Machine learning unveils the impact of anthropogenic emission changes on urban PM2.5 and O3: A case study in Wuhu.

PM2.5 and O3 are two major issues hindering air quality improvement in China. However, the response of these two pollutants to anthropogenic emission variations in the real atmosphere was not yet well understood. Here, we selected the short-term epidemic lockdown in Wuhu in 2022 as a case study and evaluated the impacts of meteorology and anthropogenic emission on PM2.5 and O3 using field observations combined with machine learning algorithms. The results showed that NO2 observed during the lockdown was 32.2 ± 8.1 µg/m3, 10.1 % lower than before the lockdown, and that NO2 continued to decrease by 19.2 % after the lockdown. Notably, both PM2.5 and O3 concentrations were higher during the lockdown than before and after the lockdown. Random forest model revealed that meteorological conditions during the lockdown increased PM2.5 and O3 by 8.7 % and 24.2 %, respectively, but decreased NO2 by 6.4 %. Atmospheric pressure and relative humidity were the main meteorological variables influencing PM2.5 and O3 variations, respectively. Scenario simulation analysis uncovered that anthropogenic emission reduction caused by the lockdown reduced NO2 by 19.7 %, but increased PM2.5 and O3 by 6.3 % and 26.8 %, respectively. This was mainly due to the weakening titration effect of nitrogen oxides and enhanced atmospheric oxidation capacity, further increasing O3 and secondary PM2.5 production. Our results revealed that NO2 in Wuhu decreased significantly due to short-term epidemic lockdown, but PM2.5 and O3 pollution were not effectively reduced. To continuously improve future urban air quality, joint reductions in emissions from multiple anthropogenic sources and multiple pollutants are required.