is None or best_distance > 10:
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could this be too strict? I mean computing the distance between centroids of two geometries, is it likely that the window is within a polygon but their centroid distance is more than 10?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants