From Cameras to Concentrations: Estimating Black Carbon From Vehicles with Machine Learning and Computer Vision Techniques
Bibliographic record
Abstract
Urban traffic congestion contributes significantly to black carbon (BC) pollution, a harmful byproduct of fuel combustion with disproportionate impacts on residents living near busy roads. While understanding the impact of BC on our health is critical, accurate BC monitoring remains limited because the necessary instruments are costly and sparsely deployed. The inability to more frequently and equally get data on BC from vehicles, in turn, creates data deserts in under-monitored areas.In contrast, traffic surveillance cameras are widely deployed across cities worldwide and offer an abundant, high-resolution data source that captures vehicle types, density, and flow as factors known to influence BC levels. We hypothesize that features representing vehicle emission covariates derived from traffic video, when combined with environmental data, can serve as a proxy to estimate BC concentrations. We developed a computer vision-based system using YOLOv8 and XGBoost to extract traffic features and predict minute-level BC concentration, explaining up to 72\% of variance in selected Toronto locations. We discuss the implications of vision-based sensing on privacy, feature limitations, and large-scale deployment. This thesis closes with plans to extend this study by considering other low-cost sensing modalities.
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 | 0.000 | 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 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".