发表机构
Queen Mary University of London; Instituto Politecnico Nacional（伦敦玛丽女王大学; 国家理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究以伦敦监测站点为对象，通过场景式实验评估四种树基ML模型，发现纳入远程交通数据可提升NO₂估算精度，交通变量在交通主导环境中对NO₂的贡献可与相邻监测站污染物测量相当。
AI 中文摘要
车辆交通是空气污染的主要来源，但远程获取的交通信息对本地机器学习（ML）空气污染物模型的贡献仍未得到充分表征。本研究评估了四种可解释的基于树的机器学习模型（Random Forest、Extra Trees、LightGBM、XGBoost），设置了六个预测变量场景，这些场景结合了逐步扩大的预测变量集，范围从仅远程获取的交通、气象和时间变量，到纳入1个和4个相邻监测站的测量数据，以估算伦敦多个站点的NO₂、PM₁₀、PM₂.₅和O₃浓度。将ML模型的性能与作为基准的岭线性回归模型、空间插值方法以及跨站点验证实验进行了比较。在不使用相邻站点数据建模时，未纳入交通信息的NO₂的RMSE范围为9.73至11.66μg/m³，而纳入交通信息时该范围为8.72至11.52μg/m³。此外，对于NO₂，SHAP分析表明，在交通主导的环境中，与交通相关的变量可贡献至与相邻监测站的污染物测量相当的水平。
英文摘要
Vehicular traffic is a major source of air pollution; however, the contribution of remotely acquired traffic information to local machine-learning (ML) air-pollution models remains insufficiently characterised. This study evaluates four interpretable tree-based ML models (Random Forest, Extra Trees, LightGBM, and XGBoost) under six predictor scenarios combining progressively larger predictor sets, ranging from remotely acquired traffic, meteorological, and temporal variables alone to the inclusion of measurements from one and four neighbouring monitoring stations, to estimate NO$_2$, PM$_{10}$, PM$_{2.5}$, and O$_3$ concentrations across several sites in London. ML model performance was compared with a ridge linear regression model as a baseline, with spatial interpolation methods and with a cross-site validation experiment. When modelling without data from neighbouring stations, the RMSE for NO$_2$ ranged from 9.73 to 11.66 $μ$g/m$^3$ without traffic information, compared with 8.72 to 11.52 $μ$g/m$^3$ when traffic information was included. Additionally, for NO$_2$, SHAP analyses indicate that traffic-related variables can contribute at levels comparable to pollutant measurements from neighbouring monitoring stations in traffic-dominated~environments.
CommentsAccepted for publication in Atmosphere
Journal refhttps://www.mdpi.com/2073-4433/17/8/806
