[2507][Evaluation] Implement Adjusted SSR#2508
Open
moritzhauschulz wants to merge 3 commits into
Open
Conversation
Use the robust ens-detection variant in _plot_score_maps_per_stream so the block is identical (apart from the branch-specific tag string) to mh/full-pipeline-diffusion-adjusted-scores, minimising future merge conflicts: - restore ens labels via assign_coords(ens=preds.ens.values) (positional) instead of plot_metrics["ens"] = preds.ens (index-aligned) - gate has-ens detection on the ens *dimension* (all_ens) rather than the coordinate - compute per-metric ens iteration via metric_has_ens / ens_values Behaviour is unchanged. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
moritzhauschulz
changed the title
github-actions
Bot
added
the
eval
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Adds two probabilistic metrics following GenCast (Price et al., 2024, App. A),
leaving the existing
spread/ssruntouched.Changes
spread_adj— unbiased ensemble spreadsqrt(mean Var_ens(ddof=1))(GenCast Eq. A.6).ssr_adj— adjusted spread-skill ratiosqrt((M+1)/M) · spread_adj / RMSE(ens_mean)(GenCast Eq. A.9), where
Mis the ensemble size. Thesqrt((M+1)/M)factor removes thefinite-ensemble bias so a perfectly calibrated ensemble gives SSR = 1.
ssr_adjline plots draw a horizontal reference line at the optimal value of 1.Notes
spread(biasedddof=0) andssrare unchanged; GenCast has no uncorrected SSR,so these remain only as non-standard diagnostics.
evaluation.metricsin the eval config (e.g. addssr_adj,spread_adj).Should be reviewed by someone from the evaluation team
On Santis, run with
uv run evaluate --config ./config/evaluate/eval_config_test.yml -run-ids qvim6zb3using the attached eval config.Issue Number
Closes #2507
Note this depends on #2503, which should be merged first.
Checklist before asking for review
./scripts/actions.sh lint./scripts/actions.sh unit-test./scripts/actions.sh integration-testlaunch-slurm.py --time 60