The escalation of ground-level ozone (O3) pollution presents a significant challenge to the sustainable growth of Chinese cities. This study utilizes advanced machine learning algorithms to investigate the intricate interplay between urban socioeconomic growth and O3 levels. Surpassing traditional environmental chemistry, it assesses the effectiveness of these algorithms in interpreting socioeconomic and environmental data, while elucidating urban development's environmental impacts from a novel socioeconomic perspective. Key findings indicate that factors such as urban infrastructure, industrial activities, and demographic dynamics significantly influence O3 pollution. The study highlights the particular sensitivity of urban public transportation and population density, each exerting a unique and substantial effect on O3 levels. Additionally, the research identifies nuanced interactions among these factors, indicating a complex web of influences on urban O3 pollution. These interactions suggest that the impact of individual socioeconomic elements on O3 pollution is interdependent, being either amplified or mitigated by other factors. The study emphasizes the crucial need to integrate socioeconomic variables into urban O3 pollution strategies, advocating for policies tailored to each city's distinct characteristics, informed by the detailed analysis provided by machine learning. This approach is essential for developing effective and nuanced urban pollution management strategies.
Keywords: Machine learning models, Pollution management; Socioeconomic factors; Urban ground-level O3 pollution.
© 2024. The Author(s), under exclusive licence to Springer Nature Switzerland AG.