Toward an Operational Machine-Learning-Based Model for Deriving the Real-Time Gapless Diurnal Cycle of Ozone Pollution in China with CLDAS Data

Abstract

An operational real-time surface ozone (O₃) retrieval (RT-SOR) model was developed that can provide a gapless diurnal cycle of O₃ retrievals with a spatial resolution of 6.25 km by integrating Chinese Land Data Assimilation System (CLDAS) data and multisource auxiliary information. The model robustly captures the hourly O₃ variability, with a sample-based (station-based) cross-validation R² of 0.88 (0.85) and RMSE of 14.3 μg/m³ (16.1 μg/m³). An additional hindcast-validation experiment demonstrated that the generalization ability of the model is robust (R² = 0.75; RMSE = 21.9 μg/m³). Compared with previous studies, the model performs comparably or even better at the daily scale and fills the gaps in terms of missing hourly O₃ data within the 24-hour cycle. More importantly, underpinned by the RT availability of CLDAS data, the hourly concentration of O₃ can be updated in RT, which is expected to advance our understanding of the diurnal cycle of O₃ pollution in China.