Identifying Optimal Green Plot Ratio Thresholds for Mitigating PM2.5 in Street Canyons: Integrating LiDA, CFD, Explainable Machine Learning

Authors

• Bin Guo, University of Science and Technology, Xi’an, Shaanxi
• Hailong Chen, University of Science and Technology, Xi’an, Shaanxi
• Zheng Wang, Qilu Institute of Technology
• Miaoyi Chen, Southern University of Science and Technology, Shenzhen
• Lu Li, Qilu Institute of Technology
• Puhao Chen, University of Science and Technology, Xi’an, Shaanxi
• Lin Pei, Xi’an Physical Education University
• Tengyue Guo, Qinghai University
• Xuying Ma, University of Science and Technology, Xi’an, Shaanxi
• Rongming Hu, University of Science and Technology, Xi’an, Shaanxi
• Xiaowei Zhu, Portland State UniversityFollow

Author ORCID Identifier(s)

Xiaowei Zhu 0000-0003-1507-5681

Sponsor

This work was supported by the Key Technologies for Strategic Reserve and Development Utilization of Groundwater in Cities along the Northern Foothills of the Qinling Mountains (XBY-ZDKJ−2023–10), the Natural Science Foundation of Shaanxi Province (2024JC-YBQN−0304), the Key Research and Development Projects of Shaanxi Province (2024NC-YBXM−241), the Shaanxi Key Laboratory of Enviromental Monitoring and Forewarning of Trace Pollutants (SHJKFJJ202319), and the National Natural Science Foundation.

Published In

Journal of Hazardous Materials

Document Type

Post-Print

Publication Date

2026

Abstract

Vegetation significantly influences PM_2.5 dispersion in urban street canyons, but the interplay between aerodynamic and deposition mechanisms remains poorly quantified at this scale. This study comprehensively utilized LiDAR, YOLOv8, scenario analysis, and Computational Fluid Dynamics (CFD) to derive realistic 3D geometry, to identify precise traffic flow for estimating PM_2.5 emissions, and to simulate PM_2.5 distribution, respectively, in a real street canyon of Xi’an. The model was validated against field measurements, achieving strong agreement (R² = 0.91, RMSE = 1.87 µg/m³). Results show that dense or obstructive vegetation mainly increases near-surface concentrations by creating low-wind zones that hinder ventilation. At the same time, deposition helps remove particles, with low shrubs proving more effective at 0.3 m than trees at higher levels (4.5 m and 7.5 m). Among the tested configurations, scenarios with low hedges along both sides of the street canyon, with or without central trees, performed best at reducing pedestrian-level PM_2.5, as they maintained good airflow while enhancing near-surface deposition, with Averaged Relative Difference in Concentration (ARDC) values of −2.49% and −0.34%. Further analysis using Shapley Additive Explanations (SHAP) identified Green Plot Ratio (GPR) as the most influential metric and revealed an actionable, model-derived threshold range: GPR values between 0.54 and 0.56 are associated with effective concentration reductions. These findings demonstrate that net PM_2.5 mitigation in street canyons requires balancing aerodynamic suppression against deposition enhancement through careful vegetation configuration, providing a quantitative basis for mechanism-informed urban greening design.

Rights

Licensed under CC BY 4.0

This is the author accepted manuscript subsequently published by Elsevier.

https://doi.org/10.1016/j.jhazmat.2026.143277

DOI

10.1016/j.jhazmat.2026.143277

Persistent Identifier

https://archives.pdx.edu/ds/psu/45099

Citation Details

Guo, B., Chen, H., Wang, Z., Chen, M., Li, L., Chen, P., ... & Zhu, X. (2026). Identifying optimal green plot ratio thresholds for mitigating PM2. 5 in street canyons: Integrating LiDAR, CFD, and explainable machine learning. Journal of Hazardous Materials, 143277.