Integrating variable importance and spatial heterogeneity to reveal the environmental effects on outdoor jogging

Abstract

Outdoor jogging is increasingly recognized as a crucial component of urban active transport strategies aimed at improving public health. Despite growing research on the influence of both natural and built environmental factors on outdoor jogging, less is known about the relative importance of these factors. Moreover, the spatial heterogeneity effects of environmental factors remain unclear. Failing to consider these varying effects regarding impact intensity and spatial scale results in inefficient planning policies aimed at promoting active transport. This study addresses these gaps by analyzing crowdsourced jogging trajectory data in Shenzhen using a computational framework that combines Random Forest Variable Importance (RF-VI) and Multi-Scale Geographically Weighted Regression (MGWR). The analysis identifies hierarchical environmental effects and the varying impacts of twelve key determinants across different spatial scales. Results reveal that natural environmental factors are most contributing to outdoor jogging, while density-related built environment factors contribute the least. Additionally, environmental effects vary in scale, direction, and intensity, with seven variables exerting global impacts and five showing localized effects. Notably, the central and suburban areas of Shenzhen display considerable spatial heterogeneity in environmental influences. The findings inform the importance of integrating green infrastructure, mitigating over-dense urban development, and enhancing pedestrian-accessible road networks to promote outdoor jogging. These insights advocate for context-sensitive urban planning that balances natural and built environments to to foster healthier mobility.

References

[1] Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019). Optuna: A Next-generation Hyperparameter Optimization Framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2623–2631. https://doi.org/10.1145/3292500.3330701

[2] Anagnostopoulos, A. (2021). The Rise of Run-Commuting as a Form of Transportation: Research on the Characteristics and Spatial Needs of These Trips. In E. G. Nathanail, G. Adamos, & I. Karakikes (Eds.), Advances in Mobility-as-a-Service Systems (pp. 684–693). Springer International Publishing. https://doi.org/10.1007/978-3-030-61075-3_67

[3] BarrenoM, SisaI, Yépez GarcíaMC, ShenH, VillarM, KovalskysI, FisbergM, GomezG, RigottiA, CortésLY, ParejaRG, Herrera-CuencaM, GuajardoV. Association between built environment and physical activity in Latin American countries: A multicentre cross-sectional study. British Medical Journal Open, 2021, 11(11): e046271

[4] BreimanL. Random Forests. Machine Learning, 2001, 45(1): 5-32

[5] BrownG, SchebellaMF, WeberD. Using participatory GIS to measure physical activity and urban park benefits. Landscape and Urban Planning, 2014, 121: 34-44

[6] CampbellMJ, DennisonPE, ButlerBW, PageWG. Using crowdsourced fitness tracker data to model the relationship between slope and travel rates. Applied Geography, 2019, 106: 93-107

[7] Chen, G., & Wei, Z. (2024). Exploring the impacts of built environment on bike-sharing trips on weekends: The case of Guangzhou. International Journal of Sustainable Transportation, 0(0), 1–13. https://doi.org/10.1080/15568318.2023.2299018

[8] ChenL, ZhangZ, LongY. Association between leisure-time physical activity and the built environment in China: Empirical evidence from an accelerometer and GPS-based fitness app. PLoS ONE, 2021, 16(12): e0260570

[9] Chen, Y., Liu, T., Xie, X., & Marušić, B. G. (2016). What Attracts People to Visit Community Open Spaces? A Case Study of the Overseas Chinese Town Community in Shenzhen, China. International Journal of Environmental Research and Public Health, 13(7), Article 7. https://doi.org/10.3390/ijerph13070644

[10] ChengL, De VosJ, ZhaoP, YangM, WitloxF. Examining non-linear built environment effects on elderly’s walking: A random forest approach. Transportation Research Part d: Transport and Environment, 2020, 88: 102552

[11] CookS. Geographies of run-commuting in the UK. Journal of Transport Geography, 2021, 92: 103038

[12] DingC, CaoX, Jason, NaessP. Applying gradient boosting decision trees to examine non-linear effects of the built environment on driving distance in Oslo. Transportation Research Part a: Policy and Practice, 2018, 110: 107-117

[13] DongL, JiangH, LiW, QiuB, WangH, QiuW. Assessing impacts of objective features and subjective perceptions of street environment on running amount: A case study of Boston. Landscape and Urban Planning, 2023, 235: 104756

[14] EwingR, CerveroR. Travel and the Built Environment: A Synthesis. Transportation Research Record, 2001, 1780(1): 87-114

[15] EwingR, CerveroR. Travel and the Built Environment: A Meta-Analysis. Journal of the American Planning Association, 2010, 76(3): 265-294

[16] FangT, ZhouL, CaiZ, TanZ, ChenC, ZhengJ, FangC. Investigating spatial and temporal characteristics and elements influencing running among residents of Nanchang city in green open areas. Computational Urban Science, 2024, 4(1): 30

[17] FotheringhamAS, YangW, KangW. Multiscale Geographically Weighted Regression (MGWR). Annals of the American Association of Geographers, 2017, 107(6): 1247-1265

[18] GaoF, ChenX, LiaoS, ChenW, FengL, WuJ, ZhouQ, ZhengY, LiG, LiS. Crafting a jogging-friendly city: Harnessing big data to evaluate the runnability of urban streets. Journal of Transport Geography, 2024, 121: 104015

[19] GuoC, JiangY, QiaoR, ZhaoJ, WengJ, ChenY. The nonlinear relationship between the active travel behavior of older adults and built environments: A comparison between an inner-city area and a suburban area. Sustainable Cities and Society, 2023, 99: 104961

[20] Guo, L., Yang, S., Peng, Y., & Yuan, M. (2023). Examining the Nonlinear Effects of Residential and Workplace-built Environments on Active Travel in Short-Distance: A Random Forest Approach. International Journal of Environmental Research and Public Health, 20(3), Article 3. https://doi.org/10.3390/ijerph20031969

[21] HanK-T. The effect of environmental factors and physical activity on emotions and attention while walking and jogging. Journal of Leisure Research, 2021, 52(5): 619-641

[22] Harden, S. R., Schuurman, N., Keller, P., & Lear, S. A. (2022). Neighborhood Characteristics Associated with Running in Metro Vancouver: A Preliminary Analysis. International Journal of Environmental Research and Public Health, 19(21), Article 21. https://doi.org/10.3390/ijerph192114328

[23] HeH, LinX, YangY, LuY. Association of street greenery and physical activity in older adults: A novel study using pedestrian-centered photographs. Urban Forestry & Urban Greening, 2020, 55: 126789

[24] HohlA, LotfataA. Modeling spatiotemporal associations of obesity prevalence with biking, housing cost and green spaces in Chicago, IL, USA, 2015–2017. Journal of Transport & Health, 2022, 26: 101412

[25] HuangD, JiangB, YuanL. Analyzing the effects of nature exposure on perceived satisfaction with running routes: An activity path-based measure approach. Urban Forestry & Urban Greening, 2022, 68: 127480

[26] HuangD, TianM, YuanL. Sustainable design of running friendly streets: Environmental exposures predict runnability by Volunteered Geographic Information and multilevel model approaches. Sustainable Cities and Society, 2023, 89: 104336

[27] JiS, WangX, LyuT, LiuX, WangY, HeinenE, SunZ. Understanding cycling distance according to the prediction of the XGBoost and the interpretation of SHAP: A non-linear and interaction effect analysis. Journal of Transport Geography, 2022, 103: 103414

[28] JiangH, DongL, QiuB. How Are Macro-Scale and Micro-Scale Built Environments Associated with Running Activity? The Application of Strava Data and Deep Learning in Inner London. ISPRS International Journal of Geo-Information, 2022, 11(10): 504

[29] Johnston, R., & Sidaway, J. D. (2015). Human geography as spatial science. In Geography and Geographers (7th ed.). Routledge.

[30] Krasner, L. (2013). Environmental Design and Human Behavior: A Psychology of the Individual in Society. Elsevier.

[31] KubotaA, AbeT, HadgraftN, OwenN, SugiyamaT. Prevalence of physically active and sedentary travel in a regional area of Japan: Geographic and demographic variations. Journal of Transport & Health, 2022, 24: 101318

[32] LiZ. GeoShapley: A Game Theory Approach to Measuring Spatial Effects in Machine Learning Models. Annals of the American Association of Geographers, 2024, 114(7): 1365-1385

[33] LiuK, SiuKWM, GongXY, GaoY, LuD. Where do networks really work? The effects of the Shenzhen greenway network on supporting physical activities. Landscape and Urban Planning, 2016, 152: 49-58

[34] LiuW, WangB, YangY, MouN, ZhengY, ZhangL, YangT. Cluster analysis of microscopic spatio-temporal patterns of tourists’ movement behaviors in mountainous scenic areas using open GPS-trajectory data. Tourism Management, 2022, 93: 104614

[35] LiuY, HuJ, YangW, LuoC. Effects of urban park environment on recreational jogging activity based on trajectory data: A case of Chongqing. China. Urban Forestry & Urban Greening, 2022, 67: 127443

[36] LiuY, LiY, YangW, HuJ. Exploring nonlinear effects of built environment on jogging behavior using random forest. Applied Geography, 2023, 156: 102990

[37] LiuY, MinS, ShiZ, HeM. Exploring students’ choice of active travel to school in different spatial environments: A case study in a mountain city. Journal of Transport Geography, 2024, 115: 103795

[38] LopesIJC, BiondiD, CorteAPD, ReisARN, OliveiraTGS. A methodological framework to create an urban greenway network promoting avian connectivity: A case study of Curitiba City. Urban Forestry & Urban Greening, 2023, 87: 128050

[39] LyuT, WangY, JiS, FengT, WuZ. A multiscale spatial analysis of taxi ridership. Journal of Transport Geography, 2023, 113: 103718

[40] MizdrakA, TatahL, MuellerN, ShawC, WoodcockJ. Assessing the health impacts of changes in active transport: An updated systematic review. Journal of Transport & Health, 2023, 33: 101702

[41] Oshan, T. M., Li, Z., Kang, W., Wolf, L. J., & Fotheringham, A. S. (2019). mgwr: A Python Implementation of Multiscale Geographically Weighted Regression for Investigating Process Spatial Heterogeneity and Scale. ISPRS International Journal of Geo-Information, 8(6), Article 6. https://doi.org/10.3390/ijgi8060269

[42] Raford, N., Chiaradia, A., & Gil, J. (2007). Space Syntax: The Role of Urban Form in Cyclist Route Choice in Central London. https://escholarship.org/uc/item/8qz8m4fz

[43] RugelEJ, HendersonSB, CarpianoRM, BrauerM. Beyond the Normalized Difference Vegetation Index (NDVI): Developing a Natural Space Index for population-level health research. Environmental Research, 2017, 159: 474-483

[44] Schuurman, N., Rosenkrantz, L., & Lear, S. A. (2021). Environmental Preferences and Concerns of Recreational Road Runners. International Journal of Environmental Research and Public Health, 18(12), Article 12. https://doi.org/10.3390/ijerph18126268

[45] ShiH, YaoL, LiuQ, WangY, WeiZ, ZhaoM, MaD. From trajectories to network: Delineating the spatial pattern of recreational walking in Guangzhou. Applied Geography, 2024, 170: 103344

[46] SongY, MerlinL, RodriguezD. Comparing measures of urban land use mix. Computers, Environment and Urban Systems, 2013, 42: 1-13

[47] TaoT, WuX, CaoJ, FanY, DasK, RamaswamiA. Exploring the Nonlinear Relationship between the Built Environment and Active Travel in the Twin Cities. Journal of Planning Education and Research, 2023, 43(3): 637-652

[48] Wang, H., Huang, Z., Yin, G., Bao, Y., Zhou, X., & Gao, Y. (2022). GWRBoost:A geographically weighted gradient boosting method for explainable quantification of spatially-varying relationships (arXiv:2212.05814). arXiv. https://doi.org/10.48550/arXiv.2212.05814

[49] WangM, QiuM, ChenM, ZhangY, ZhangS, WangL. How does urban green space feature influence physical activity diversity in high-density built environment? An on-site observational study. Urban Forestry & Urban Greening, 2021, 62: 127129

[50] WuJ, LiC. Illustrating the nonlinear effects of urban form factors on transportation carbon emissions based on gradient boosting decision trees. Science of the Total Environment, 2024, 929: 172547

[51] XiaoZ, ZhangC, LiY, ChenY. Community park visits determined by the interactions between built environment attributes: An explainable machine learning method. Applied Geography, 2024, 172: 103423

[52] YangL, YangH, YuB, LuY, CuiJ, LinD. Exploring non-linear and synergistic effects of green spaces on active travel using crowdsourced data and interpretable machine learning. Travel Behaviour and Society, 2024, 34: 100673

[53] YangW, HuJ, LiuY, GuoW. Examining the influence of neighborhood and street-level built environment on fitness jogging in Chengdu, China: A massive GPS trajectory data analysis. Journal of Transport Geography, 2023, 108: 103575

[54] YangW, LiY, LiuY, FanP, YueW. Environmental factors for outdoor jogging in Beijing: Insights from using explainable spatial machine learning and massive trajectory data. Landscape and Urban Planning, 2024, 243: 104969

[55] Zhang, S., Liu, N., Ma, B., & Yan, S. (2023). The effects of street environment features on road running: An analysis using crowdsourced fitness tracker data and machine learning. Environment and Planning B: Urban Analytics and City Science, 23998083231185589. https://doi.org/10.1177/23998083231185589

[56] Zhang, Y., & Hu, X. (2024). The nonlinear impact of cycling environment on bicycle distance: A perspective combining objective and perceptual dimensions. Journal of Transport and Land Use, 17(1), Article 1. https://doi.org/10.5198/jtlu.2024.2434

[57] ZhangZ, YinD, VirrantausK, YeX, WangS. Modeling human activity dynamics: An object-class oriented space–time composite model based on social media and urban infrastructure data. Computational Urban Science, 2021, 1(1): 7

[58] ZhouC, AnY, ZhaoJ, XueY, FuL. How do mini-parks serve in groups? A visit analysis of mini-park groups in the neighbourhoods of Nanjing. Cities, 2022, 129: 103804

Funding

Guangdong Provincial University Young Innovative Talents Project(2023WQNCX140)

RIGHTS & PERMISSIONS

The Author(s)