The effects of street environment features on road running: An analysis using crowdsourced fitness tracker data and machine learning

Abstract

Urban streets provide environment for road running. The study proposes a non-parametric approach that uses machine learning models to predict road running intensity. The models were developed using route check-in data from Keep, a mobile exercise application, and street geographic information data in Beijing’s core district. The results show that blue space and trail continuity are the most important factors in improving road running intensity. There is an optimum design value for the sky openness and the street enclosure, which need to be balanced with shade while meeting the light of the road. And it is also important to provide appropriate visual permeability. Furthermore, unlike daily activities, it was found that higher function mixture and function density did not have significant positive effects on the road running intensity. This study provides empirical evidence on road running and highlights the key factors that planners, landscape architects, and city managers should consider when design running-friendly urban streets.

Toward Resilient Urban Design: Pedestrians as an Important Element of City Design

“…Even people who habitually use a motorized vehicle walk more or less long distances. Non-motorized transport modes are ecological, economical, and reasonably quick for distances shorter than 3.5 km [23]. As previously indicated, walkability in an urban area is a fundamental factor of a sustainable city.…”

“…Regional or provincial level [50,51,66] City level [39,54,60] District or neighborhood level [49,58,59,63,65,67,68] Street level [1,9,23,[53][54][55][56]62,64,[69][70][71] The methods that they applied to observe walkability varied, and they included interviews and surveys, GIS-based analyses, the auditing of physical reality, and the use of images and instruments [72]. They were performed in different research settings-mostly urban and rural planning, transport, and public health.…”

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

“…Spatiotemporal data encapsulates various information sets crucial for understanding spatial and temporal aspects of urban dynamics. Tracking data involving crowdsourced trajectory and check-in information [52] facilitated calculating road running intensity, offering insights into urban road movement patterns and utilization. Road network data analysis [31,47] aided in assessing street safety, diagnosing strategies for urban street space, and contributing significantly to urban planning and safety assessments.…”

“…[51] Uses machine learning to predict urban street running intensity. [52] Analyses Dhaka's travel patterns using household diaries, artificial neural networks, and regression. [53] Evaluating human perceptions of streetscapes using integrating PSPNET, attention mechanisms, and transfer learning.…”