An Ensemble Machine Learning Approach for Predicting Sources of Organic Aerosols Measured by Aerosol Mass Spectrometry

Yunjiang Zhang*, Jie Fang, Qingxiao Meng, Xinlei Ge, Hasna Chebaicheb, Olivier Favez and Jean-Eudes Petit*, 
{"title":"An Ensemble Machine Learning Approach for Predicting Sources of Organic Aerosols Measured by Aerosol Mass Spectrometry","authors":"Yunjiang Zhang*,&nbsp;Jie Fang,&nbsp;Qingxiao Meng,&nbsp;Xinlei Ge,&nbsp;Hasna Chebaicheb,&nbsp;Olivier Favez and Jean-Eudes Petit*,&nbsp;","doi":"10.1021/acsestair.4c0026210.1021/acsestair.4c00262","DOIUrl":null,"url":null,"abstract":"<p >Long-term source apportionment of atmospheric organic aerosols (OA) is essential for supporting air pollution management strategies. While aerosol mass spectrometry (AMS) combined with traditional source apportionment tools can accurately identify various OA sources, they face efficiency challenges when processing large volumes of long-term data. This study proposes an ensemble machine learning approach to efficiently apportion OA sources from long-term AMS measurements. Using six-year observation of a simplified version of AMS (i.e., ACSM) in the Paris region along with OA factor data derived from positive matrix factorization analysis, we developed an ensemble machine learning source apportionment model. Compared to individual machine learning algorithms, the ensemble model substantially reduced the root-mean-square error (RMSE) and increased the correlation coefficient in predicting OA sources by approximately 30% and 5%, respectively. Sensitivity analysis with five years of baseline data revealed that model performance relatively stabilizes when the training data exceeds two years, with RMSE values for primary and secondary OA factors at 0.31–0.45 μg/m<sup>3</sup> and 0.69–0.84 μg/m<sup>3</sup>, respectively. This ensemble model not only enhances the efficiency of long-term OA source apportionment but also holds potential for near-real-time online applications.</p>","PeriodicalId":100014,"journal":{"name":"ACS ES&T Air","volume":"2 3","pages":"378–385 378–385"},"PeriodicalIF":0.0000,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS ES&T Air","FirstCategoryId":"1085","ListUrlMain":"https://pubs.acs.org/doi/10.1021/acsestair.4c00262","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Long-term source apportionment of atmospheric organic aerosols (OA) is essential for supporting air pollution management strategies. While aerosol mass spectrometry (AMS) combined with traditional source apportionment tools can accurately identify various OA sources, they face efficiency challenges when processing large volumes of long-term data. This study proposes an ensemble machine learning approach to efficiently apportion OA sources from long-term AMS measurements. Using six-year observation of a simplified version of AMS (i.e., ACSM) in the Paris region along with OA factor data derived from positive matrix factorization analysis, we developed an ensemble machine learning source apportionment model. Compared to individual machine learning algorithms, the ensemble model substantially reduced the root-mean-square error (RMSE) and increased the correlation coefficient in predicting OA sources by approximately 30% and 5%, respectively. Sensitivity analysis with five years of baseline data revealed that model performance relatively stabilizes when the training data exceeds two years, with RMSE values for primary and secondary OA factors at 0.31–0.45 μg/m3 and 0.69–0.84 μg/m3, respectively. This ensemble model not only enhances the efficiency of long-term OA source apportionment but also holds potential for near-real-time online applications.

Abstract Image

用集成机器学习方法预测气溶胶质谱测量的有机气溶胶来源
大气有机气溶胶(OA)的长期来源分配对于支持空气污染管理战略至关重要。虽然气溶胶质谱(AMS)与传统的源分配工具相结合可以准确地识别各种OA源,但在处理大量长期数据时,它们面临效率挑战。本研究提出了一种集成机器学习方法来有效地分配来自长期AMS测量的OA源。利用对巴黎地区简化版AMS(即ACSM)的6年观测以及来自正矩阵分解分析的OA因子数据,我们开发了一个集成机器学习源分配模型。与单个机器学习算法相比,集成模型显著降低了预测OA源的均方根误差(RMSE),并将相关系数分别提高了约30%和5%。基于5年基线数据的敏感性分析表明,当训练数据超过2年时,模型性能相对稳定,主要OA因子和次要OA因子的RMSE值分别为0.31 ~ 0.45 μg/m3和0.69 ~ 0.84 μg/m3。该集成模型不仅提高了长期OA源分配的效率,而且具有近实时在线应用的潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信