High-spatiotemporal-resolution mapping of PM2.5 traffic source impacts integrating machine learning and source-specific multipollutant indicator

Lingling Lv; Peng Wei; Jingnan Hu; Yangxi Chu; Xiao Liu

doi:10.1016/j.envint.2024.108421

High-spatiotemporal-resolution mapping of PM_2.5 traffic source impacts integrating machine learning and source-specific multipollutant indicator

Environ Int. 2024 Jan:183:108421. doi: 10.1016/j.envint.2024.108421. Epub 2024 Jan 3.

Authors

Lingling Lv¹, Peng Wei², Jingnan Hu³, Yangxi Chu², Xiao Liu²

Affiliations

¹ State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, PR China; School of the Environment and Safety Engineering, Jiangsu University, Zhenjiang 212013, PR China.
² State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, PR China.
³ State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, PR China. Electronic address: hujn@craes.org.cn.

PMID: 38194757
DOI: 10.1016/j.envint.2024.108421

Abstract

Traffic sources are a major contributor to fine particulate matter (PM_2.5) pollution, with their emissions and diffusion exhibiting complex spatiotemporal patterns. Receptor models have limitations in estimating high-resolution source contributions due to insufficient observation networks of PM_2.5 compositions. This study developed a source apportionment method that integrates machine learning and emission-based integrated mobile source indicator (IMSI) to rapidly and accurately estimate PM_2.5 traffic source impacts with high spatiotemporal resolution in the Beijing-Tianjin-Hebei region. Firstly, we utilized multisource data and developed various machine learning models to optimize the traffic-related pollutant concentration fields simulated by a chemical transport model. Results demonstrated that the Extreme Gradient Boosting (XGBoost) model exhibited excellent prediction accuracy of nitrogen oxide (NO₂), carbon oxide (CO), and elemental carbon (EC), with the cross-validated R values increasing to 0.87-0.92 and error indices decreasing by 50-67%. Furthermore, we estimated and predicted daily mappings of PM_2.5 traffic source impacts using the IMSI method based on optimized concentration fields, which improved spatially resolved source contributions to PM_2.5. Our findings reveal that PM_2.5 traffic source impacts display significant spatial heterogeneity, and these hotspots can be precisely identified during the pollution processes with sharp changes. The evaluation results indicated that there is a good correlation (R of 0.79) between PM_2.5 traffic source impacts by IMSI method and traffic source contributions apportioned by a receptor model at Beijing site. Our study provides deeper insights of estimating the spatiotemporal distribution of PM_2.5 source-specific impacts especially in regions without PM_2.5 compositions, which can provide more complete and timely guidance to implement precise air pollution management strategies.

Keywords: Machine learning; Multipollutant indicator; PM(2.5); Source apportionment; Traffic source.

MeSH terms

Air Pollutants* / analysis
Air Pollution* / analysis
Carbon
Environmental Monitoring / methods
Machine Learning
Nitric Oxide
Particulate Matter / analysis

Substances

Air Pollutants
Particulate Matter
Nitric Oxide
Carbon