兰州大学机构库
Enhancing urban real-time PM2.5 monitoring in street canyons by machine learning and computer vision technology
Fan, Zhiguang1; Zhao, Yuan1; Hu, Baicheng1; Wang, Li2; Guo, Yuxuan1; Tang, Zhiyuan1; Tang, Junwen1; Ma, Jianmin3; Gao, Hong1; Huang, Tao1; Mao, Xiaoxuan1
2024-01
Source PublicationSustainable Cities and Society   Impact Factor & Quartile
ISSN2210-6707 ; 2210-6715
EISSN2210-6715
Volume100
page numbers10
AbstractDuring peak hours, both pedestrians and drivers face extended exposure to road air pollution, raising the risk of respiratory diseases. Variations in traffic volume, building attributes, and weather conditions in street canyons lead to differing exposure levels across road sections and intersections. Though deploying numerous sensors provides real-time access to PM2.5 levels in each road section, they cannot interpret the impact of weather, traffic, and buildings on these levels. Therefore, in Lanzhou City, we attempted to use Computer Vision Technology (CVT) to extract real-time traffic volume and street-view features from traffic images for PM2.5 concentration prediction, and to interpret the impact of road environment changes on PM2.5 levels. Results show that by using the Extreme Gradient Boosting (XGB) regression model, the coefficient of determination for PM2.5 prediction reaches R2=0.956. Meteorological conditions, traffic volume, and buildings are key variables in predicting road PM2.5 concentrations. Meteorological conditions control the continuous fluctuation of road PM2.5 levels, while traffic volume can lead to sudden changes in PM2.5 levels. The research indicates that the combination of traffic cameras and CVT can acquire road PM2.5 concentrations, contributing significantly to rapidly understanding road pollution status, identifying highly polluted roads, and conducting exposure assessments of roadways.
KeywordPM2.5 Urban roads Street view Traffic image Computer vision technology Extreme gradient boosting
PublisherELSEVIER
DOI10.1016/j.scs.2023.105009
Indexed BySCIE
Language英语
WOS Research AreaConstruction & Building Technology ; Science & Technology - Other Topics ; Energy & Fuels
WOS SubjectConstruction & Building Technology ; Green & Sustainable Science & Technology ; Energy & Fuels
WOS IDWOS:001102884800001
Original Document TypeArticle
Citation statistics
Document Type期刊论文
Identifierhttps://ir.lzu.edu.cn/handle/262010/569517
Collection兰州大学
Corresponding AuthorZhao, Yuan
Affiliation
1.Lanzhou Univ, Coll Earth & Environm Sci, Key Lab Environm Pollut Predict & Control, Lanzhou 730000, Gansu, Peoples R China;
2.Lanzhou Univ, Collaborat Innovat Ctr Western Ecol Safety, Lanzhou 730000, Peoples R China;
3.Peking Univ, Coll Urban & Environm Sci, Lab Earth Surface Proc, Beijing 100871, Peoples R China
Recommended Citation
GB/T 7714
Fan, Zhiguang,Zhao, Yuan,Hu, Baicheng,et al. Enhancing urban real-time PM2.5 monitoring in street canyons by machine learning and computer vision technology[J]. Sustainable Cities and Society,2024,100.
APA Fan, Zhiguang.,Zhao, Yuan.,Hu, Baicheng.,Wang, Li.,Guo, Yuxuan.,...&Mao, Xiaoxuan.(2024).Enhancing urban real-time PM2.5 monitoring in street canyons by machine learning and computer vision technology.Sustainable Cities and Society,100.
MLA Fan, Zhiguang,et al."Enhancing urban real-time PM2.5 monitoring in street canyons by machine learning and computer vision technology".Sustainable Cities and Society 100(2024).
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[Fan, Zhiguang]'s Articles
[Zhao, Yuan]'s Articles
[Hu, Baicheng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Fan, Zhiguang]'s Articles
[Zhao, Yuan]'s Articles
[Hu, Baicheng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Fan, Zhiguang]'s Articles
[Zhao, Yuan]'s Articles
[Hu, Baicheng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.