The COVID-19 pandemic led to the lockdown of over one-third of Chinese cities in early 2020. Observations have shown significant reductions of atmospheric abundances of NO2 over China during this period. This change in atmospheric NO2 implies a dramatic change in emission of NOx, which provides a unique opportunity to study the response of the chemistry of the atmospheric to large reductions in anthropogenic emissions. However, there is inconsistency between satellite derived NO2 and in situ NO2, and reanalysis might not be able to capture trends in urban regions. Moreover, high-resolution data assimilation is computationally expensive. Integrating surface observations with satellite observations into data assimilation schemes is also challenging sometimes. We use a deep learning (DL) model to quantify the change in surface emissions of NOx in China that are associated with the observed changes in atmospheric NO2 during the lockdown period.
Compared to conventional data assimilation systems, the DL model is free of the potential errors associated with defective parameterization of subgrid-scale processes. Furthermore, it is not susceptible to the chemical errors typically found in atmospheric chemical transport models (CTMs). We show that the DL model can integrate satellite-based information from a chemical reanalysis with in situ observations of NO2 to provide estimates of surface emissions of NOx.