Department of Environmental Science and Engineering, Institute of Polar Environment & Anhui Key Laboratory of Polar Environment and Global Change, University of Science and Technology of China, Hefei, Anhui, 230026, China.
Department of Environmental Science and Engineering, Institute of Polar Environment & Anhui Key Laboratory of Polar Environment and Global Change, University of Science and Technology of China, Hefei, Anhui, 230026, China; Center for Excellence in Urban Atmospheric Environment, Institute of Urban Environment, Chinese Academy of Sciences, Xiamen, Fujian, 361021, China.
Environ Pollut. 2022 May 1;300:118932. doi: 10.1016/j.envpol.2022.118932. Epub 2022 Feb 1.
Air pollution is becoming serious in developing country, and how to quantify the role of local emission and/or meteorological factors is very important for government to implement policy to control pollution. Here, we use a random forest model, a machine learning (ML) approach, combined with a de-weather method to analyze the PM level during the COVID-19 outbreak in Hubei Province. The results show that changes in anthropogenic emissions have reduced PM concentrations in February and March 2020 by about 33.3% compared to the same period in 2019, while changes in meteorological conditions have increased PM concentrations by about 8.8%. Moreover, the impact of meteorological conditions is more significant in the central region, which is likely to be related to regional transport. After excluding the contribution of meteorological conditions, the PM concentration in Hubei Province in February and March 2020 is lower than the secondary standard of China (35 μ g/m). Our estimates also indicate that under similar meteorological conditions as in February and March 2019, an emission reduction intensity equivalent to about 48% of the emission reduction intensity during the lockdown may bring the annual average PM concentration to the standard (35 μ g/m). Our study shows that machine learning is a powerful tool to quantify the influencing factors of PM, and the results further emphasize the need for scientific emission reduction as well as joint regional control measures in future.
空气污染在发展中国家变得越来越严重，如何量化本地排放和/或气象因素的作用，对于政府实施污染控制政策非常重要。在这里，我们使用随机森林模型（一种机器学习（ML）方法），结合去气象方法，来分析 COVID-19 疫情期间湖北省的 PM 水平。结果表明，与 2019 年同期相比，2020 年 2 月和 3 月人为排放的变化使 PM 浓度降低了约 33.3%，而气象条件的变化使 PM 浓度增加了约 8.8%。此外，气象条件的影响在中部地区更为显著，这可能与区域传输有关。在排除气象条件的贡献后，2020 年 2 月和 3 月湖北省的 PM 浓度低于中国的二级标准（35μg/m）。我们的估计还表明，在与 2019 年 2 月和 3 月相似的气象条件下，减排强度相当于封锁期间减排强度的约 48%，可能使年平均 PM 浓度达到标准（35μg/m）。本研究表明，机器学习是量化 PM 影响因素的有力工具，结果进一步强调了未来科学减排以及联合区域控制措施的必要性。
Zotero 插件
