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

Area of Science:

• Environmental Science
• Urban Planning
• Artificial Intelligence

Background:

• Air pollution in Chinese cities, particularly particulate matter (PM2.5 and PM10), showed high concentrations peaking between 2014-2017.
• A decline in pollution levels post-2017 suggests potential impacts of improved regulations or global events like the COVID-19 pandemic.
• Pollution levels exhibit complex interrelationships, with moderate to strong positive correlations between PM2.5 and other pollutants (PM10, NO2, SO2, CO), but not O3.

Purpose of the Study:

• To explore the role of Artificial Intelligence (AI) in urban design for pollution reduction in Chinese cities.
• To investigate the application of AI-driven urban planning tools for creating sustainable, efficient, and functional urban environments.
• To analyze the correlations and causal relationships between various air pollutants and understand their impact on urban air quality.

Main Methods:

• Analysis of historical air quality data, including PM2.5, PM10, NO2, SO2, CO, and O3 concentrations.
• Statistical analysis to determine correlations between different pollutants.
• Causality analysis to understand the predictive relationships between pollutant levels.

Main Results:

• Pollution levels, especially PM2.5 and PM10, peaked between 2014-2017, with a subsequent decline.
• Significant positive correlations were found between PM2.5 and PM10, NO2, SO2, and CO, indicating shared sources or co-occurrence.
• Bi-directional causality was observed among several pollutant pairs, highlighting complex interactions in pollution dynamics.

Conclusions:

• AI in urban design is crucial for identifying effective pollution reduction strategies.
• AI-driven planning can contribute to building more sustainable and functional urban environments in China.
• Understanding pollutant interrelationships is key for targeted environmental interventions.