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
Indian Institute of Tropical Meteorology (IITM) High-Resolution Global Forecast Model version 1: an attempt to resolve monsoon prediction deadlock
R. Phani Murali Krishna, Siddharth Kumar, A. Gopinathan Prajeesh, Peter Bechtold, Nils Wedi, Kumar Roy, Malay Ganai, B. Revanth Reddy, Snehlata Tirkey, Tanmoy Goswami, Radhika Kanase, Sahadat Sarkar, Medha Deshpande, and Parthasarathi Mukhopadhyay
Geosci. Model Dev., 18, 1879–1894, https://doi.org/10.5194/gmd-18-1879-2025,https://doi.org/10.5194/gmd-18-1879-2025, 2025
Short summary
Cell-tracking-based framework for assessing nowcasting model skill in reproducing growth and decay of convective rainfall
Jenna Ritvanen, Seppo Pulkkinen, Dmitri Moisseev, and Daniele Nerini
Geosci. Model Dev., 18, 1851–1878, https://doi.org/10.5194/gmd-18-1851-2025,https://doi.org/10.5194/gmd-18-1851-2025, 2025
Short summary
NeuralMie (v1.0): an aerosol optics emulator
Andrew Geiss and Po-Lun Ma
Geosci. Model Dev., 18, 1809–1827, https://doi.org/10.5194/gmd-18-1809-2025,https://doi.org/10.5194/gmd-18-1809-2025, 2025
Short summary
Simulation performance of planetary boundary layer schemes in WRF v4.3.1 for near-surface wind over the western Sichuan Basin: a single-site assessment
Qin Wang, Bo Zeng, Gong Chen, and Yaoting Li
Geosci. Model Dev., 18, 1769–1784, https://doi.org/10.5194/gmd-18-1769-2025,https://doi.org/10.5194/gmd-18-1769-2025, 2025
Short summary
FootNet v1.0: development of a machine learning emulator of atmospheric transport
Tai-Long He, Nikhil Dadheech, Tammy M. Thompson, and Alexander J. Turner
Geosci. Model Dev., 18, 1661–1671, https://doi.org/10.5194/gmd-18-1661-2025,https://doi.org/10.5194/gmd-18-1661-2025, 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