International Journal of Urban Sciences

AI and Big Data for Urban Mobility and built environment: New Approaches to Understanding Mobility and the Built Environment

Urban mobility and transportation systems are undergoing a profound transformation driven by the rapid proliferation of novel data sources, sensing technologies, and advanced analytical paradigms. The increasing availability of large-scale, high-resolution datasets such as mobile phone records, GPS trajectories, smart card transactions, ride-hailing data, street-level imagery, and social media has fundamentally expanded researchers’ capacity to capture and interpret complex spatiotemporal mobility patterns. These developments offer unprecedented opportunities to address long-standing challenges in urban transportation, including congestion, accessibility inequities, and system resilience.

Concurrently, there is growing recognition of the critical role of the built environment in shaping travel behavior and mobility experiences. Urban form, land-use configurations, streetscape characteristics, and perceived environmental qualities such as walkability, comfort, and safety substantially influence individual mobility decisions and overall accessibility. Recent advances in data acquisition techniques (e.g., street view imagery) and computational methods (e.g., deep learning-based feature extraction) have enabled more precise and scalable measurement of these environmental attributes, facilitating deeper insights into their interactions with mobility outcomes.

This special issue aims to advance the frontier of urban mobility research by bringing together cutting-edge studies that leverage innovative data sources and state-of-the-art analytical approaches. We invite contributions that examine mobility systems, the built environment, and, critically, their dynamic interrelationships. Submissions employing advanced methodologies, including complex statistical modeling, machine learning, deep learning, artificial intelligence, and large language models (LLMs) are particularly encouraged. Relevant topics include, but are not limited to, mobility pattern analysis, travel behavior modeling, environmental perception measurement, and the evaluation of transportation policies and planning interventions.

Submissions may address, but are not limited to, the following topics:

• Applications of machine learning, deep learning, and artificial intelligence in transportation and built environment research
• Use of large language models (LLMs) and AI-assisted analytical approaches in urban mobility studies
• Measurement and analysis of built environment characteristics, including walkability, comfort, safety, and streetscape qualities
• Interactions between the built environment and travel behavior with advanced methods
• Smart mobility, shared mobility, and emerging transportation systems
• Integration of multimodal mobility data and built environment indicators for planning and policy analysis

This special issue aims to advance data-driven research on urban mobility, transportation systems, the built environment, and their interactions by highlighting both methodological innovations and empirical applications.