Urban Flow: Decoding Foot Traffic in NYC
Why It Matters
By turning sparse counts into citywide, comparable pedestrian-exposure metrics and forecasts, the model enables more equitable, data-driven allocation of infrastructure, safety interventions and regulatory decisions that have been historically biased toward motorized modes. Confidence:85.
Summary
At the MIT Mobility Forum, researchers led by Andres Sevtsuk presented a Nature Cities study, developed with New York DOT data, that builds a pedestrian travel-demand model for NYC using urban network analysis and an open-source Python toolkit. The model extrapolates limited foot-traffic counts to estimate peak-hour pedestrian volumes on every sidewalk, crosswalk and footpath, and can vary by day and season. Panelists highlighted applications including normalizing crash, pollution and heat exposure metrics by pedestrian exposure, prioritizing sidewalk and public-space investments, and forecasting impacts of land-use or street-design changes. The work fills a major data gap—walking is NYC’s dominant mode yet is poorly measured—and creates a framework for scalable, policy-relevant pedestrian metrics.
Comments
Want to join the conversation?
Loading comments...