Scholarlink

<p>The identification and quantification of abrupt atmospheric pollutant emissions are crucial for the implementation of effective emergency control measures. Firework emissions during the Chinese New Year represent a widespread and distinct scenario for studying such abrupt emissions. In this study, we applied a machine learning-based approach to quantify the contribution of firework emissions to major air pollutants, using surface observations over China during 2017–2023. The results reveal a sharp increase in fine (PM<sub>2.5</sub>) and coarse (PM<sub>10</sub>) particulate matter, and sulfur dioxide concentrations from New Year’s Eve into the early hours of the following day, observed across multiple cities. Notably, smaller cities (e.g., Huangshan and Gannan) experienced markedly higher peak concentrations compared to megacities (e.g., Beijing and Shenzhen). The relative contribution (<i>P</i><sub>CSF</sub>) of firework emissions to PM<sub>2.5</sub> was generally higher in parts of the Southwest, Northeast, and Northwest regions, with the <i>P</i><sub>CSF</sub> value from 2017 to 2019 ranging from 150 to 600&#xa0;μg/m<sup>3</sup>, while during the COVID-19 periods (2020–2022), it decreased to 100–300&#xa0;μg/m<sup>3</sup>. Notably, ozone levels exhibited a consistent decline during peak fireworks hours, showing overall good negative correlations with PM<sub>2.5</sub> <i>P</i><sub>CSF</sub>, suggesting potential short-term ozone suppression linked to firework-related chemistry. Spatial patterns of firework emissions also reflected the effects of population migration and regional policy enforcement. This study demonstrates the utility of machine learning in diagnosing abrupt air pollution events and provides insights for targeted mitigation during episodic high-emission periods.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine Learning-Assisted Diagnosis of Abrupt Air Pollution Emissions: Insights From Firework Emissions in China

  • 期刊论文

  • 发表日期：

    2025年9月10日

查看全文
  • Lu Yang,
  • Di Liu,
  • Han Yang,
  • Jie Fang,
  • Qingxiao Meng,
  • Yunjiang Zhang,
  • Xinlei Ge

摘要

The identification and quantification of abrupt atmospheric pollutant emissions are crucial for the implementation of effective emergency control measures. Firework emissions during the Chinese New Year represent a widespread and distinct scenario for studying such abrupt emissions. In this study, we applied a machine learning-based approach to quantify the contribution of firework emissions to major air pollutants, using surface observations over China during 2017–2023. The results reveal a sharp increase in fine (PM2.5) and coarse (PM10) particulate matter, and sulfur dioxide concentrations from New Year’s Eve into the early hours of the following day, observed across multiple cities. Notably, smaller cities (e.g., Huangshan and Gannan) experienced markedly higher peak concentrations compared to megacities (e.g., Beijing and Shenzhen). The relative contribution (PCSF) of firework emissions to PM2.5 was generally higher in parts of the Southwest, Northeast, and Northwest regions, with the PCSF value from 2017 to 2019 ranging from 150 to 600 μg/m3, while during the COVID-19 periods (2020–2022), it decreased to 100–300 μg/m3. Notably, ozone levels exhibited a consistent decline during peak fireworks hours, showing overall good negative correlations with PM2.5 PCSF, suggesting potential short-term ozone suppression linked to firework-related chemistry. Spatial patterns of firework emissions also reflected the effects of population migration and regional policy enforcement. This study demonstrates the utility of machine learning in diagnosing abrupt air pollution events and provides insights for targeted mitigation during episodic high-emission periods.