Machine Learning‐Driven Identification of Factors Governing Secondary Organic Aerosol Formation During Autumn in Beijing
Abstract Organic aerosol (OA) and its constituent particulate organic nitrate (pON) are critical factors affecting air quality and climate, yet their sources and transformation processes remain poorly understood. Machine learning (ML) excels at identifying nonlinear relationships among features, and in this study, interpretable ML is employed to identify the key factors governing OA and pON formation during an autumn field campaign in Beijing. Results demonstrate that both aerosol liquid water content (ALWC) and aerosol surface area are two primary factors governing the formation of OA and pON. Specifically, OA formation was predominantly driven by ALWC that is associated with aqueous‐phase processes or gas‐liquid partitioning, particularly during severe pollution episodes. pON formation was constrained by aerosol surface area, indicating the vital contribution of gas‐to‐particle partitioning from low volatility vapors or interface processes of precursors. Our results provide new insights into OA formation mechanisms.
Authors
- Jingkun Jiang (ORCID: https://orcid.org/0000-0001-6172-190X)
- Biwu Chu (ORCID: https://orcid.org/0000-0002-7548-5669)
- Kebin He (ORCID: https://orcid.org/0000-0001-6006-9323)
- Wei Huang
- Quan Liu (ORCID: https://orcid.org/0000-0003-0382-5764)
- Tianzeng Chen (ORCID: https://orcid.org/0000-0001-8123-0534)
- Yonghong Wang (ORCID: https://orcid.org/0000-0003-2498-9143)
- Qingxin Ma (ORCID: https://orcid.org/0000-0002-9668-7008)
- Yujing Mu (ORCID: https://orcid.org/0000-0002-7048-2856)
- Hao Li (ORCID: https://orcid.org/0000-0002-5785-247X)
- Jun Liu (ORCID: https://orcid.org/0000-0002-3065-799X)
- Peng Zhang (ORCID: https://orcid.org/0000-0002-1806-4200)
- Shuxiao Wang (ORCID: https://orcid.org/0000-0001-9727-1963)
- Yanlin Zhang (ORCID: https://orcid.org/0000-0002-8722-8635)
- Shuying Li (ORCID: https://orcid.org/0000-0003-0786-5931)
- Yuan Liu (ORCID: https://orcid.org/0000-0003-0672-2242)
- Douglas Worsnop
- Hong He (ORCID: https://orcid.org/0000-0001-8476-8217)
Institutions
- University of Helsinki (FI)
- Xi'an University of Architecture and Technology (CN)
- Chinese Academy of Sciences (CN)
- Washington University in St. Louis (US)
- Ministry of Ecology and Environment (CN)
- Helsinki Institute of Physics (FI)
- Helsinki Institute for Information Technology (FI)
- Aerodyne Research (US)
- Institute of Urban Environment (CN)
- State Key Joint Laboratory of Environment Simulation and Pollution Control (CN)
- Chinese Academy of Meteorological Sciences (CN)
- Research Center for Eco-Environmental Sciences (CN)
- Chinese Research Academy of Environmental Sciences (CN)
- University of Chinese Academy of Sciences (CN)
- Tsinghua University (CN)
Publication Details
- Journal
- Geophysical Research Letters
- Published
- 2025-12-17
- DOI
- https://doi.org/10.1029/2025gl119745
- Citations
- 1
- Primary Topic
- Atmospheric chemistry and aerosols
- Type
- article
- Field-Weighted Citation Impact
- 1.30
Funders
- National Natural Science Foundation of China