Integrated diagnostic framework for resolving distinct ozone formation mechanisms via observations, modeling, and machine learning
5 affiliations
- 1Key Laboratory of Wetland Ecology and Environment, Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences , Changchun, Jilin, 130102 ,
- 2University of Chinese Academy of Sciences , Beijing, 100049 ,
- 3Public Meteorological Service Centre, China Meteorological Administration , Beijing, 100081 ,
- 4Key Laboratory of Environment Optics and Technology, Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences , Hefei, Anhui, 230031 ,
- 5Jilin Province Ecological Environment Monitoring Center , Changchun, Jilin, 130032 ,
Abstract
Ozone (O3) pollution in relatively high-latitude industrial cities shows spatiotemporal patterns associated with coupled meteorological, transport, and chemical processes, yet its dominant formation mechanisms remain unresolved. This study developed an interpretable diagnostic framework integrating process-resolved Weather Research and Forecasting model coupled with Chemistry (WRF-Chem) simulations, observations, and Extreme Gradient Boosting (XGBoost) interpreted using Shapley additive explanations (SHAP) for Changchun, Northeast China (September 2023–August 2024). Surface daily maximum 8-h average (MDA8) O3 exceedances occurred from April to July, peaking above 200 μg/m3. Lidar monthly means at 0.3–1.0 km peaked from April to June (108.9–111.4 μg/m3), while the 1.0–2.0 and 2.0–3.0 km layers peaked in May (97.3 and 76.4 μg/m3), indicating that lower-layer intensity and vertical extent peaked asynchronously. Across five analysis windows (E1–E5), WRF-Chem diagnosed vertical mixing as the largest positive contribution in E1 and E3 (+19.6 and +12.2 µg/m3), concurrent positive contributions in E2 led by vertical mixing (+41.3 µg/m3) and chemistry (+21.1 µg/m3), and chemistry as the largest positive contribution in E5 (+21.8 µg/m3). In E4, upper-quartile O3 coincided with predominantly negative contributions, particularly vertical advection (−24.0 µg/m3), showing that high concentrations and hourly O3 changes were asynchronous. XGBoost–SHAP identified 2-m temperature (T2) and NO2 as the leading nonlinear predictors: T2-related SHAP values became positive near 18.5 °C, whereas the NO2-related values shifted from positive at 10–20 μg/m3 to predominantly negative above 26 μg/m3. The framework integrates vertical observations, statistical attribution, and modeled tendencies to support event-scale O3 diagnosis.
Related
- A global internal tide modeling framework for improving satellite observations of fine-scale ocean circulation
- An Artificial Intelligence Integrated Geospatial Decision-Support Framework for Scenario-Based Climate-Adaptive Land-Use Optimization and Environmental Risk Reduction
- An integrated framework for agroclimatic, salinity, and groundwater assessment in the Jizzakh Region, Uzbekistan
- A Continental-Scale Framework for Harmonised Soil Monitoring in African Agricultural Lands: Design, Implementation, and Baseline Field Observations from the Soils4Africa Project
- Integrated machine learning and AHP-based framework for spatial delineation of rainwater harvesting potential
BibTeX
@article{shi2026integrated,
title = {{Integrated diagnostic framework for resolving distinct ozone formation mechanisms via observations, modeling, and machine learning}},
author = {Bowen Shi and Shunqiang Pei and Tianshu Zhang and Lin Liang and Pingping An and Xiaopeng Ding and Li Shen and Jing Fu and Bo You and Weiwei Chen and Lingjian Duanmu and Luyan He and Xue Yang},
journal = {PNAS Nexus},
year = {2026},
month = oct,
doi = {10.1093/pnasnexus/pgag337},
url = {https://academic.oup.com/pnasnexus/advance-article/doi/10.1093/pnasnexus/pgag337/8857158},
note = {CC BY-NC 4.0},
}
RIS
TY - JOUR
TI - Integrated diagnostic framework for resolving distinct ozone formation mechanisms via observations, modeling, and machine learning
AU - Bowen Shi
AU - Shunqiang Pei
AU - Tianshu Zhang
AU - Lin Liang
AU - Pingping An
AU - Xiaopeng Ding
AU - Li Shen
AU - Jing Fu
AU - Bo You
AU - Weiwei Chen
AU - Lingjian Duanmu
AU - Luyan He
AU - Xue Yang
PY - 2026
DA - 2026/10/01
JO - PNAS Nexus
DO - 10.1093/pnasnexus/pgag337
UR - https://academic.oup.com/pnasnexus/advance-article/doi/10.1093/pnasnexus/pgag337/8857158
AB - Ozone (O3) pollution in relatively high-latitude industrial cities shows spatiotemporal patterns associated with coupled meteorological, transport, and chemical processes, yet its dominant formation mechanisms remain unresolved. This study developed an interpretable diagnostic framework integrating process-resolved Weather Research and Forecasting model coupled with Chemistry (WRF-Chem) simulations, observations, and Extreme Gradient Boosting (XGBoost) interpreted using Shapley additive explanations (SHAP) for Changchun, Northeast China (September 2023–August 2024). Surface daily maximum 8-h average (MDA8) O3 exceedances occurred from April to July, peaking above 200 μg/m3. Lidar monthly means at 0.3–1.0 km peaked from April to June (108.9–111.4 μg/m3), while the 1.0–2.0 and 2.0–3.0 km layers peaked in May (97.3 and 76.4 μg/m3), indicating that lower-layer intensity and vertical extent peaked asynchronously. Across five analysis windows (E1–E5), WRF-Chem diagnosed vertical mixing as the largest positive contribution in E1 and E3 (+19.6 and +12.2 µg/m3), concurrent positive contributions in E2 led by vertical mixing (+41.3 µg/m3) and chemistry (+21.1 µg/m3), and chemistry as the largest positive contribution in E5 (+21.8 µg/m3). In E4, upper-quartile O3 coincided with predominantly negative contributions, particularly vertical advection (−24.0 µg/m3), showing that high concentrations and hourly O3 changes were asynchronous. XGBoost–SHAP identified 2-m temperature (T2) and NO2 as the leading nonlinear predictors: T2-related SHAP values became positive near 18.5 °C, whereas the NO2-related values shifted from positive at 10–20 μg/m3 to predominantly negative above 26 μg/m3. The framework integrates vertical observations, statistical attribution, and modeled tendencies to support event-scale O3 diagnosis.
SN - 2752-6542
ER -