AI finds what makes cities more walkable

Researchers used artificial intelligence (AI) to study streets in Hong Kong and found out what makes them more walkable.

Architecture firm Perkins Eastman used a novel form of data analysis, studying a combination of qualitative pedestrian preference surveys, visual streetscape imagery from Google Street View, artificial intelligence, and computer vision to identify the type and mix of urban design elements that most influence people’s walking habits. The walkability study found that people prefer to walk in places with a higher proportion of several basic streetscape elements.

AI Finds What Makes Cities More Walkable

A generous supply of benches, shade trees, sidewalks, and crosswalks all contribute to walkability. When those elements are provided in combination with one another people are likely to walk even more.

The analysis led to development of urban design guidelines that suggest ways of making spaces more walkable. The guidelines include combining street furniture with greenery and open space, pairing crosswalks with improved street lighting, and increasing the social interactivity of a space by having more benches in areas with an above average proportion of street-facing windows, balconies, and patios.