ABSTRACT
Surface ozone (O3), a well-recognized air pollutant, exists in the atmosphere, which has a detrimental effect on public health and the ecological environment. It is reported that surface O3 has seen a significant increase in many cities from 2019 to 2021 (COVID-19 pandemic). In this study, we applied an innovative machine learning model (Deep Forest) coupled with satellites, the Troposphere Monitoring Instrument (TROPOMI) and the Ozone Monitoring Instrument (OMI), and meteorological datasets to estimate monthly surface O3 of 1 km spatial resolution across China during this pandemic period. Our model achieved an overall R2 of 0.974, 0.963, and root mean square error (RMSE) of 6.016 μg/m3, 7.214 μg/m3 on TROPOMI-based datasets and OMI-based datasets, respectively. Also, we found the higher ozone concentration regions were in Eastern China. Simultaneously, the surface O3 concentration was high in summer(average = 110.57 ± 15.01 μg/m3). And the ozone concentration in summer 2020 (average = 107.78 ± 13.90 μg/m3) declined unprecedently than in summer 2019 (average = 110.54 ± 16.58 μg/m3). Our results indicated that TROPOMI data could provide robust data support for surface ozone concentration estimation. Furthermore, this study could enhance our comprehension of the formation mechanisms of surface O3 in China and assist air environment management decision-making.