Predict spread across several ELFs, blending across their boundaries - #18
Merged
Merged
Conversation
logisticAll() picks logistic3pUpper when the stored parameters include upperTail1 (fireSenseUtils 0.2.3.9038), so the floor rises to that and a value test pins the prediction against a hand calculation. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CwcjqqK59FmTJscyi7xUqv
Each fitted ELF's model predicts its own pixels and those within ELFblendWidth (20 km) of them; overlapping predictions are averaged with weights falling linearly from 1 inside an ELF to 0 at ELFblendWidth outside it. Each ELF uses its own parameters, covMinMax_spread and covariates from its ledger row. The per-ELF computation moves to spreadProbOneELF(); one ELF behaves as before. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CwcjqqK59FmTJscyi7xUqv
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
With several fitted ELFs in one study area, every pixel now gets a spread probability. Each ELF's model predicts its own pixels and those within
ELFblendWidth(default 20 km, the buffermakeELFs()uses) of them. Where predictions overlap they are averaged with weights falling linearly from 1 inside an ELF to 0 atELFblendWidthoutside it, so a boundary is 50/50. Each ELF uses its own ledger row: its parameter sets, itscovMinMax_spread, and only the covariates it was fitted with. Each pixel's ELF comes from a new input,rasterToMatchLargeELF, whichfireSense_ELFsmakes for astudyAreaLarge.With one ELF nothing changes. New tests use a two-ELF strip with hand-computed blend weights. The suite passes locally against fireSenseUtils 0.2.3.9039.
Draft: built on #17, and it needs
fireSense_dataPrepPredictto supply both ELFs' covariates in the blend zone; it goes ready after the end-to-end 2-ELF run.🤖 Generated with Claude Code
https://claude.ai/code/session_01CwcjqqK59FmTJscyi7xUqv