Advancing Aerosol Chemistry with Machine Learning: A Short Review
Machine learning (ML) models have emerged as powerful tools for advancing aerosol chemistry research, offering the ability to effectively analyze large-scale, high-dimensional, and nonlinear data sets. This review highlights recent advancements in the application of ML models to aerosol chemistry, including predictions of aerosol burdens, precursors and oxidants, sources, formation mechanisms, and physicochemical properties. Additionally, we explore common limitations of current ML approaches and propose potential improvements to enhance their future applications in aerosol chemistry studies. This perspective aims to provide a comprehensive understanding of the opportunities and challenges at the intersection of ML and aerosol chemistry, paving the way for future developments in this field.
Authors
- Baihua Chen
- Ru‐Jin Huang (ORCID: https://orcid.org/0000-0002-4907-9616)
- Haobin Zhong (ORCID: https://orcid.org/0000-0001-9588-7019)
- Chunshui Lin (ORCID: https://orcid.org/0000-0003-3175-6778)
- Ying Wang (ORCID: https://orcid.org/0000-0001-7903-151X)
- Lin Wang (ORCID: https://orcid.org/0000-0002-4905-3432)
- Wei Xu (ORCID: https://orcid.org/0000-0002-9590-1906)
- Lin Yang (ORCID: https://orcid.org/0000-0003-1547-8990)
- Jing Duan (ORCID: https://orcid.org/0000-0003-2182-1847)
- Jingye Ren
Institutions
- Chinese Academy of Sciences (CN)
- Beijing Normal University (CN)
- Jiaxing University (CN)
- Institute of Urban Environment (CN)
- State Laboratory (IE)
- Department of Chemistry and Earth Sciences (BY)
- Institute of Earth Environment (CN)
Publication Details
- Journal
- ACS ES&T Air
- Published
- 2025-11-05
- DOI
- https://doi.org/10.1021/acsestair.5c00001
- Primary Topic
- Atmospheric chemistry and aerosols
- Type
- article
- Field-Weighted Citation Impact
- 0.00