Evidence for regional heterogeneous atmospheric particulate matter distribution in China: implications for air pollution control

摘要: China has suffered from severe nationwide air quality degradation for decades. PM2.5, the atmospheric particulate matter with an aerodynamic equivalent diameter of less than 2.5 μm, is most concerning pollutant heath. Pollution control policies are commonly applied nationwide, but pollution may vary one area to another, thus suggesting need different, adapted policies. However, there little knowledge on distribution in China. Therefore, here we used recurrent neural network and random forest models analyze wintertime regional PM2.5 patterns four polluted cities China, which Beijing, Shanghai, Guangzhou Chengdu, December 2014 February 2019. We find that different megacities have completely patterns, remained unchanged during past 6 years. CO plays a predominant role shaping importance varies region region. should be carried out better regulation. Furthermore, demonstrate not strongly linked time series, inferring concentrations at given date previous concentrations. This finding suggests chemical reaction equilibrium get reversed rate reactions faster normally think.