Tracking Air Pollution: Global Near Real-Time Fire PM2.5 Retrievals from Multisource Data Fusion
Bibliographic record
Abstract
Wildfire smoke has raised concerns on air quality and public health with the increasing intensity, frequency, and duration of wildfires as a result of climate change. This study generates a global near real-time wildfire-related PM2.5 (i.e., fire PM2.5) concentration product by combining multisource data with machine learning algorithm. This is the first daily updated full-coverage high-resolution fire PM2.5 data products that allows timely tracking of the fast-growing fire PM2.5 globally. The gridded fire PM2.5 data at a spatial resolution of 0.1°×0.1° are estimated by fusing surface PM2.5 monitoring, satellite observations, meteorological fields, atmospheric composition reanalysis data, and population distribution through a three-layer random forest model. We found that during 2023-2024, wildfire smoke contributed 1.32 μg/m3 (4.7%) and 1.25 μg/m3 (4.7%) to population-weighted annual average PM2.5 worldwide, and caused 50,700 (95% confidence interval: 33,600-68,300) and 51,500 (34,100-69,400) all-cause deaths through acute fire PM2.5 exposure, respectively. Regionally, the record-breaking wildfires resulted to 1.42 μg/m3 (21%) and 2.53 μg/m3 (16%) increase in population-weighted annual average PM2.5 in Canada (2023) and South America (2024), respectively. We noticed that a relatively small number of extreme wildfire episodes could disproportionately impact regional public health, emphasizing the importance of timely monitoring of wildfire-induced PM2.5 pollution. The global fire PM2.5 data will be publicly available on the Tracking Air Pollution platform (TAP, http://tapdata.org.cn), to support promptly health impact assessment and policymaking for wildfire risk mitigation.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 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".