The Design, Calibration, and Evaluation of a Mobile Sensor System for Air Pollution Measurement and Prediction in Urban Areas
Bibliographic record
Abstract
BACKGROUND: The increasing ubiquity of low-cost air quality sensors has been recently met with a growing body of research on sensor calibration and validation. While most studies documenting low-cost sensor performance are limited to the analysis of fixed sensors, there is still much to be learned from the performance of air quality sensors in a mobile environment. This study presents the design and testing of a mobile platform for simultaneous air quality, traffic, and built environment characterization. METHODS: The Urban Scanner is a platform mounted on the rooftop of a vehicle and equipped with air quality sensors (NO2, O3, PM2.5, PM10, CO) and ancillary instruments such as GPS, 360degree camera, LIDAR 3D scanner, and wind anemometer. It also includes a data acquisition module with real-time analytics for traffic characterization from video imagery (cars, trucks, buses) and built environment features (trees, sidewalk, building façade, building height). Air quality sensor calibration was conducted through co-location against reference instruments with novel signal processing techniques. A year-long data collection campaign in the City of Toronto, along routes carefully designed to maximize the variability in road types, land-use, and built environment features. RESULTS: After urban scanner development and calibration, all sensors exhibited small standard errors and significant relationships with reference data. Traditional land-use regression models explained spatial variations in NO2 and O3 across Toronto, with R2 = 0.64 and 0.65, respectively. In addition to linear regression, a principal component analysis of the predictors was first conducted and subsequently used in Bayesian Regularized Neural-Networks models (BRANN). This approach yielded R2 of 0.82 and 0.80 for O3 and NO2. CONCLUSIONS: The combination of a fully calibrated sensor system and a carefully designed data collection protocol that optimizes spatial variability and temporal representation, can give rise to a powerful tool for air quality prediction in urban areas.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".