Han Jiakuan, Yang Yi, Yang Xiaoyue, Wang Dongchao, Wang Xiaolong, Sun Pengqi
School of Marine Technology and Geomatics, Jiangsu Ocean University, Lianyungang, 222005, China.
School of Marine Technology and Geomatics, Jiangsu Ocean University, Lianyungang, 222005, China.
Environ Res. 2023 May 1;224:115512. doi: 10.1016/j.envres.2023.115512. Epub 2023 Feb 18.
Air pollution has become a global public health risk factor as rapid urbanization advances. To observe the air pollution situation, air monitoring stations have been established in many cities, which record six air pollutants. Previous studies have identified cities exhibiting similar air pollution characteristics by combining principal component analysis (PCA) with cluster analysis (CA). However, spatial and temporal effects were neglected. In this paper, we focus on the combination of GTWPCA and STCA, which fully incorporates spatio-temporal effects. It is then applied to air pollution data from the top 10 urban agglomerations in China during 2016-2021. Key experimental findings include: 1. GTWPCA provides a more detailed interpretation of local variation than PCA. 2. Compared with CA, STCA highlights the coupling effect in the spatial and temporal dimensions. 3. The combination of GTWPCA and STCA captures similar air pollution characteristics from spatio-temporal perspectives, which has the potential to help environmental authorities take further action to control air pollution.
随着快速城市化的推进，空气污染已成为全球公共卫生风险因素。为了观测空气污染状况，许多城市都设立了空气监测站，这些监测站记录六种空气污染物。以往的研究通过将主成分分析（PCA）与聚类分析（CA）相结合，识别出了具有相似空气污染特征的城市。然而，空间和时间效应被忽略了。在本文中，我们重点关注广义时空加权主成分分析（GTWPCA）和时空聚类分析（STCA）的结合，该方法充分纳入了时空效应。然后将其应用于2016 - 2021年中国十大城市群的空气污染数据。主要实验结果包括：1. 与PCA相比，GTWPCA对局部变化提供了更详细的解释。2. 与CA相比，STCA突出了时空维度上的耦合效应。3. GTWPCA和STCA的结合从时空角度捕捉了相似的空气污染特征，这有可能帮助环境当局采取进一步行动来控制空气污染。
