The production and quality of human life have been impacted by the extreme heat wave events caused by global warming and urbanization. This study analyzed the prevention of air pollution and the strategies of emission reduction based on decision trees (DT), random forests (RF), and extreme random trees (ERT). Additionally, we quantitatively investigated the contribution rate of atmospheric particulate pollutants and greenhouse gases to urban heat wave occurrences by combining numerical models and big data mining technology. This study focuses on changes in the urban environment and climate. The main findings of this study are as follows. The average concentrations of PM2.5 in the northeast of Beijing-Tianjin-Hebei in 2020 were 7.4%, 0.9%, and 9.6% lower than those in the corresponding years of 2017, 2018, and 2019, respectively. The carbon emissions in the Beijing-Tianjin-Hebei region showed an increasing trend during the previous 4 years, which was consistent with the spatial distribution of PM2.5. In 2020, there were fewer urban heat waves, which was attributable to a reduction of 75.7% in emissions and an improvement of 24.3% in the prevention and management of air pollution. These results suggest that the government and environmental protection agencies need to pay attention to changes in the urban environment and climate to diminish the negative effects of heatwaves on the health and economic growth of the urban population.
Keywords: Climate change; Contribution rate; Machine learning; Urban heat wave events.
© 2023. The Author(s), under exclusive licence to Springer Nature B.V.