Satellite Remote Sensing of Daily Surface Ozone in a Mountainous Area

High levels of surface ozone (O-3) pollution threaten human and environmental health. Chongqing, a mountainous municipality located in southwest China, is exposed to serious O-3 pollution and requires more studies. Due to its complex terrain and always foggy weather, it is difficult to maintain many in situ sites in Chongqing, and chemical transportation model (CTM) simulations are also challenged. The recently launched (in 2017) Sentinel-5p satellite provides O-3 columns with advanced spatiotemporal resolution. Without the dependence on CTMs, we linked O-3 columns and surface monitoring data from 2019 to 2021 in virtue of a deep forest machine learning model. Compared with another widely used machine learning model and previous studies, our results showed great advantages in estimating surface O-3 on a daily scale. Validated against in situ sites in Chongqing, averaged R-2 of cross validations reached 0.9, while the root-mean-squared error (RMSE) and mean bias error (MBE) were 13.57 and 0.37 mu g/m(3), respectively. We found out that the model performance is associated with the relative height difference between training sites and the test site. The model performed stably when the height difference was lower than 200 m, but obvious performance degradation was seen when the height difference is exceeding 400 m.

Automated summary

High levels of surface ozone pollution pose a threat to human and environmental health in Chongqing, a mountainous area in southwest China. However, due to its complex terrain and foggy weather, studying ozone pollution in Chongqing presents challenges. In this study, we used advanced satellite data and a machine learning model to estimate surface ozone concentrations. Our results showed great advantages in estimating daily surface ozone levels, and we also identified the influence of the height difference between training and test sites on model performance.