Long-term ozone formation sensitivity in China: spatiotemporal evolution and machine learning attribution

Lin, Jinglan; Wu, Liqing; Chen, Chujun; Wu, Yongkang; Lin, Rui; Wang, Xuemei; Chen, Weihua

doi:10.5194/acp-26-7081-2026

Articles | Volume 26, issue 10

https://doi.org/10.5194/acp-26-7081-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/acp-26-7081-2026

© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 26, issue 10

Research article

|

22 May 2026

Research article |

| 22 May 2026

Long-term ozone formation sensitivity in China: spatiotemporal evolution and machine learning attribution

Jinglan Lin, Liqing Wu, Chujun Chen, Yongkang Wu, Rui Lin, Xuemei Wang, and Weihua Chen

Supplement

https://doi.org/10.5194/acp-26-7081-2026-supplement

Data sets

OMI/Aura Surface UVB Irradiance and Erythemal Dose Daily L3 Global Gridded 1.0 degree x 1.0 degree V3 (OMUVBd) N. A. Krotkov et al. https://doi.org/10.5067/Aura/OMI/DATA3007

OMI/Aura Formaldehyde (HCHO) Total Column Daily L3 Weighted Mean Global 0.1deg Lat/Lon Grid V003 K. Chance https://doi.org/10.5067/Aura/OMI/DATA3010

ERA5 monthly averaged data on pressure levels from 1940 to present H. Hersbach et al. https://doi.org/10.24381/cds.6860a573

ERA5 monthly averaged data on single levels from 1940 to present H. Hersbach et al. https://doi.org/10.24381/cds.f17050d7

Download

Article (10709 KB)
Full-text XML

Short summary

By integrating satellite data from 2005–2023 (warm seasons), we analyzed the spatiotemporal evolution of ozone formation sensitivity across China. Results show a shift toward NO_x-limited and transitional regimes under policy measures. Explainable machine learning suggests this evolution is mainly associated with emission changes, while meteorological factors become increasingly important under cleaner conditions. These findings support more precise, region-specific ozone control strategies.