Long-term ozone formation sensitivity in China: spatiotemporal evolution and machine learning attribution
4 affiliations
- 1College of Environment and Climate, Jinan University, Guangzhou, 510632, PR China
- 2College of Ocean and Meteorology, Guangdong Ocean University, Zhanjiang, 524000, PR China
- 3High Performance Computing Department, National Supercomputing Center in Shenzhen, Shenzhen, 518000, PR China
- 4Jinan University (Guangzhou, China)
Abstract
Accurate diagnosis of ozone (O3) formation sensitivity (OFS) is crucial for effective control strategies, but a long-term, observation-based, interpretable assessment disentangling the roles of meteorology and emissions at the national scale is lacking. This study integrates OMI tropospheric columns of nitrogen dioxide (NO2) and formaldehyde (HCHO) from 2005 to 2023, using the HCHO/NO2 ratio (FNR) as a proxy to track the spatiotemporal evolution of OFS in China. We develop an explainable machine learning framework coupling Random Forest (RF) and SHapley Additive exPlanations (SHAP) to quantify the contributions of meteorology and emissions at regional scales. Our findings reveal a policy-driven phase reversal in OFS: from 2005 to 2012, rising NO2 columns shifted much of China from NOx-limited to VOC-limited or transitional regimes. Post-2013, the Clean Air Actions led to a decline in NO2 and a modest increase in HCHO, triggering a nationwide return to NOx-limited conditions, especially in eastern China. Regionally, the Sichuan Basin (SCB) remained NOx-limited, the Pearl River Delta (PRD) transitioned rapidly to NOx-limited, and the Beijing-Tianjin-Hebei (BTH), Yangtze River Delta (YRD), and Fenwei Plain (FWP) showed gradual shifts from VOC- to NOx-limited regimes. SHAP analysis identifies temperature and surface shortwave radiation as dominant meteorological drivers, while emission patterns vary regionally: non-methane volatile organic compounds (NMVOCs) dominate in BTH, NOx in PRD, and carbon monoxide (CO) amplifies radical cycling in FWP, YRD, and SCB. These results support a “climate-dominated, emission-modulated” framework for OFS restructuring, offering a transferable diagnostic tool for differentiated O3 control strategies.
Related
- Disentangling forced and internal components in observed climate evolution using spatiotemporal deep learning
- A 25-year assessment of soil salinity in an arid oasis: Spatiotemporal validation and SHAP attribution
- Explainable AI for Geoscientific Regression: Evaluating Sensitivity and Attribution Methods with the Lorenz-63 System and Applications
- Summertime ozone sensitivity to temperature in China: observational evidence and mechanistic attribution in urban and rural areas in the Yangtze River Delta region
- Spatiotemporal evolution and driving factors of ecological risks in the Wujiang River Basin over the past four decades
BibTeX
@article{lin2026longterm,
title = {{Long-term ozone formation sensitivity in China: spatiotemporal evolution and machine learning attribution}},
author = {Jinglan Lin and Liqing Wu and Chujun Chen and Yongkang Wu and Rui Lin and Xuemei Wang and Weihua Chen},
journal = {Atmospheric chemistry and physics},
year = {2026},
month = may,
doi = {10.5194/acp-26-7081-2026},
url = {https://doi.org/10.5194/acp-26-7081-2026},
note = {CC BY},
}
RIS
TY - JOUR
TI - Long-term ozone formation sensitivity in China: spatiotemporal evolution and machine learning attribution
AU - Jinglan Lin
AU - Liqing Wu
AU - Chujun Chen
AU - Yongkang Wu
AU - Rui Lin
AU - Xuemei Wang
AU - Weihua Chen
PY - 2026
DA - 2026/05/22
JO - Atmospheric chemistry and physics
DO - 10.5194/acp-26-7081-2026
UR - https://doi.org/10.5194/acp-26-7081-2026
AB - Accurate diagnosis of ozone (O3) formation sensitivity (OFS) is crucial for effective control strategies, but a long-term, observation-based, interpretable assessment disentangling the roles of meteorology and emissions at the national scale is lacking. This study integrates OMI tropospheric columns of nitrogen dioxide (NO2) and formaldehyde (HCHO) from 2005 to 2023, using the HCHO/NO2 ratio (FNR) as a proxy to track the spatiotemporal evolution of OFS in China. We develop an explainable machine learning framework coupling Random Forest (RF) and SHapley Additive exPlanations (SHAP) to quantify the contributions of meteorology and emissions at regional scales. Our findings reveal a policy-driven phase reversal in OFS: from 2005 to 2012, rising NO2 columns shifted much of China from NOx-limited to VOC-limited or transitional regimes. Post-2013, the Clean Air Actions led to a decline in NO2 and a modest increase in HCHO, triggering a nationwide return to NOx-limited conditions, especially in eastern China. Regionally, the Sichuan Basin (SCB) remained NOx-limited, the Pearl River Delta (PRD) transitioned rapidly to NOx-limited, and the Beijing-Tianjin-Hebei (BTH), Yangtze River Delta (YRD), and Fenwei Plain (FWP) showed gradual shifts from VOC- to NOx-limited regimes. SHAP analysis identifies temperature and surface shortwave radiation as dominant meteorological drivers, while emission patterns vary regionally: non-methane volatile organic compounds (NMVOCs) dominate in BTH, NOx in PRD, and carbon monoxide (CO) amplifies radical cycling in FWP, YRD, and SCB. These results support a “climate-dominated, emission-modulated” framework for OFS restructuring, offering a transferable diagnostic tool for differentiated O3 control strategies.
SN - 1680-7316
SN - 1680-7324
ER -