Unveiling the air pollution tapestry in China: A comprehensive assessment of spatiotemporal variations through geographically and temporally weighted regression

Abstract

Study of air pollution informs environmentally-conscious policies and urban planning by government and businesses, leading to more scientific decision-making. This paper comprehensively analyzes the spatiotemporal correlation of six air pollutants (PM2.5, PM10, SO2, NO2, CO, and O3) at the national level of China from 2015 to 2021. The temporal changes in environmental air pollutants are examined through statistical data analysis. Secondly, the annual and quarterly spatial distribution characteristics of air pollutants are analyzed by utilizing global and local spatial autocorrelation analysis and visualizing pollutant concentration data. To quantify the spatiotemporal correlation information obtained from the data, we proposed a novel framework based on the Geographically and Temporally Weighted Regression (GTWR) model to provide a local approach for detecting the spatiotemporal correlation between urban air pollutants on a large scale. The framework's experimental results showed that the significant correlation between urban air pollutants in time and space ranged from 0.45 to 0.9, which is better than traditional correlation algorithm, and the degree of local spatiotemporal correlations can be explained by spatiotemporal coefficients. We find noticeable differences in the correlations between different pollutants and geographical boundaries in the spatial dimension. Furthermore, in terms of spatiotemporal location, PM2.5, PM10, NO2, SO2, and CO exhibit positive correlations with each other, while O3 shows both positive and negative correlations with other pollutants. This study offers an important reference for air quality monitoring and prediction, contributing to the improvement of accuracy and timeliness of air quality warnings.