Repository navigation
Predict expected ignitions and escapes only; draw them in fireSense_burn - #33
Merged
Merged
Conversation
…burn IgnitionPredictRun() predicted ignitions, drew them (rpois), predicted escapes only where one was drawn, drew escapes (rbinom) and placed ignitions on fine pixels. It now predicts both surfaces for every coarse pixel and reports the fitted objective in fireSense_IgAndEscapeDistribution. placeIgnitions(), coarseToFineMap() and fineCoarseTable() and ignitionsAndEscapes move to fireSense_burn. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
eliotmcintire
added
enhancement
eliotmcintire
added a commit
that referenced
this pull request
Oct 16, 2026
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014G18Mik3fH4z5M5CyMSUS6
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This module now only predicts how many ignitions and escapes to expect in each coarse pixel; the random draws are made in fireSense_burn, as the spread and year effect already are. Escapes are now predicted for every pixel and follow the fitted count model.
Affects: Results change: escapes follow the fitted Poisson model instead of a binomial, and the draws move to fireSense_burn, so a seed no longer reproduces earlier runs. This must be merged and used together with the fireSense_burn PR.
Technical details
Defect:
IgnitionPredictRun()(fireSense_ignitionPredict.R:143-222on development) predicted and drew:rpoisfor ignitions, escape predicted only where an ignition was drawn and clamped to [0, 1] (foldMeanPrediction(clamp01 = TRUE)),rbinom(size = ignitions, prob = mean), placement on fine pixels. Both fits are xgboostcount:poisson, so the escape mean is a count, not a probability.Fix: both surfaces are predicted for every flammable coarse pixel (per-fold predictions floored at 0, no upper clamp). New output
fireSense_IgAndEscapeDistribution = list(ignition, escape)is read frommodel$params$objectiveof every fold of every ELF; it stops if unreadable or if folds or ELFs disagree, naming the ELFs.ignitionsAndEscapes,placeIgnitions(),coarseToFineMap(),fineCoarseTable()and theflammableRTMinput are removed (they move to fireSense_burn).Tests: placement tests moved to fireSense_burn; new tests for the full escape surface, the objective read, and the errors for unreadable, fold-mismatched and ELF-mismatched objectives.
convertToPackage()+test_local(): 35 tests, 0 failures on the branch; 45 tests, 0 failures, 2 skipped on development. The new tests run against the development code give 7 failures and 23 errors.🤖 Generated with Claude Code