A literature review on WUI fire susceptibility using machine learning
Bibliographic record
Abstract
This report comprises a literature review on the use of machine learning (ML) in fire susceptibility/hazard mapping, fuel mapping/characterization and experimental work on ember-driven ignition. This review is part of the CRBE WUI Fire Hazard Assessment tool project. Previously, a literature review on the use of ML in fire dynamics and detection was conducted (Report A1-017985). The scope of the review involves: 1. Providing an overview of theoretical fundamentals on the ML applied in the literature. 2. Identifying the literature involved in ML in fire susceptibility/hazard mapping and fuel mapping/characterization. 3. Identifying the literature involved in experimental ember-driven ignition in as a guide to the data required to develop the ML-based tool. Machine learning has been recently utilized in various applications and fields of science and technologies with impressive results. With this in mind, several studies employed machine learning for WUI fire incidents. The aim of previous studies in this literature have been to use machine learning methods for prediction of fire susceptibility (hazard) maps as well as maps of fuel characteristics. Overall, the trend found that ML-based methods, and in particular deep learning methods, were outperforming traditional methods such as linear and logistic regression in both fire susceptibility/hazard mapping and fuel mapping/characterization. With regards to the proposed CRBE WUI Ember Hazard Assessment tool project, this literature review shows that no study has examined the strict use of ML in the prediction of ignition probabilities/risk based on ember-driven ignition, but a similar study using machine learning to predict firebrand areal mass density and firebrand areal number density was found. Many studies have experimentally documented solely ember-driven ignition, and this data can be used in a ML algorithm. However, this literature review also identified gaps in the literature that can be addressed by additional experimental work that would enhance the proposed ML-based tool. Additionally, the literature presented novel work coupling thermal radiation with ember-driven ignition. These studies serve as a foundation for understanding the mechanisms behind WUI fires and as a foundation to a more complex ML-based algorithm that can predict coupled thermal radiation and ember-driven ignition.
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 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.008 | 0.007 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.001 |
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".