Comprehensive walkability assessment of urban pedestrian environments using big data and deep learning techniques

Area of Science:

• Urban Planning
• Environmental Psychology
• Public Health

Background:

• Current walkability assessments often overlook subjective experiences and diverse walking needs.
• Urban spatial elements significantly influence individual walking experiences and preferences.
• A comprehensive approach is needed to integrate objective and subjective walkability dimensions.

Purpose of the Study:

• To develop and validate a comprehensive framework for assessing street walkability.
• To integrate macro-scale, micro-scale, and street walking preference indicators.
• To provide a nuanced understanding of walkability in high-density urban environments.

Main Methods:

• Constructed a novel evaluation framework integrating Macro-Scale Index, Micro-Scale Index, and Street Walking Preferences Index.
• Employed a normalization weighting method to synthesize indicators into a comprehensive walkability index.
• Applied the framework to assess street environments within Beijing's Fifth Ring Road.

Main Results:

• The developed framework accurately reflects the spatial distribution of street walkability.
• The three distinct indicators reveal both overlapping and unique insights into walkability.
• The Macro-Scale Index proved highly accurate in high-density, ring-road cities, aligning with the comprehensive index.

Conclusions:

• The integrated framework offers a more holistic assessment of street walkability.
• Considering both objective and subjective dimensions is crucial for effective urban planning.
• Findings support the development of more inclusive, sustainable, and walkable urban spaces.