Quantifying Changes in NOx Emissions in China during the COVID-19 Pandemic Using a Neural Network Approach

Abstract:

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 NO_x, which provides a unique opportunity to study the response of the chemistry of the atmospheric to large reductions in anthropogenic emissions. We use a deep learning (DL) model to quantify the change in surface emissions of NO_x in China that are associated with the observed changes in atmospheric NO₂ during the lockdown period. Compared to conventional data assimilation systems, deep neural networks are free of the potential errors associated with parameterized subgrid-scale processes. Furthermore, they are not susceptible to the chemical errors typically found in atmospheric chemical transport models. The neural-network-based approach also offers a more computationally efficient means of inverse modeling of NO_x emissions at high spatial resolutions. Our DL model is trained using meteorological predictors and reanalysis data of surface NO₂ and ozone from 2005 to 2017. Data in 2018 is used to validate the performance of the model. The evaluation is conducted using in-situ measurements of NO₂ in 2019 and 2020. We show that the pre-trained model is able to reproduce the observed variability in surface NO₂ and ozone and capture the reduction in NO_x emissions in China during the period of the COVID-19 pandemic.