Correlation Mechanism between Street Space Quality and Walking Behavior

What is it about?

It is of great significance to explore the correlation mechanism between urban street space quality and residents’walking behavior for rational and effective allocation of street facilities resources and promotion of healthy and green travel. Taking Qiguitang block in Hefei as an example, the streetscape image is crawled through Python, and the elements of street spatial quality are quantified by a machine learning algorithm, spatial syntax, and ArcGIS. Get travel data through behavior observation, and then build a multiple linear regression model for the correlation study of spatial quality and behavior characteristics to summarize the interaction degree and mode of various influencing factors. The research shows that there is a specific mathematical relationship between walking behavior and street space elements, among which functional formats, walking width, and interface openness have a more significant impact on walking behavior. Accordingly, the optimization strategy of street space in the old city area is proposed to provide a reference for the formulation of Hefei street design guidelines.

Featured Image

Photo by Dominic Kurniawan Suryaputra on Unsplash

Photo by Dominic Kurniawan Suryaputra on Unsplash

Why is it important?

Significance & Contributions Evidence-Based Urban Design Through machine learning, spatial syntax, and geographic information systems (ArcGIS), the authors analyze street images and layout data to quantify elements of street space—such as sidewalk width and interface openness . This data-driven method adds scientific rigor to urban planning decisions. Behavioral Modeling for Better Planning By observing pedestrian movement in Hefei’s Qiguitang district and applying multiple linear regression, the study identifies clear statistical links between street features and walking patterns . Notably, aspects like functionality, width, and openness strongly influence pedestrian behavior. Promoting Healthy & Green Mobility The research highlights how thoughtful street design can encourage walking—a healthier, more sustainable mode of transit. This aligns with global trends aiming to reduce car dependency and improve urban livability. Practical Guidelines for Real-World Application One major contribution is the proposal of optimized street-space strategies specifically for older urban zones. These recommendations can directly inform local street design and policy frameworks, such as Hefei’s future street design guidelines . Why It Matters Today Urban Growth & Sustainability: As cities expand, optimizing streets for pedestrians helps combat pollution, traffic congestion, and sedentary lifestyles. This study provides measurable criteria (e.g., minimum sidewalk widths or open interfaces) to guide urban revitalization globally. Interdisciplinary Methodology: The combination of AI image recognition, spatial analysis, and traditional behavioral observation offers a replicable model for similar research worldwide, advancing the field of urban analytics. Health & Social Equity Focus: By improving walkability, cities support public health and ensure equitable access to amenities—a particularly pressing concern in aging or underserved neighborhoods. In Summary This article is important because it: Quantifies how street design directly affects walking behavior Employs cutting-edge tools (ML, GIS, spatial syntax) to analyze urban form Delivers actionable recommendations for city planners Contributes to broader goals of health, sustainability, and social equity in urban development By bridging data analysis with urban policy, it offers an empirical foundation for designing healthier, more pedestrian-friendly streets.