Search

Quantitative Analysis of Jogging Behavior Spatial Differentiation Mechanism in Washington, D.C. Streets Based on the XGBoost-SHAP Method and Urban Construction Characteristics

Author(s)

Hanlin Xiong

Affiliation(s)

Academy of Geography and Information Engineering, China University of Geosciences, Wuhan, China

Abstract

With the acceleration of urbanization, outdoor sports, especially jogging, have gradually gained popularity among urban residents. Urban greening, particularly street trees, as an important means to improve the quality of life, has a significant impact on residents' sports behavior. However, there is a lack of research on the relationship between street tree characteristics and the willingness to jog. Based on the characteristics of street trees in Washington, D.C., this study quantitatively analyzes 11 street - related characteristic variables such as tree pit length, crown width, crown length, and the number of street trees. The XGBoost regression model is used to predict the willingness to jog, and the SHAP method is combined for result interpretability analysis. The study aims to reveal the potential relationship between these street characteristics and residents' willingness to jog. The goal of this study is to provide scientific basis for urban planners to optimize the design of street trees and urban greening, thereby promoting residents' healthy behaviors and participation in jogging activities. By filling the research gap in the relationship between street trees and the willingness to jog, this paper provides theoretical support and practical guidance for the construction of healthy cities and the improvement of residents' quality of life.

Keywords

Component; Urban Construction Environment; Street Trees; Xgboost-SHAP Interpretation; Jogging Willingness

References

[1] Huagui Guo, Shuyu Zhang, Yufei Liu, et al. Building running-friendly cities: effects of streetscapes on running using 9.73 million fitness tracker data in Shanghai, China[J]. BMC Public Health, 2024, 24(1):2251-2251. [2] Zhang Ying, Chen Liang, Liu Xin. Grey Relational Analysis of Urban Human Settlement Environment Factors Affecting Pedestrian Suitability in Coastal Cities. Journal of Environment and Health, 2010. 27(12): p. 1106-1108. [3] Feng Ziji, Ma Danya. Research on the Strategy of Creating Urban Jogging Environments Based on Mobile Phone Fitness Data: A Case Study of Tianjin. In 2022/2023 China Urban Planning Conference. 2023. Wuhan, Hubei, China. [4] Yujia Zhong, Meng Guo, Menghan Zhang, et al. Identifying Street Environmental Factors That Attract Public Attention from the Jogger’s Perspective: A Multiscale Spatial Exploration[J]. Buildings, 2024, 14(7):1935-1935. [5] Liu Yong, Hu Jie, Yang Wei, et al. Effects of urban park environment on recreational jogging activity based on trajectory data: A case of Chongqing, China[J]. Urban Forestry & Urban Greening, 2022, 67 [6] Yang Wei, Li Yingpeng, Liu Yong, et al. Environmental factors for outdoor jogging in Beijing: Insights from using explainable spatial machine learning and massive trajectory data[J]. Landscape and Urban Planning, 2024, 243:104969. [7] Wei Yang, Jun Fei, Yingpeng Li, et al. Unraveling nonlinear and interaction effects of multilevel built environment features on outdoor jogging with explainable machine learning[J]. Cities, 2024, 147:104813. [8] Yang Wei, Hu Jie, Liu Yong. The Correlation and Interaction between Built Environment and Outdoor Jogging Supported by Crowdsourced Geographic Information. Landscape Architecture, 2024. 31(04): p. 44-52. [9] Nadine Schuurman, Leah Rosenkrantz, Scott A Lear. Environmental Preferences and Concerns of Recreational Road Runners[J]. International Journal of Environmental Research and Public Health, 2021, 18(12): p.6268. [10] Mingke Xie, Zhangxian Feng, Wang Long, et al. What are the environmental preferences of runners? Evidence from Guangzhou[J]. Applied Geography, 2025, 174: p.103469. [11] Jiang, H., D. Lin, Q. Bing, How Are Macro-Scale & Micro-Scale Built Environments Associated with Running Activity? The Application of Strava Data & Deep Learning in Inner London. ISPRS Int. J. Geo Inf., 2022. 11: p. 504. [12] Yang Linchuan, Yu Bingjie, Liang Pengpeng, et al. Crowdsourced Data for Physical Activity-Built Environment Research: Applying Strava Data in Chengdu, China
[J]. Frontiers in Public Health, 2022, 10:883177-883177. [13] Huang Dengkai, Tian Meng, Yuan Lei. Sustainable design of running friendly streets: Environmental exposures predict runnability by Volunteered Geographic Information and multilevel model approaches[J]. Sustainable Cities and Society, 2023, 89. [14] Cai, C., et al., Unraveling nonlinear effects of environment features on green view index using multiple data sources & explainable machine learning. Scientific Reports, 2024. 14. [15] Liu Yong, Li Yingpeng, Yang Wei, et al. Exploring nonlinear effects of built environment on jogging behavior using random forest[J]. Applied Geography, 2023, 156.