NO2 exposure disparities in active transportation: insights from the 15-minute city

The intersection of environmental justice and urban accessibility presents a critical challenge in sustainable city planning. While the “15-minute city” promotes accessible neighborhoods, its implications for air pollution exposure remain understudied. This study develops a novel methodology that integrates machine learning-based street-level nitrogen dioxide (NO2) predictions with graph network analysis to assess exposure disparities within New York City's 15-minute active mobility zones. Results show that disparities are more pronounced under cycling conditions, where broader spatial coverage increases exposure variability and amplifies inequality in disadvantaged areas. Block-level analysis further identifies spatially clustered inequality hot spots associated with freight infrastructure, network connectivity, and public services. By incorporating active mobility patterns, the framework addresses the neighbourhood effect averaging problem and uncovers disparities masked by traditional tract-level analyses. These findings highlight the importance of embedding mobility-informed environmental justice into 15-minute city planning for more equitable urban development.