Estimation of NOx Emission in China by Use of Data Assimilation and Machine Learning Methods

Nitrogen oxides (NO_x, mainly comprising NO and NO₂) is the essential precursor of secondary air pollutants, such as ozone and particulate nitrate. To better understand NO_x emission levels and acquire reasonable simulation results for further analysis, a reasonable emission inventory is needed. In this study, a new method, combining the three-dimensional chemical transport model simulation, surface NO₂ observations, the three-dimensional variational assimilation method, and an ensemble back propagation neural network, was proposed and applied to correct NO_x emissions over China for the summers of 2015 and 2020. Compared with the simulation using prior NO_x emissions, the root-mean-square error and normalized mean bias decreased by approximately 40% and 60% in the NO₂ simulation using posterior NO_x emissions. Compared with the emissions for 2015, the NO_x emission generally reduced by an average of 5% in the simulation domain for 2020, especially in Henan and Anhui provinces, where the percentage reductions reached 24% and 19%, respectively. The proposed framework is sufficiently flexible to correct emissions in other periods and regions. It can provide policymakers and academic researchers with the latest emission information for better emission control and air pollution research.