提高氧化有机气溶的差异化:一种机器学习方法来区分本地和跨境污染
Lu Lei1, Wei Xu2, Chunshui Lin3
1School of Natural Sciences, Ryan Institute's Centre for Climate & Air Pollution Studies, University of Galway, Galway, H91 CF50 Ireland.
概括
机器学习增强了都柏林有氧有机气溶源的分配. 一个新的模型区分了局部污染和运输污染,揭示了局部供暖是清洁空气战略的关键来源.
科学领域:
- 大气化学和物理大气化学和物理
- 环境科学 环境科学
- 数据科学和机器学习应用程序数据科学和机器学习应用程序
背景情况:
- 精确的颗粒物 (PM),特别是有机气溶 (OA) 的来源分配对于有效的空气质量管理至关重要.
- 传统的方法,如正矩阵因子化 (PMF) 面临的挑战在区分氧化OA (OOA) 的来源,由于类似的化学特征.
- 在有针对性的减排政策中,区分本地和跨境OOA来源至关重要.
研究的目的:
- 开发和应用机器学习 (ML) 模型,以改善都柏林氧化OA (OOA) 的来源分配.
- 要区分较少氧化OOA (LO-OOA) 和较多氧化OOA (MO-OOA) 以及它们各自的本地和跨境贡献.
- 提供对OOA的来源和形成机制的见解,以告知空气质量法规.
主要方法:
- 使用支持向量的回归机器学习模型与滚动正矩阵因子化 (PMF) 分析相结合.
- 分析了2016年至2023年的都柏林颗粒物物质数据.
- 将OOA分为LO-OOA和MO-OOA,并进一步将局部 (LO-OOAlocal,MO-OOAlocal) 与跨境OOA组件分开.
主要成果:
- 在OOA中,OOA占OA总量的很大一部分 (47-74%).
- ML模型成功地将本地OOA与跨境运输区分开来,在各种污染场景中表现出强的表现.
- 当地化石燃料排放 (碳化合物类OA,煤炭) 显著影响了LO-OOA,而MO-OOA受到LO-OOA的影响.
- 在污染事件中,当地排放占总OA的68%,在供暖时间上升到78%,尽管有跨境贡献.
结论:
- 开发的ML模型通过将本地和跨境贡献分开,有效地提高了OOA来源分配.
- 地方供暖排放被确定为都柏林的OA的关键来源,强调需要减少当地排放.
- 对OOA来源的定量分离为未来的空气质量管理和监管策略提供了有价值的数据.
相关概念视频
Atomic Emission Spectroscopy: Interference
132
In atomic emission spectroscopy (AES), high-temperature atomizers excite a broad range of elements and molecules that generate complex emissions from sources such as oxides, hydroxides, and flame combustion products in the flame or plasma. Several strategies can be employed to minimize spectral interferences caused by overlapping emission lines or bands. These include increasing instrument resolution, choosing alternative emission lines, optimally placing the detector in low-background regions,...
132
Sampling Methods: Sample Types
167
Sampling materials are classified into three main types: solid, liquid, and gas.
Solid samples include a variety of substances, such as sediments from water bodies, soil, metals, and biological tissues. Two standard methods for extracting sediments from water bodies are grab sampling and piston coring. Grab sampling involves using a device to collect a discrete sediment sample from the bottom of a water body with minimal disturbance. Grab samples do not always represent the entire area due to...
Solid samples include a variety of substances, such as sediments from water bodies, soil, metals, and biological tissues. Two standard methods for extracting sediments from water bodies are grab sampling and piston coring. Grab sampling involves using a device to collect a discrete sediment sample from the bottom of a water body with minimal disturbance. Grab samples do not always represent the entire area due to...
167


