Explainable ensemble machine learning revealing spatiotemporal heterogeneity in driving factors of particulate nitro-aromatic compounds in eastern China
<p>Nitro-aromatic compounds (NACs) are important atmospheric pollutants that impact air quality, atmospheric chemistry, and human health. Understanding the relationship between NAC formation and key environmental driving factors is crucial for mitigating their environmental and health impacts....
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2025-08-01
|
| Series: | Atmospheric Chemistry and Physics |
| Online Access: | https://acp.copernicus.org/articles/25/8407/2025/acp-25-8407-2025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839606295613669376 |
|---|---|
| author | M. Li X. Wang T. Li T. Li Y. Wang Y. Jiang Y. Jiang Y. Zhu W. Nie R. Li J. Gao L. Xue Q. Zhang W. Wang |
| author_facet | M. Li X. Wang T. Li T. Li Y. Wang Y. Jiang Y. Jiang Y. Zhu W. Nie R. Li J. Gao L. Xue Q. Zhang W. Wang |
| author_sort | M. Li |
| collection | DOAJ |
| description | <p>Nitro-aromatic compounds (NACs) are important atmospheric pollutants that impact air quality, atmospheric chemistry, and human health. Understanding the relationship between NAC formation and key environmental driving factors is crucial for mitigating their environmental and health impacts. In this work, we combined an ensemble machine learning (EML) model with the SHapley Additive exPlanation (SHAP) and positive matrix factorization (PMF) model to identify the key driving factors for ambient particulate NACs, covering primary emissions, secondary formation, and meteorological conditions based on field observations at urban, rural, and mountain sites in eastern China. The EML model effectively reproduced ambient NACs and recognized that anthropogenic emissions (i.e., coal combustion, traffic emission, and biomass burning) were the most important driving factors, with a total contribution of 49.3 %, while significant influences from meteorology (27.4 %) and secondary formation (23.3 %) were also confirmed. Seasonal variation analysis showed that direct emissions presented positive responses to NAC concentrations in spring, summer, and autumn, while lower temperatures had the largest positive impact in winter. By evaluating NAC formation and loss under various locations in winter, we found that anthropogenic sources played a dominant role in increasing NAC levels in urban and rural sites, while reduced ambient temperature, along with secondary formation from gas-phase oxidation, was the main reason for relatively high particulate NAC levels at the mountain site. This work provides a reliable modeling method for understanding the dominant sources and influencing factors for atmospheric NACs and highlights the necessity of strengthening emission source controls to mitigate organic aerosol pollution.</p> |
| format | Article |
| id | doaj-art-db788cef3d5f4501bca3ffbdb925f789 |
| institution | Matheson Library |
| issn | 1680-7316 1680-7324 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Atmospheric Chemistry and Physics |
| spelling | doaj-art-db788cef3d5f4501bca3ffbdb925f7892025-08-01T08:18:38ZengCopernicus PublicationsAtmospheric Chemistry and Physics1680-73161680-73242025-08-01258407842510.5194/acp-25-8407-2025Explainable ensemble machine learning revealing spatiotemporal heterogeneity in driving factors of particulate nitro-aromatic compounds in eastern ChinaM. Li0X. Wang1T. Li2T. Li3Y. Wang4Y. Jiang5Y. Jiang6Y. Zhu7W. Nie8R. Li9J. Gao10L. Xue11Q. Zhang12W. Wang13Environment Research Institute, Shandong University, Qingdao, Shandong 266237, ChinaEnvironment Research Institute, Shandong University, Qingdao, Shandong 266237, ChinaEnvironment Research Institute, Shandong University, Qingdao, Shandong 266237, ChinaJoint International Research Laboratory of Atmospheric and Earth System Sciences, School of Atmospheric Sciences, Nanjing University, Nanjing 210023, ChinaEnvironment Research Institute, Shandong University, Qingdao, Shandong 266237, ChinaEnvironment Research Institute, Shandong University, Qingdao, Shandong 266237, ChinaJoint International Research Laboratory of Atmospheric and Earth System Sciences, School of Atmospheric Sciences, Nanjing University, Nanjing 210023, ChinaEnvironment Research Institute, Shandong University, Qingdao, Shandong 266237, ChinaJoint International Research Laboratory of Atmospheric and Earth System Sciences, School of Atmospheric Sciences, Nanjing University, Nanjing 210023, ChinaSchool of Public Health, MOE Key Laboratory of Coal Environmental Pathogenicity and Prevention, Shanxi Medical University, Taiyuan 030001, ChinaState Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Science, Beijing 100012, ChinaEnvironment Research Institute, Shandong University, Qingdao, Shandong 266237, ChinaEnvironment Research Institute, Shandong University, Qingdao, Shandong 266237, ChinaEnvironment Research Institute, Shandong University, Qingdao, Shandong 266237, China<p>Nitro-aromatic compounds (NACs) are important atmospheric pollutants that impact air quality, atmospheric chemistry, and human health. Understanding the relationship between NAC formation and key environmental driving factors is crucial for mitigating their environmental and health impacts. In this work, we combined an ensemble machine learning (EML) model with the SHapley Additive exPlanation (SHAP) and positive matrix factorization (PMF) model to identify the key driving factors for ambient particulate NACs, covering primary emissions, secondary formation, and meteorological conditions based on field observations at urban, rural, and mountain sites in eastern China. The EML model effectively reproduced ambient NACs and recognized that anthropogenic emissions (i.e., coal combustion, traffic emission, and biomass burning) were the most important driving factors, with a total contribution of 49.3 %, while significant influences from meteorology (27.4 %) and secondary formation (23.3 %) were also confirmed. Seasonal variation analysis showed that direct emissions presented positive responses to NAC concentrations in spring, summer, and autumn, while lower temperatures had the largest positive impact in winter. By evaluating NAC formation and loss under various locations in winter, we found that anthropogenic sources played a dominant role in increasing NAC levels in urban and rural sites, while reduced ambient temperature, along with secondary formation from gas-phase oxidation, was the main reason for relatively high particulate NAC levels at the mountain site. This work provides a reliable modeling method for understanding the dominant sources and influencing factors for atmospheric NACs and highlights the necessity of strengthening emission source controls to mitigate organic aerosol pollution.</p>https://acp.copernicus.org/articles/25/8407/2025/acp-25-8407-2025.pdf |
| spellingShingle | M. Li X. Wang T. Li T. Li Y. Wang Y. Jiang Y. Jiang Y. Zhu W. Nie R. Li J. Gao L. Xue Q. Zhang W. Wang Explainable ensemble machine learning revealing spatiotemporal heterogeneity in driving factors of particulate nitro-aromatic compounds in eastern China Atmospheric Chemistry and Physics |
| title | Explainable ensemble machine learning revealing spatiotemporal heterogeneity in driving factors of particulate nitro-aromatic compounds in eastern China |
| title_full | Explainable ensemble machine learning revealing spatiotemporal heterogeneity in driving factors of particulate nitro-aromatic compounds in eastern China |
| title_fullStr | Explainable ensemble machine learning revealing spatiotemporal heterogeneity in driving factors of particulate nitro-aromatic compounds in eastern China |
| title_full_unstemmed | Explainable ensemble machine learning revealing spatiotemporal heterogeneity in driving factors of particulate nitro-aromatic compounds in eastern China |
| title_short | Explainable ensemble machine learning revealing spatiotemporal heterogeneity in driving factors of particulate nitro-aromatic compounds in eastern China |
| title_sort | explainable ensemble machine learning revealing spatiotemporal heterogeneity in driving factors of particulate nitro aromatic compounds in eastern china |
| url | https://acp.copernicus.org/articles/25/8407/2025/acp-25-8407-2025.pdf |
| work_keys_str_mv | AT mli explainableensemblemachinelearningrevealingspatiotemporalheterogeneityindrivingfactorsofparticulatenitroaromaticcompoundsineasternchina AT xwang explainableensemblemachinelearningrevealingspatiotemporalheterogeneityindrivingfactorsofparticulatenitroaromaticcompoundsineasternchina AT tli explainableensemblemachinelearningrevealingspatiotemporalheterogeneityindrivingfactorsofparticulatenitroaromaticcompoundsineasternchina AT tli explainableensemblemachinelearningrevealingspatiotemporalheterogeneityindrivingfactorsofparticulatenitroaromaticcompoundsineasternchina AT ywang explainableensemblemachinelearningrevealingspatiotemporalheterogeneityindrivingfactorsofparticulatenitroaromaticcompoundsineasternchina AT yjiang explainableensemblemachinelearningrevealingspatiotemporalheterogeneityindrivingfactorsofparticulatenitroaromaticcompoundsineasternchina AT yjiang explainableensemblemachinelearningrevealingspatiotemporalheterogeneityindrivingfactorsofparticulatenitroaromaticcompoundsineasternchina AT yzhu explainableensemblemachinelearningrevealingspatiotemporalheterogeneityindrivingfactorsofparticulatenitroaromaticcompoundsineasternchina AT wnie explainableensemblemachinelearningrevealingspatiotemporalheterogeneityindrivingfactorsofparticulatenitroaromaticcompoundsineasternchina AT rli explainableensemblemachinelearningrevealingspatiotemporalheterogeneityindrivingfactorsofparticulatenitroaromaticcompoundsineasternchina AT jgao explainableensemblemachinelearningrevealingspatiotemporalheterogeneityindrivingfactorsofparticulatenitroaromaticcompoundsineasternchina AT lxue explainableensemblemachinelearningrevealingspatiotemporalheterogeneityindrivingfactorsofparticulatenitroaromaticcompoundsineasternchina AT qzhang explainableensemblemachinelearningrevealingspatiotemporalheterogeneityindrivingfactorsofparticulatenitroaromaticcompoundsineasternchina AT wwang explainableensemblemachinelearningrevealingspatiotemporalheterogeneityindrivingfactorsofparticulatenitroaromaticcompoundsineasternchina |