Predicting the Danger of Particulate Matter Pollution from Wildfires Using Classification Models
Bibliographic record
Abstract
Due to a mix of climate change and California’s mega-drought, California’s wildfire seasons have overall gotten progressively longer, more destructive, and more expensive. In 2020 alone, around 9,900 wildfires burned about 4.3 million acres, costing the state over $12 billion. (Kerlin, 2022) Larger and more numerous wildfires pollute billions of harmful particles into the atmosphere, including PM2.5. This study aims to use features of a wildfire and other factors to predict whether a wildfire pollutes enough PM2.5 particles to be detrimental to human health. The 8 features used in the model are the acres burned, the length in days of the fire, available green space within a 15-mile radius of the fire, the highest population density within a 15-mile radius of the fire, electricity usage, median income, temperature, and precipitation. A Gradient Boosting Classifier (GBC) was applied to the dataset to predict whether a wildfire’s emissions necessitated an evacuation. The GBC results achieved a high accuracy of 0.931 as well as a great Area Under the Curve (AUC) of 0.911. By far the most important feature in the GBC is Length, with a feature importance score of 0.109 +/- 0.009.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".