Wei Qing, Chen Yongqi, Zhang Huijin, Jia Zichen, Yang Ju, Niu Bin
College of Environmental Science and Engineering, Tongji University, Shanghai 200092, China; State Key Laboratory of Pollution Control and Resource Utilization, Tongji University, Shanghai 200092, China.
College of Environmental Science and Engineering, Tongji University, Shanghai 200092, China; State Key Laboratory of Pollution Control and Resource Utilization, Tongji University, Shanghai 200092, China.
Environ Res. 2025 Apr 1;270:121003. doi: 10.1016/j.envres.2025.121003. Epub 2025 Feb 1.
PM2.5 is a critical air pollutant, and understanding its drivers is essential for regional air quality control. This study employed meteorological and pollutant variables to predict PM2.5 concentrations in Shanghai using interpretable tree-based models. The random forest (RF) model performed best, achieving MAE, RMSE, MBE, and R values of 3.279, 4.609, 1.254, and 0.971, respectively, improving accuracy by 42.1%-85.5% compared to AdaBoost. Shapley additive explanations (SHAP) analysis identified CO, SO, and O as the most influential factors. Partial dependence plots (PDPs) showed SO had the strongest impact below 40 μg/m³, while NO exhibited a linear positive correlation with PM2.5 up to 60 μg/m³. Atmospheric pressure and rainfall were negatively correlated with PM2.5, with notable reductions in concentrations under high-pressure conditions and rainfall levels between 0 and 20 mm. Temperature and relative humidity showed complex relationships, with sharp increases in PM2.5 at temperatures between -5 °C and 15 °C and SHAP values declining for humidity above 90%. Wind speed exhibited a non-linear effect, with minimal influence at higher velocities. The combined effects of different pollutants can be intensified significantly at higher levels. These findings offer valuable guidance for urban air quality management and pollution mitigation strategies.
细颗粒物（PM2.5）是一种关键的空气污染物，了解其驱动因素对于区域空气质量控制至关重要。本研究利用气象和污染物变量，采用基于可解释树的模型预测上海的PM2.5浓度。随机森林（RF）模型表现最佳，平均绝对误差（MAE）、均方根误差（RMSE）、平均偏差误差（MBE）和R值分别为3.279、4.609、1.254和0.971，与自适应增强（AdaBoost）相比，准确率提高了42.1%-85.5%。夏普利值法（SHAP）分析确定一氧化碳（CO）、二氧化硫（SO）和臭氧（O）为最具影响力的因素。偏依赖图（PDP）显示，在40μg/m³以下，SO的影响最强，而在60μg/m³以下，二氧化氮（NO）与PM2.5呈线性正相关。大气压力和降雨与PM2.5呈负相关，在高压条件下以及降雨量在0至20毫米之间时，浓度显著降低。温度和相对湿度呈现复杂关系，在-5°C至15°C之间，PM2.5急剧增加，湿度高于90%时SHAP值下降。风速呈现非线性效应，在较高风速下影响最小。不同污染物在较高水平时的综合影响可能会显著增强。这些发现为城市空气质量管理和污染缓解策略提供了有价值的指导。
