Multi-sensor, multi-scale, Bayesian data synthesis for mapping within-year wildfire progression
Bibliographic record
Abstract
As freely available remotely sensed data sources proliferate, the ability to combine imagery with high spatial and temporal resolutions enables applications aimed at near-term disturbance detection. In this case study, we present methods for synthesizing burned-area information from multiple sources to map the active phase of the Elephant Hill fire from the 2017 fire season in British Columbia. We used the Bayesian Updating of Land Cover (BULC) algorithm to merge burned-area classifications from a range of remote-sensing sources such as Landsat-8, Sentinel-2, and MODIS. We created provisional classifications by comparing the post-fire Normalized Burn Ratio against pre-fire image composite within the fire boundary provided by the Province of British Columbia. BULC fused the classifications in Google Earth Engine, producing a cohesive time-series stack with updated burned areas for 19 distinct days. The fire burned unevenly throughout its lifespan: a rapid burn phase of 53,097 ha in two weeks by late July, a steady burn phase to 60,000 ha until late August, an accelerated burn phase of 95,766 ha until mid-September, and containment at 203,560 ha in October. The highly automated methods presented herein can synthesize multi-source fire classifications for active phase monitoring both retrospectively and in near-real-time.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".