Investigating the association between street environmental factors and pedestrian volume in a southern Chinese city: a machine learning based analysis

Abstract

The pedestrian volume, a critical indicator of urban vitality, has been broadly investigated in urban streets, particularly in China. However, how the street environment impacts the pedestrian volume has not received much attention in current Chinese cities. This study has adopted a machine learning model of LightGBM to test the association between 22 typical street environmental factors (spatial elements & spatial proximity) and the pedestrian volume (two models: the average value & the distance weighted value), and the SHAP approach to interpret and visualize the results achieved using the model. Guangzhou, a mega city in southern China, was chosen as the location studied. Key findings achieved are as follows: 1) Several environmental factors, particularly the density of commercial points of interest (POIs) and functional density, could significantly affect the average pedestrian volume. While most paired environmental factors may also produce important interaction effects, the strongest one was specifically observed between commercial and transportation POIs. 2) The distance-weighted pedestrian volume was significantly impacted by all 22 environmental factors, with commercial POIs having the highest impact. Furthermore, although most paired environmental factors had significant interaction effects, these effects were generally small. 3) Most paired environmental factors had significant interaction effects on both average and distance-weighted pedestrian volumes. However, the size of these effects was smaller relative to their main effects.

Keywords

Street environmental factors / Pedestrian volume / Machining learning analysis / LightGBM / SHAP / Southern China

References

[1] Anguelov D, Dulong C, Filip Det al. . Google street view: Capturing the world at street level. Computer. 2010, 43(6): 32-38.

[2] Azmi DI, Karim HA. Implications of walkability towards promoting sustainable urban neighbourhood. Procedia - Social and Behavioral SciencEs. 2012, 50: 204-213.

[3] Biljecki, F., & Ito, K. (2021). Street view imagery in urban analytics and GIS: A review. Landscape and Urban Planning,215, 104217. https://doi.org/10.1016/j.landurbplan.2021.104217

[4] Brownson, R.C., Hoehner, C.M., Day, K., et al. (2009). Measuring the built environment for physical activity: State of the science. American Journal of Preventive Medicine, 36, S99-S123. e112. https://doi.org/10.1016/j.amepre.2009.01.005

[5] Chakraborty S. TOPSIS and modified TOPSIS: A comparative analysis. Decision Analytics Journal. 2022, 2. 100021

[6] Chen J, Tian W, Xu Ket al. . Testing small-scale vitality measurement based on 5D model assessment with multi-source data: A resettlement community case in Suzhou. ISPRS International Journal of Geo-Information. 2022, 11(12. 626

[7] Chen L, Lu Y, Ye Yet al. . Examining the association between the built environment and pedestrian volume using street view images. Cities. 2022, 127. 103734

[8] Chen L, Zhao L, Xiao Yet al. . Investigating the spatiotemporal pattern between the built environment and urban vibrancy using big data in Shenzhen, China. Computers, Environment and Urban Systems. 2022, 95. Article 101827

[9] Chen, L. C., Zhu, Y., Papandreou, G., et al. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European conference on computer vision (ECCV) (pp. 801–818).

[10] Chen M, Cai Y, Guo Set al. . Evaluating implied urban nature vitality in San Francisco: An interdisciplinary approach combining census data, street view images, and social media analysis. Urban Forestry & Urban Greening. 2024, 95. Article 128289

[11] Chen S, Biljecki F. Automatic assessment of public open spaces using street view imagery. Cities. 2023, 137. Article 104329

[12] Chen T, Guestrin C. (2016) Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining 785–94. https://doi.org/10.1145/2939672.2939785

[13] Cordts, M., Omran, M., Ramos, S., et al. (2016). The cityscapes dataset for semantic urban scene understanding. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3213–3223).

[14] Danish M, Labib SM, Ricker Bet al. . A citizen science toolkit to collect human perceptions of urban environments using open street view images. Computers, Environment and Urban Systems. 2025, 116. Article 102207

[15] DeMers M. Fundamentals of geographic information systems. 20094th edJohn Wiley & Sons, inc.

[16] Doan QC, Ma J, Chen Set al. . Nonlinear and threshold effects of the built environment, road vehicles and air pollution on urban vitality. Landscape and Urban Planning. 2025, 253. Article 105204

[17] Dogan O, Lee S. Jane Jacobs's urban vitality focusing on three-facet criteria and its confluence with urban physical complexity. Cities. 2024, 155. Article 105446

[18] Du W, Tong S, Zhang Met al. . Revealing the spatiotemporal dynamics and nonlinear interaction-driven mechanisms of wetland ecosystem health in Northeast China using interpretable machine learning. Ecological Indicators. 2025, 178. 113878

[19] Dubey, A., Naik, N., Parikh, D., et al. (2016). Deep learning the city: Quantifying urban perception at a global scale. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14 (pp. 196–212). Springer International Publishing.

[20] Emmons, D. (1965). The pedestrian count. (Report no. 199). American Society of Planning Officials. https://www.planning.org/pas/reports/report199.htm (final access: 07 November 2025)

[21] Ergen, M. (2020). Using the buffer zone method to measure the accessibility of the green areas in Tokat, Turkey. In Landscape Architecture-Processes and Practices Towards Sustainable Development. IntechOpen. https://doi.org/10.5772/intechopen.92744

[22] Frank LD, Engelke PO. The built environment and human activity patterns: Exploring the impacts of urban form on public health. Journal of Planning Literature. 2001, 162): 202-218.

[23] Friedman, H. J. (2001). Greedy function approximation: A gradient boosting machine. Annals of statistics, 1189-232. https://www.jstor.org/stable/2699986

[24] Gao F, Deng X, Liao Set al. . Portraying business district vibrancy with mobile phone data and optimal parameters-based geographical detector model. Sustainable Cities and Society. 2023, 96. Article 104635

[25] Gebel K, Bauman AE, Petticrew M. The physical environment and physical activity: A critical appraisal of review articles. American Journal of Preventive Medicine. 2007, 32: 361-369. e363.

[26] Gehl J. Life between buildings. 1986Van Nostrand Reinhold

[27] Gelman A, Hill J, Vehtari A. Regression and other stories. 2021Cambridge University Press

[28] Guangzhou Municipal People's Government (GMPG). (2024). Guangzhou territorial spatial master plan (2021–2035). Guangzhou, China.

[29] Guangzhou Municipal Planning and Natural Resources Bureau (GMPNRB). (2024). Guangzhou comprehensive transportation system plan (2023–2035). Guangzhou, China.

[30] Guangzhou Statistics Bureau (GSB). (2023). Guangzhou statistical yearbook 2023. Guangzhou, China.

[31] Guimarães P, Figueiredo O, Woodward D. Accounting for neighbouring effects in measures of spatial concentration. Journal of Regional Science. 2011, 51: 678-693.

[32] Han Y, Qin C, Xiao L, Ye, Y., et al. (2024). The nonlinear relationships between built environment features and urban street vitality: A data-driven exploration. Environment and Planning b: Urban Analytics and City Science,51(1), 195–215. https://doi.org/10.1177/23998083231172985.

[33] Helbich M, Emmichoven MJ, Dijst MJet al. . Natural and built environmental exposures on children's active school travel: A Dutch global positioning system-based cross-sectional study. Health & Place. 2016, 39: 101-109.

[34] Heris MP, Foks NL, Bagstad KJet al. . A rasterized building footprint dataset for the United States. Scientific Data. 2020, 7(1): 207.

[35] Hillier, B., Burdett, R., Peponis, J., et al. (1986). Creating life: or, does architecture determine anything? Architecture & Comportement/Architecture & Behaviour, 3(3), 233–250. https://discovery.ucl.ac.uk/id/eprint/101

[36] Hou, C., Li, Y., & Zhang, F. (2024). Sensing urban physical environment with GeoAI and street-level imagery. In Handbook of geospatial approaches to sustainable cities (pp. 3–30). CRC Press.

[37] Huang J, Hu X, Wang J, Lu A. How diversity and accessibility affect street vitality in historic districts?. Land. 2023, 12. Article 219

[38] Huang J, Wang Y, Wu Ket al. . Livability-oriented urban built environment: What kind of built environment can increase the housing prices?. Journal of Urban Management. 2024, 13: 357-371.

[39] Humpel N, Owen N, Leslie E. Environmental factors associated with adults’ participation in physical activity: A review. American Journal of Preventive Medicine. 2002, 22: 188-199.

[40] Hwang CL, Lai YJ, Liu TY. A new approach for multiple objective decision making. Computers & Operations Research. 1993, 208889-899.

[41] Hwang CL, Yoon K. Multiple attribute decision making: Methods and applications. 1981Springer-Verlag.

[42] Jacobs J. Death and Life of Great American Cities. 1961Random House

[43] Jiang, D. (2007). The theory of city form vitality. Southeast University Press, Nanjing, China.

[44] Johnsen PV, Riemer-Sørensen S, DeWan ATet al. . A new method for exploring gene–gene and gene–environment interactions in GWAS with tree ensemble methods and SHAP values. BMC Bioinformatics. 2021, 22(1. 230

[45] Kaklauskas, A., Gudauskas, R. (2016). Intelligent decision-support systems and the Internet of Things for the smart built environment. In Pacheco-Torgal, F., Rasmussen, E., Granqvist, C-G., Ivanov, V., Kaklauskas, A., Makonin, S. (Eds.), Start-up creation: The smart eco-efficient built environment (pp. 413–449). Woodhead Publishing. https://doi.org/10.1016/C2014-0-04828-9

[46] Ke G, Meng Q, Finley T, et al. (2017) Lightgbm: A highly efficient gradient boosting decision tree. Proceedings of the 31st International Conference on Neural Information Processing Systems, 30, 3149–57. https://dl.acm.org/doi/10.5555/3294996.3295074

[47] Kim, D., Ko, J., & Lee, Y. I. (2013). Estimating pedestrian traffic volume: a preliminary analysis. In Proceedings of the Eastern Asia society for transportation studies, 9, 154. Department of Transportation Taipei.

[48] Koo BW, Guhathakurta S, Botchwey N. How are neighborhood and street-level walkability factors associated with walking behaviors? A big data approach using street view images. Environment and Behavior. 2022, 54: 211-241.

[49] Kostas M, Wouter P. Built environment, urban vitality and social cohesion: Do vibrant neighborhoods foster strong communities?. Landscape and Urban Planning. 2020, 204. Article 103951

[50] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015, 5217553): 436-444.

[51] Li J, Kong N, Lin Set al. . Spatial nonlinear effects of street vitality constrained by construction intensity and functional diversity—A case study from the streets of Shenzhen. ISPRS International Journal of Geo-Information. 2024, 13(7. 238

[52] Li J, Lin S, Kong Net al. . Nonlinear and synergistic effects of built environment indicators on street vitality: A case study of humid and hot urban cities. Sustainability. 2024, 165. 1731

[53] Li T, Zheng X, Wu Jet al. . Spatial relationship between green view index and normalized differential vegetation index within the Sixth Ring Road of Beijing. Urban Forestry & Urban Greening. 2021, 62. Article 127153

[54] Li Y, Guo J, Zhao Let al. . Research on the spatial-temporal pattern and spatial spillover effect of tourism based on mobile signaling and POIs data: A case study of Xiamen city, southeast China. Asia Pacific Journal of Tourism Research. 2022, 2710): 1052-1070.

[55] Li Y, Yabuki N, Fukuda T. Exploring the association between street built environment and street vitality using deep learning methods. Sustainable Cities and Society. 2022, 79. Article 103656

[56] Ling Z, Zheng X, Chen Yet al. . The nonlinear relationship and synergistic effects between built environment and urban vitality at the neighbourhood scale: A case study of Guangzhou’s central urban area. Remote Sensing. 2024, 16(15. 2826

[57] Liu D, Lu Y, Yang L. Exploring non-linear effects of environmental factors on the volume of pedestrians of different ages using street view images and computer vision technology. Travel Behaviour and Society. 2024, 36. 100814

[58] Liu, F. T., Ting, K. M. & Zhou, Z. H. (2008). Isolation forest. The Eighth IEEE International Conference on Data Mining, Pisa, Italy, pp. 413–422, https://doi.org/10.1109/ICDM.2008.17

[59] Liu M, Jiang Y, He J. Quantitative evaluation on street vitality: A case study of Zhoujiadu community in Shanghai. Sustainability. 2021, 136. Article 3027

[60] Lundberg, S. M., Erion, G. G., & Lee, S. I. (2018). Consistent individualized feature attribution for tree ensembles. arXiv preprint arXiv:1802.03888. https://doi.org/10.48550/arXiv.1802.03888

[61] Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems. 2017, 30: 3149-3157

[62] Lynch, K. (1984). Reconsidering the image of the city. MIT Press. Cambridge, Massachusetts, USA.

[63] Lyu G, Angkawisittpan N, Fu Xet al. . Investigating the relationship between built environment and urban vitality using big data. Scientific Reports. 2025, 151. 579

[64] Massey, D. B. (2005). For space. London: SAGE Publications.

[65] Mazúr E, Urbánek J. Space in geography. GeoJournal. 1983, 7: 139-143.

[66] McCormack GR, Shiell A. In search of causality: A systematic review of the relationship between the built environment and physical activity among adults. International Journal of Behavioral Nutrition and Physical Activity. 2011, 8: 1-11.

[67] Meng Y, Xing H. Exploring the relationship between landscape characteristics and urban vibrancy: A case study using morphology and review data. Cities. 2019, 95. Article 102389

[68] Montgomery J. Making a city: Urbanity, vitality and urban design. Journal of Urban Design. 1998, 31): 93-116.

[69] Nathvani R, Cavanaugh A, Suel Eet al. . Measurement of urban vitality with time-lapsed street-view images and object-detection for scalable assessment of pedestrian-sidewalk dynamics. ISPRS Journal of Photogrammetry and Remote Sensing. 2025, 221: 251-264.

[70] Ogawa Y, Oki T, Zhao Cet al. . Evaluating the subjective perceptions of streetscapes using street-view images. Landscape and Urban Planning. 2024, 247. Article 105073

[71] Pažout A., Brughmans T., Soto P., (2022). Road and transport networks. Encyclopedia of Archaeology (Second Edition) (Second Edition), 2A, 124–134. https://doi.org/10.1016/B978-0-323-90799-6.00044-6

[72] Psyllidis A, Gao S, Hu Yet al. . Points of interest (POI): A commentary on the state of the art, challenges, and prospects for the future. Computational Urban Science. 2022, 2. 20

[73] Rajput D, Wang WJ, Chen CC. Evaluation of a decided sample size in machine learning applications. BMC Bioinformatics. 2023, 24. 48

[74] Ryus, P., Musunuru, A., Bonneson, J., et al. (2022). Guide to pedestrian analysis (No. NCHRP Project 17–87).

[75] Schiller, J., & Voisard, A. (Eds.). (2004). Location-based services. Elsevier.

[76] Shannon CE. A mathematical theory of communication. Bell System Technical Journal. 1948, 27(3): 379-423.

[77] Shapley, L. S. (1953). A value for n-person games. In H. W. Kuhn & A. W. Tucker (Eds.), Contributions to the Theory of Games (Vol. 2, pp. 307–317). Princeton University Press.

[78] Spence, R. (2001). Information visualization (Vol. 1). New York: Addison-Wesley.

[79] State Council of the People's Republic of China (SCPRC). (2019). Outline development plan for the Guangdong-Hong Kong-Macao Greater Bay Area. Beijing, China.

[80] Tang S, Ta N. How the built environment affects the spatiotemporal pattern of urban vitality: A comparison among different urban functional areas. Computational Urban Science. 2022, 2(1. Article 39

[81] Turner A. From axial to road-centre lines: A new representation for space syntax and a new model of route choice for transport network analysis. Environment and Planning b, Planning and Design. 2007, 343): 539-555.

[82] Wang R, Liu Y, Lu Yet al. . Perceptions of built environment and health outcomes for older Chinese in Beijing: A big data approach with street view images and deep learning technique. Computers, Environment and Urban Systems. 2019, 78. 101386

[83] Wang R, Lu Y, Zhang Jet al. . The relationship between visual enclosure for neighbourhood street walkability and elders’ mental health in China: Using street view images. Journal of Transport & Health. 2019, 13: 90-102.

[84] Wang, W., He, H., & Ma, C. (2023). An improved Deeplabv3+ model for semantic segmentation of urban environments targeting autonomous driving. International Journal of Computers, Communications & Control, 18(6). https://doi.org/10.15837/ijccc.2023.6.5879

[85] Wang Z, Ma D, Sun Det al. . Identification and analysis of urban functional area in Hangzhou based on OSM and POI data. PLoS ONE. 2021, 16(5. e0251988

[86] Welch WJ. Construction of permutation tests. Journal of the American Statistical Association. 1990, 85411): 693-698.

[87] Wu C, Ye X, Ren Fet al. . Check-in behaviour and spatio-temporal vibrancy: An exploratory analysis in Shenzhen, China. Cities. 2018, 77: 104-116.

[88] Wu W, Dang Y, Zhao Ket al. . Spatial nonlinear effects of urban vitality under the constraints of development intensity and functional diversity. Alexandria Engineering Journal. 2023, 77: 645-656.

[89] Xia C, Yeh AGO, Zhang A. Analyzing spatial relationships between urban land use intensity and urban vitality at street block level: A case study of five Chinese megacities. Landscape and Urban Planning. 2020, 193. Article 103669

[90] Xiao L, Liu J. Exploring non-linear built environment effects on urban vibrancy under COVID-19: The case of Hong Kong. Applied Geography. 2023, 155. Article 102960

[91] Yan X. Research on the action mechanism of circular economy development and green finance based on entropy method and big data. Journal of Enterprise Information Management. 2021, 35(4/5): 98.

[92] Yin L, Wang Z. Measuring visual enclosure for street walkability: Using machine learning algorithms and Google Street View imagery. Applied Geography. 2016, 76: 147-153.

[93] Yu, Y., Li, D., & Liu, X. (2018). How block density and typology affect urban vitality: An exploratory analysis in Shenzhen, China. Urban Geography,39(4), 631–652. https://doi.org/10.1080/02723638.2017.1381536

[94] Yue Y, Zhuang Y, Yeh AGet al. . Measurements of POI-based mixed use and their relationships with neighbourhood vibrancy. International Journal of Geographical Information Science. 2017, 314658-675.

[95] Zeng Q, Wu H, Wei Yet al. . Association between built environment factors and collective walking behavior in peri-urban area: Evidence from Chengdu. Applied Geography. 2024, 167. Article 103274

[96] Zhang F, Salazar-Miranda A, Duarte Fet al. . Urban visual intelligence: Studying cities with artificial intelligence and street-level imagery. Annals of the American Association of Geographers. 2024, 114(5): 876-897.

[97] Zhang, H. (2023). Understanding human perceptions of street view images using MIT place pulse 2.0 dataset (Doctoral dissertation). Waseda University, Japan.

[98] Zhang Q, Zheng Z, Wu Zet al. . Using multi-source geospatial information to reduce the saturation problem of DMSP/OLS nighttime light data. Remote Sensing. 2022, 14(14. Article 3264

[99] Zhang W, Zeng H. Spatial differentiation characteristics and influencing factors of the green view index in urban areas based on street view images: A case study of Futian District, Shenzhen, China. Urban Forestry & Urban Greening. 2024, 93. Article 128219

[100] Zhang Y, Li S, Dong Ret al. . Quantifying physical and psychological perceptions of urban scenes using deep learning. Land Use Policy. 2021, 111. 105762

[101] Zhang, Y., Wang, X., Ye, Y., et al. (2025). Nonlinear relationships and interaction effects of urban built environment on urban vitality based on explainable machine learning. City and Environment Interactions. 100244. https://doi.org/10.1016/j.cacint.2025.100244

[102] Zhang Y, Zhong W, Wang Det al. . Understanding the spatiotemporal patterns of nighttime urban vibrancy in central Shanghai inferred from mobile phone data. Regional Sustainability. 2021, 24): 297-307.

[103] Zikirya B, He X, Li Met al. . Urban food takeaway vitality: A new technique to assess urban vitality. International Journal of Environmental Research and Public Health. 2021, 187. Article 3578

[104] Zhao Xukai, Lu Yuxing, Lin Guangsi. An integrated deep learning approach for assessing the visual qualities of built environments utilizing street view images. Engineering Applications of Artificial Intelligence. 2024, 130107805.

Funding

Innovative Research Group Project of the National Natural Science Foundation of China(52268011)

RIGHTS & PERMISSIONS

The Author(s)