Applying traffic camera and deep learning-based image analysis to predict PM2.5 concentrations

Background: Air pollution has caused a significant burden in terms of mortality and mobility worldwide. However, the current coverage of air quality monitoring networks is still limited.Objective: This study aims to apply a novel approach to convert the existing traffic cameras into sensors measuring particulate matter with a diameter of 2.5 mu m or less (PM2.5) so that the coverage of PM2.5 monitoring could be expanded without extra cost.Methods: In our study, the traffic camera images were collected at a rate of 4 images/h and the corresponding hourly PM2.5 concentration was collected from the reference grade PM2.5 station 3 km away. A customized neural network model was trained to obtain the PM2.5 concentration from images followed by a random forest model to predict the hourly PM2.5 concentration. The saliency maps and the feature importance were utilized to interpret the neural network. Results: Proposed novel approach has a high prediction performance to predict hourly PM2.5 from traffic camera images, with a root mean square error (RMSE) of 0.76 mu g/m3 and a coefficient of determination (R2) of 0.98. The saliency map shows neural network focuses on unobstructed far-end road surfaces while the random forest feature importance highlights the first quarter image's significance. The model performance is robust whether weather conditions are controlled or not.Conclusion: Our study provided a practical approach to converting the existing traffic cameras into PM2.5 sensors. The deep learning method based on the Resnet architecture in our study can broaden the coverage of PM2.5 monitoring with no additional infrastructure needed.