Real-time air quality prediction using traffic videos and machine learning

Simple item page
dc.contributor.authorDeveer, Laura
dc.contributor.authorMinet, Laura
dc.date.accessioned2026-03-12T21:25:31Z
dc.date.available2026-03-12T21:25:31Z
dc.date.issued2025
dc.description.abstractMachine learning techniques are yielding better results than traditional statistical techniques to estimate traffic-related air pollutant (TRAP) concentrations. However, required data inputs, particularly complex traffic data, are costly and rarely collected in real-time. This study leverages real-time object detection techniques to accurately predict TRAP concentrations by extracting traffic variables solely from videos. Fine particulate matter (PM2.5), nitrogen dioxide (NO2) and ozone (O3) concentrations are recorded by low-cost sensors, with traffic data extracted using object detection and tracking algorithms. Extreme Gradient Boosting, random forest, and multilinear regression models are employed to predict concentrations across different predictor combinations. Our optimal models accurately predict PM2.5, NO2, and O3 concentrations with R2 values of 0.94, 0.95, and 0.92, respectively. This study demonstrates a cost-effective approach with high accuracies in predicting real-time TRAP using a low-cost and low-maintenance tool: a video camera. Cities could similarly track TRAP using traffic camera infrastructure without additional sensor deployment.
dc.description.reviewstatusReviewed
dc.description.scholarlevelFaculty
dc.description.sponsorshipNatural Sciences and Engineering Research Council of Canada
dc.identifier.citationDeveer, L., & Minet, L. (2025). Real-time air quality prediction using traffic videos and machine learning. Transportation Research Part D Transport and Environment, 142, 104688. https://doi.org/10.1016/j.trd.2025.104688
dc.identifier.urihttps://doi.org/10.1016/j.trd.2025.104688
dc.identifier.urihttps://hdl.handle.net/1828/23478
dc.language.isoen
dc.publisherTransportation Research Part D
dc.rightsCC BY-NC-ND
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectInstitute for Integrated Energy Systems (IESVic)
dc.subjectmachine learning
dc.subjecttraffic-related air pollution
dc.subjectlow-cost sensors
dc.subjecttraffic videos
dc.subjectcomputer vision
dc.subject.departmentDepartment of Civil Engineering
dc.titleReal-time air quality prediction using traffic videos and machine learning
dc.typeArticle

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
deveer_laura_transpResDTranspEnviron_2025.pdf
Size:
6.37 MB
Format:
Adobe Portable Document Format
Download

Collections

Faculty and Staff Publications
 
University of Victoria Libraries

We acknowledge and respect the Lək̓ʷəŋən (Songhees and Esquimalt) Peoples on whose territory the university stands, and the Lək̓ʷəŋən and W̱SÁNEĆ Peoples whose historical relationships with the land continue to this day.