Incorporating networks in semantic understanding of streetscapes: Contextualising active mobility decisions

Abstract

Planning for active mobility satisfies many fundamental tenets of good urban design and planning. However, planning for active mobility is a complex endeavour due to numerous local, place-based factors that influence active mobility decisions. Recent advancements in urban data research have demonstrated the effectiveness of deep learning methods in evaluating active mobility potential for urban environments. At present, the incorporation of semantic information from deep learning models and street view imagery into spatio-temporal contexts remains a challenge. In particular, knowledge extraction from deep learning models remains an open question for urban planning and decision-making. Towards this issue, we propose a functional deep learning and network science workflow that employs open data from OpenStreetMap and Mapillary to assess factors affecting active mobility decisions and route planning. We demonstrate the generalisability of our analytical workflow through two case studies focusing on urban greenery in Nerima city (Japan) and urban visual complexity in Pasir Ris town (Singapore). Our results reveal clear patterns of heterogeneity in urban streetscapes and identify unevenness in street infrastructure provision based on destination types. Using this information, we propose specific areas for design intervention to improve active mobility planning. Our workflow is applicable for a diverse range of use cases making it relevant to a wide range of stakeholders, not limited to, urban researchers, policy makers and urban planners.

Understanding factors influencing people with disabilities’ participation in sports and cultural activities

“…At the district (WETDZ) level, we assessed the number of accessible cultural and sports facilities within 1,000 m and 2,000 m based on road network. This approach helps to illustrate the possible combinations of origin–destination traffic between residential areas and service facilities [ 39 ] as well as to map the overall coverage of facilities by the whole network, thereby creating a schematic diagram of the cultural and sports facilities’ accessibility in the WETDZ in a spatially explicit way.…”

Advancing Urban Life: A Systematic Review of Emerging Technologies and Artificial Intelligence in Urban Design and Planning

“…Advancements in urban data research have demonstrated the effectiveness of deep learning methods in evaluating active mobility potential for urban environments. Yap et al [25] integrated street view imagery and urban networks to evaluate active mobility, using deep learning to assess traffic environment factors impacting subjective decisions. Unlike traditional GPS resources, Chen and Yang [26] combined social media signals with pedestrian simulation technologies in historic neighborhoods, addressing conflicts between tourists and locals and enhancing urban planning.…”

“…Enhances active mobility planning using deep learning DeepLabV3 segmentation trained on a WideResNet-38 model analyzing street imagery. [25] Uses big data, pedestrian simulation, and AnyLogic to identify facility gaps and traffic issues.…”

A Global Feature-Rich Network Dataset of Cities and Dashboard for Comprehensive Urban Analyses

“…Network population estimates can also help evaluate the accessibility of public facilities, such as schools, hospitals, or parks, empowering planners to pinpoint underserved areas and prioritise infrastructure investments [39][40][41] . Street view indicators along network edges are crucial for modeling pedestrian-friendly urban environments and suggesting improvements to promote walking, cycling, and other active transportation modes [42][43][44][45] In emergency planning, identifying critical nodes and links can inform strategies to enhance city resilience against various shocks and stresses, including climate change, natural disasters, or economic fluctuations. Lastly, building morphology information along networks plays a vital role in energy-based modeling and carbon forecasting for urban areas, providing insights into the implications of urban growth for social, economic, and environmental outcomes 19,46 .…”