Articles | Volume 17, issue 9
https://doi.org/10.5194/gmd-17-3617-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-17-3617-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Development and technical paper
| 
06 May 2024
Development and technical paper |
| 06 May 2024
| 06 May 2024
Diagnosing drivers of PM2.5 simulation biases in China from meteorology, chemical composition, and emission sources using an efficient machine learning method
Shuai Wang
Department of Environmental Science and Engineering, Fudan University, Shanghai 200438, China
Mengyuan Zhang
Department of Environmental Science and Engineering, Fudan University, Shanghai 200438, China
Yueqi Gao
Department of Environmental Science and Engineering, Fudan University, Shanghai 200438, China
Peng Wang
Department of Atmospheric and Oceanic Sciences and Institute of Atmospheric Sciences, Fudan University, Shanghai 200438, China
IRDR ICoE on Risk Interconnectivity and Governance on Weather/Climate Extremes Impact and Public Health, Fudan University, Shanghai, China
Qingyan Fu
Shanghai Environmental Monitoring Center, Shanghai 200235, China
Department of Environmental Science and Engineering, Fudan University, Shanghai 200438, China
IRDR ICoE on Risk Interconnectivity and Governance on Weather/Climate Extremes Impact and Public Health, Fudan University, Shanghai, China
Institute of Eco-Chongming (IEC), Shanghai 200062, China
Viewed
Total article views: 4,424 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 10 Aug 2023)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 3,227 | 1,019 | 178 | 4,424 | 364 | 166 | 293 |
- HTML: 3,227
- PDF: 1,019
- XML: 178
- Total: 4,424
- Supplement: 364
- BibTeX: 166
- EndNote: 293
Total article views: 2,019 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 06 May 2024)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 1,539 | 393 | 87 | 2,019 | 130 | 76 | 155 |
- HTML: 1,539
- PDF: 393
- XML: 87
- Total: 2,019
- Supplement: 130
- BibTeX: 76
- EndNote: 155
Total article views: 2,405 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 10 Aug 2023)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 1,688 | 626 | 91 | 2,405 | 234 | 90 | 138 |
- HTML: 1,688
- PDF: 626
- XML: 91
- Total: 2,405
- Supplement: 234
- BibTeX: 90
- EndNote: 138
Viewed (geographical distribution)
Total article views: 4,424 (including HTML, PDF, and XML)
Thereof 4,356 with geography defined
and 68 with unknown origin.
Total article views: 2,019 (including HTML, PDF, and XML)
Thereof 1,975 with geography defined
and 44 with unknown origin.
Total article views: 2,405 (including HTML, PDF, and XML)
Thereof 2,381 with geography defined
and 24 with unknown origin.
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
Cited
16 citations as recorded by crossref.
- Hybridizing deep learning models and a chemical transport model for medium-term PM2.5 forecasts in the Yangtze River Delta, China M. Zhu et al. https://doi.org/10.1016/j.jes.2026.01.080
- An Evaluation of the Current Short-term PM2.5 Forecasting Accuracy in Seoul B. Yeon et al. https://doi.org/10.1007/s13143-025-00426-3
- Assessment of bias correction technique to improve ozone reanalysis dataset over India T. Gangwar et al. https://doi.org/10.1007/s42865-025-00109-x
- Advances and Perspectives in Atmospheric Environment Modeling in China Z. Wang et al. https://doi.org/10.1007/s00376-026-5677-5
- Quantifying Meteorological and Emission-Control Contributions to PM2.5 and Ozone Changes During the 2023 G20 Summit in New Delhi Z. Han et al. https://doi.org/10.3390/atmos17060584
- High-resolution anthropogenic emission inventory for China (2015–2024): Spatiotemporal changes and environmental application D. Li et al. https://doi.org/10.1016/j.atmosenv.2025.121495
- Impacts of uncertainties in Chinese NH3 emissions on PM2.5 concentrations over mainland China and downwind regions H. Choe et al. https://doi.org/10.1016/j.envpol.2025.127159
- Unleashing the potential of geostationary satellite observations in air quality forecasting through artificial intelligence techniques C. Zhang et al. https://doi.org/10.5194/acp-25-759-2025
- Evaluation of three chemical transport models for extreme PM10 events in Morocco and improvement of forecasts using hybrid CTM–Random Forest models Y. Chelhaoui et al. https://doi.org/10.1016/j.scitotenv.2025.180668
- Impacts of reductions in anthropogenic emissions from 2015 to 2024 on PM2.5 and meteorological conditions over China D. Li et al. https://doi.org/10.1016/j.atmosenv.2025.121658
- Machine learning-guided integration of fixed and mobile sensors for high resolution urban PM2.5 mapping T. Li et al. https://doi.org/10.1038/s41612-025-00984-3
- Specific-Source Insights into Changes of O3 Concentrations and Health Risks in China Y. Wang et al. https://doi.org/10.1021/acs.est.6c01808
- Improving dust aerosol simulation over northern China: Synergy of updated numerical models and machine learning post-processing T. Sha et al. https://doi.org/10.1016/j.atmosenv.2026.122098
- Impact of marine chlorine emissions on secondary organic aerosols in North China Plain Z. Gao et al. https://doi.org/10.1016/j.envpol.2025.126524
- Understanding the spatial heterogeneity of black carbon variation drivers in China: Views from explainable machine learning H. Zheng et al. https://doi.org/10.1016/j.atmosres.2026.108749
- The impact of China's Clean Air Action and future strategies: Actions targeting regionally dominant sources X. Peng et al. https://doi.org/10.1016/j.jenvman.2025.127680
16 citations as recorded by crossref.
- Hybridizing deep learning models and a chemical transport model for medium-term PM2.5 forecasts in the Yangtze River Delta, China M. Zhu et al. https://doi.org/10.1016/j.jes.2026.01.080
- An Evaluation of the Current Short-term PM2.5 Forecasting Accuracy in Seoul B. Yeon et al. https://doi.org/10.1007/s13143-025-00426-3
- Assessment of bias correction technique to improve ozone reanalysis dataset over India T. Gangwar et al. https://doi.org/10.1007/s42865-025-00109-x
- Advances and Perspectives in Atmospheric Environment Modeling in China Z. Wang et al. https://doi.org/10.1007/s00376-026-5677-5
- Quantifying Meteorological and Emission-Control Contributions to PM2.5 and Ozone Changes During the 2023 G20 Summit in New Delhi Z. Han et al. https://doi.org/10.3390/atmos17060584
- High-resolution anthropogenic emission inventory for China (2015–2024): Spatiotemporal changes and environmental application D. Li et al. https://doi.org/10.1016/j.atmosenv.2025.121495
- Impacts of uncertainties in Chinese NH3 emissions on PM2.5 concentrations over mainland China and downwind regions H. Choe et al. https://doi.org/10.1016/j.envpol.2025.127159
- Unleashing the potential of geostationary satellite observations in air quality forecasting through artificial intelligence techniques C. Zhang et al. https://doi.org/10.5194/acp-25-759-2025
- Evaluation of three chemical transport models for extreme PM10 events in Morocco and improvement of forecasts using hybrid CTM–Random Forest models Y. Chelhaoui et al. https://doi.org/10.1016/j.scitotenv.2025.180668
- Impacts of reductions in anthropogenic emissions from 2015 to 2024 on PM2.5 and meteorological conditions over China D. Li et al. https://doi.org/10.1016/j.atmosenv.2025.121658
- Machine learning-guided integration of fixed and mobile sensors for high resolution urban PM2.5 mapping T. Li et al. https://doi.org/10.1038/s41612-025-00984-3
- Specific-Source Insights into Changes of O3 Concentrations and Health Risks in China Y. Wang et al. https://doi.org/10.1021/acs.est.6c01808
- Improving dust aerosol simulation over northern China: Synergy of updated numerical models and machine learning post-processing T. Sha et al. https://doi.org/10.1016/j.atmosenv.2026.122098
- Impact of marine chlorine emissions on secondary organic aerosols in North China Plain Z. Gao et al. https://doi.org/10.1016/j.envpol.2025.126524
- Understanding the spatial heterogeneity of black carbon variation drivers in China: Views from explainable machine learning H. Zheng et al. https://doi.org/10.1016/j.atmosres.2026.108749
- The impact of China's Clean Air Action and future strategies: Actions targeting regionally dominant sources X. Peng et al. https://doi.org/10.1016/j.jenvman.2025.127680
Saved (final revised paper)
Latest update: 21 Jul 2026
Short summary
Numerical models are widely used in air pollution modeling but suffer from significant biases. The machine learning model designed in this study shows high efficiency in identifying such biases. Meteorology (relative humidity and cloud cover), chemical composition (secondary organic components and dust aerosols), and emission sources (residential activities) are diagnosed as the main drivers of bias in modeling PM2.5, a typical air pollutant. The results will help to improve numerical models.
Numerical models are widely used in air pollution modeling but suffer from significant biases....
