The impact of Chinese new year on air quality in north China based on machine learning

Abstract

The reduced economic and social activities during the Chinese New Year offer a unique opportunity to assess declines in anthropogenic emissions. However, limited research quantifies changes in PM_2.5, NO₂, and O₃ concentrations during this period while accounting for meteorological conditions. This study utilized machine learning and the Time Warping-based K-Means method to evaluate the effectiveness of firework bans, the impact of emission reductions on pollutants during the Chinese New Year holiday, and the influence of meteorological conditions on pollutant concentrations during this period. Our findings reveal a significant reduction in emissions, with PM_2.5 and NO₂ concentrations decreasing by up to 24.76% and 33.39%, respectively, while O₃ concentrations increased by up to 45%. Regions without firework bans saw peak PM_2.5 levels on New Year's Eve. The ban has been effective, though signs of relaxation appeared in 2023. It is worth noting that pollution during the 2018 Chinese New Year holiday was more severe than before the holiday because the meteorological conditions before the holiday were favorable for pollutant dispersion, while unfavorable meteorological conditions during the holiday masked the emission reductions that occurred due to the holiday period. These results emphasize the significant role of meteorological conditions and the need for stricter emission controls beyond traffic restrictions or factory shutdowns to mitigate haze pollution during adverse weather.