Articles | Volume 17, issue 9
https://doi.org/10.5194/gmd-17-3617-2024
https://doi.org/10.5194/gmd-17-3617-2024
Development and technical paper
 | 
06 May 2024
Development and technical paper |  | 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, Mengyuan Zhang, Yueqi Gao, Peng Wang, Qingyan Fu, and Hongliang Zhang

Related authors

Reconstructing long-term (1980–2022) daily ground particulate matter concentrations in India (LongPMInd)
Shuai Wang, Mengyuan Zhang, Hui Zhao, Peng Wang, Sri Harsha Kota, Qingyan Fu, Cong Liu, and Hongliang Zhang
Earth Syst. Sci. Data, 16, 3565–3577, https://doi.org/10.5194/essd-16-3565-2024,https://doi.org/10.5194/essd-16-3565-2024, 2024
Short summary

Related subject area

Atmospheric sciences
The sensitivity of aerosol data assimilation to vertical profiles: case study of dust storm assimilation with LOTOS-EUROS v2.2
Mijie Pang, Jianbing Jin, Ting Yang, Xi Chen, Arjo Segers, Batjargal Buyantogtokh, Yixuan Gu, Jiandong Li, Hai Xiang Lin, Hong Liao, and Wei Han
Geosci. Model Dev., 18, 3781–3798, https://doi.org/10.5194/gmd-18-3781-2025,https://doi.org/10.5194/gmd-18-3781-2025, 2025
Short summary
Knowledge-inspired fusion strategies for the inference of PM2.5 values with a neural network
Matthieu Dabrowski, José Mennesson, Jérôme Riedi, Chaabane Djeraba, and Pierre Nabat
Geosci. Model Dev., 18, 3707–3733, https://doi.org/10.5194/gmd-18-3707-2025,https://doi.org/10.5194/gmd-18-3707-2025, 2025
Short summary
Tuning the ICON-A 2.6.4 climate model with machine-learning-based emulators and history matching
Pauline Bonnet, Lorenzo Pastori, Mierk Schwabe, Marco Giorgetta, Fernando Iglesias-Suarez, and Veronika Eyring
Geosci. Model Dev., 18, 3681–3706, https://doi.org/10.5194/gmd-18-3681-2025,https://doi.org/10.5194/gmd-18-3681-2025, 2025
Short summary
A novel method for quantifying the contribution of regional transport to PM2.5 in Beijing (2013–2020): combining machine learning with concentration-weighted trajectory analysis
Kang Hu, Hong Liao, Dantong Liu, Jianbing Jin, Lei Chen, Siyuan Li, Yangzhou Wu, Changhao Wu, Shitong Zhao, Xiaotong Jiang, Ping Tian, Kai Bi, Ye Wang, and Delong Zhao
Geosci. Model Dev., 18, 3623–3634, https://doi.org/10.5194/gmd-18-3623-2025,https://doi.org/10.5194/gmd-18-3623-2025, 2025
Short summary
Quantification of CO2 hotspot emissions from OCO-3 SAM CO2 satellite images using deep learning methods
Joffrey Dumont Le Brazidec, Pierre Vanderbecken, Alban Farchi, Grégoire Broquet, Gerrit Kuhlmann, and Marc Bocquet
Geosci. Model Dev., 18, 3607–3622, https://doi.org/10.5194/gmd-18-3607-2025,https://doi.org/10.5194/gmd-18-3607-2025, 2025
Short summary

Cited articles

Aleksankina, K., Reis, S., Vieno, M., and Heal, M. R.: Advanced methods for uncertainty assessment and global sensitivity analysis of an Eulerian atmospheric chemistry transport model, Atmos. Chem. Phys., 19, 2881–2898, https://doi.org/10.5194/acp-19-2881-2019, 2019. 
Bai, K., Li, K., Ma, M., Li, K., Li, Z., Guo, J., Chang, N.-B., Tan, Z., and Han, D.: LGHAP: the Long-term Gap-free High-resolution Air Pollutant concentration dataset, derived via tensor-flow-based multimodal data fusion, Earth Syst. Sci. Data, 14, 907–927, https://doi.org/10.5194/essd-14-907-2022, 2022. 
Beekmann, M. and Derognat, C.: Monte Carlo uncertainty analysis of a regional-scale transport chemistry model constrained by measurements from the atmospheric pollution over the Paris area (ESQUIF) campaign, J. Geophys. Res.-Atmos., 108, 8859, 10.1029/2003JD003391, 2003. 
Bei, N., Wu, J., Elser, M., Feng, T., Cao, J., El-Haddad, I., Li, X., Huang, R., Li, Z., Long, X., Xing, L., Zhao, S., Tie, X., Prévôt, A. S. H., and Li, G.: Impacts of meteorological uncertainties on the haze formation in Beijing–Tianjin–Hebei (BTH) during wintertime: a case study, Atmos. Chem. Phys., 17, 14579–14591, https://doi.org/10.5194/acp-17-14579-2017, 2017. 
Belgiu, M. and Drăguţ, L.: Random forest in remote sensing: A review of applications and future directions, ISPRS J. Photogramm., 114, 24–31, 2016. 
Download
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.
Share