Identifying Driving Factors of Atmospheric N₂O₅ with Machine Learning

Dinitrogen pentoxide (N₂O₅) plays an essential role in tropospheric chemistry, serving as a nocturnal reservoir of reactive nitrogen and significantly promoting nitrate formations. However, identifying key environmental drivers of N₂O₅ formation remains challenging using traditional statistical methods, impeding effective emission control measures to mitigate NO-induced air pollution. Here, we adopted machine learning assisted by steady-state analysis to elucidate the driving factors of N₂O₅ before and during the 2022 Winter Olympics (WO) in Beijing. Higher N₂O₅ concentrations were observed during the WO period compared to the Pre-Winter-Olympics (Pre-WO) period. The machine learning model accurately reproduced ambient N₂O₅ concentrations and showed that ozone (O₃), nitrogen dioxide (NO₂), and relative humidity (RH) were the most important driving factors of N₂O₅. Compared to the Pre-WO period, the variation in trace gases (i.e., NO₂ and O₃) along with the reduced N₂O₅ uptake coefficient was the main reason for higher N₂O₅ levels during the WO period. By predicting N₂O₅ under various control scenarios of NO and calculating the nitrate formation potential from N₂O₅ uptake, we found that the progressive reduction of nitrogen oxides initially increases the nitrate formation potential before further decreasing it. The threshold of NO was approximately 13 ppbv, below which NO reduction effectively reduced the level of night-time nitrate formations. These results demonstrate the capacity of machine learning to provide insights into understanding atmospheric nitrogen chemistry and highlight the necessity of more stringent emission control of NO to mitigate haze pollution.