College of Environment, Zhejiang University of Technology, Hangzhou, 310032, China.
School of Accounting, Southwestern University of Finance and Economics, Chengdu, 611130, China.
Environ Pollut. 2022 Aug 1;306:119420. doi: 10.1016/j.envpol.2022.119420. Epub 2022 May 5.
China was seriously affected by air pollution in the past decade, especially for particulate matter (PM) and emerging ozone pollution recently. In this study, we systematically examined the spatiotemporal variations of six air pollutants and conducted ozone prediction using machine learning (ML) algorithms in the Beijing-Tianjin-Hebei (BTH) region. The annual-average concentrations of CO, PM, PM and SO decreased at a rate of 141, 11.0, 6.6 and 5.6 μg/m/year, while a pattern of initial increase and later decrease was observed for NO and O_8 h. The concentration of SO, CO and NO was higher in Tangshan and Xingtai, while northern BTH region has lower levels of CO, NO and PM. Spatial variations of ozone were relatively small in the BTH region. Monthly variations of PM displayed an increase in March probably due to wind-blown dusts from Northwest China. A seasonal and diurnal pattern with summer and afternoon peaks was found for ozone, which was contrast with other pollutants. Further ML algorithms such as Random Forest (RF) model and Decision tree (DT) regression showed good ozone prediction performance (daily: R = 0.83 and 0.73, RMSE = 30.0 and 37.3 μg/m, respectively; monthly: R = 0.93 and 0.88, RMSE = 12.1 and 15.8 μg/m, respectively) based on 10-fold cross-validation. Both RF model and DT regression relied more on the spatial trend as higher temporal prediction performance was achieved. Solar radiation- and temperature-related variables presented high importance at daily level, whereas sea level pressure dominated at monthly level. The spatiotemporal heterogeneity in variable importance was further confirmed using case studies based on RF model. In addition, variable importance was possibly influenced by the emission reductions due to COVID-19 pandemic. Despite its possible weakness to capture ozone extremes, RF model was beneficial and suggested for predicting spatiotemporal variations of ozone in future studies.
过去十年间，中国深受空气污染影响，尤其是近年来细颗粒物（PM）和新兴臭氧污染问题严重。本研究中，我们系统地检测了京津冀地区六种空气污染物的时空变化，并采用机器学习（ML）算法对臭氧进行了预测。CO、PM、PM 和 SO 的年平均浓度以 141、11.0、6.6 和 5.6μg/m/year 的速度下降，而 NO 和 O_8h 的浓度则呈现出先增加后减少的趋势。唐山和邢台的 SO、CO 和 NO 浓度较高，而北部的京津冀地区 CO、NO 和 PM 浓度较低。京津冀地区臭氧的空间变化相对较小。PM 的月变化显示，3 月份可能由于来自中国西北部的扬尘而增加。臭氧具有季节性和日变化规律，夏季和下午出现峰值，与其他污染物相反。进一步的 ML 算法，如随机森林（RF）模型和决策树（DT）回归，在基于 10 倍交叉验证的臭氧日预测中表现出良好的性能（R=0.83 和 0.73，RMSE=30.0 和 37.3μg/m），在月预测中表现出良好的性能（R=0.93 和 0.88，RMSE=12.1 和 15.8μg/m）。RF 模型和 DT 回归都更依赖于空间趋势，从而实现了更高的时间预测性能。在日水平上，与太阳辐射和温度相关的变量非常重要，而在月水平上，海平面气压占主导地位。基于 RF 模型的案例研究进一步证实了变量重要性的时空异质性。此外，变量的重要性可能受到 COVID-19 大流行导致的减排的影响。尽管 RF 模型可能难以捕捉臭氧极值，但它有利于并建议在未来的研究中预测臭氧的时空变化。
