Urban design and pollution using AI: Implications for urban development in China

The primary aim of this study is to explore the role of AI in urban design and its potential to reduce pollution in Chinese cities. The study investigates how AI-driven urban planning tools can be applied to create more sustainable, efficient, and functional urban environments. PM_2.5 and PM₁₀ show high concentrations with peaks between 2014 and 2017, indicating simple pollution actions. Post-2017, there is a noticeable decline in pollution levels, possibly due to improved regulations or the global impact of the COVID-19 pandemic. Specific years, like 2016, show extreme spikes, possibly due to industrial activities or natural events. The overall trend suggests improved air quality and moderate to strong positive correlations exist between PM_2.5 and PM₁₀, NO₂, SO₂, and CO, indicating shared bases or co-occurrence. However, there is no significant correlation between PM_2.5 and O₃, suggesting different bases and behaviors. Bi-directional causality is observed between PM_2.5 and PM₁₀, PM_2.5 and O₃, PM_2.5 and NO₂, PM_2.5 and SO₂, and PM_2.5 and CO. This mutual cause suggests interrelated impressive processes and shared bases. The results of the causality analysis suggest the existence of complex interactions, where high levels of pollution can predict changes in others. AI in urban design play vital role for identifying the most effective strategies for reducing pollution and helping to build more sustainable and functional urban environments in China.