Repository navigation
feat(python): score an ensemble against an observed burnt area (#172) - #246
Merged
Merged
Conversation
…ireAPI#172) dice, brier_score and reliability take plain arrays: the members' burnt areas or the burn-probability map, and a boolean map of what burnt. Dice and Brier give one value per member on [member, y, x] input, so the ensemble can be compared with its members.
filippi
approved these changes
Oct 31, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds three helpers to score an ensemble against an observed burnt area, the first next step listed in my #172 comment:
dice(burnt, observed): overlap 2|A ∩ B| / (|A| + |B|), one value per member;brier_score(probability, observed): error of the probability map; on members' burnt areas, one value per member, so the ensemble can be compared with them;reliability(probability, observed, bins=...): fraction of the cells in each probability bin that actually burnt.They take plain arrays (the output of
run_ensemble/burn_probabilityand a boolean map), so no new dependency. On the Slinkard 2017 ensemble they reproduce the scores in the #172 comment (reliability 18 / 43 / 64 / 80 / 99% burnt).Tests in
tests/python/test_ensemble.py(already run by CI), a section in the ensembles User Guide page, and a CHANGELOG entry.Drafted with Claude Opus 5.5.