Smart card data (SCD) from Automatic Fare Collection (AFC) systems provide fine-grained insights into urban mobility rhythms. Yet most existing studies focus on static ridership, with limited attention to the relationship between station-level travel rhythms and the surrounding built environment. This study develops a spatiotemporal and data-driven framework to classify urban rail transit (URT) stations and examine their land-use determinants. Using two weeks of AFC data from 128 stations in Nanjing, China, a two-stage approach is implemented. First, a Gaussian Mixture Model (GMM) is applied to cluster stations based on weekday ridership profiles, yielding six distinct categories: residential oriented, employment oriented, hub comprehensive, spatial mismatched, predominantly residential mixed use, and predominantly employment mixed use. These categories reveal a clear transition from mixed and hub functions in the city center to residential-dominated stations in suburban areas. Second, a Random Parameter Logit (RPL) model is employed to assess the influence of socio-demographic, land-use, and amenity variables, capturing heterogeneity more effectively than the conventional Multinomial Logit (MNL) model. Results highlight the decisive roles of population density, housing prices, and employment land in shaping employment- and hub-oriented stations, while community-oriented facilities, such as healthcare and daily services, exert stronger effects on residential-oriented stations. These findings enrich theoretical understanding of station heterogeneity and provide empirical evidence for transit-oriented development (TOD), land-use coordination, and multimodal integration. The proposed framework is transferable to other rapidly urbanizing cities, offering practical guidance for building efficient and sustainable URT systems.
| [1] |
Shen Q, Chen P, Pan H. Factors affecting car ownership and mode choice in rail transit-supported suburbs of a large Chinese city. Transp Res Part A Policy Pract. 2016, 94: 31-44.
|
| [2] |
Yong J, Zheng LJ, Mao XW, Tang X, Gao A, Liu WN. Mining metro commuting mobility patterns using massive smart card data. Physica A. 2021, 584: 126351.
|
| [3] |
Zhang YP, Manley E, Martens K, Batty M. A metro smart card data-based analysis of group travel behaviour in Shanghai, China. J Transp Geogr. 2024, 114103764.
|
| [4] |
Bertolini L. Nodes and places: complexities of railway station redevelopment. Eur Plan Stud. 1996, 4(3): 331-345.
|
| [5] |
Zhao X, Li YX, Sun JX, Li L, Ren G. The influence of built environment on ultra-peak for urban rail transit station passenger flows based on lasso-multiscale geographically weighted regression. Travel Behav Soc. 2025, 41: 101063.
|
| [6] |
Zhong C, Manley E, Arisona SM, Batty M, Schmitt G. Measuring variability of mobility patterns from multiday smart-card data. J Comput Sci. 2015, 9125-130.
|
| [7] |
Reades J, Zhong C, Manley ED, Milton R, Batty M. Finding pearls in London’s oysters. Built Environ. 2016, 423365-381.
|
| [8] |
Liu XB, Huang MH, Qu HZ, Chien S. Minimizing metro transfer waiting time with the AFCS data using simulated annealing with parallel computing. J Adv Transport. 2018, 2018(1): 4218625
|
| [9] |
Dong SH, Wang YD, Dou MX, Wang C, Gong JY. Uncovering the similarity and heterogeneity of metro stations: from passenger mobility, land use, and streetscapes semantics. Appl Geogr. 2025, 174: 103450.
|
| [10] |
Chen C, Chen J, Barry J. Diurnal pattern of transit ridership: a case study of the New York city subway system. J Transp Geogr. 2009, 173176-186.
|
| [11] |
Chun KC, Bahk J, Kim H, Jeong HC, Kim G. Classification of the metropolitan subway stations and spheres of influence of main commercial areas in Seoul. Physica A. 2023, 609: 128387.
|
| [12] |
Cervero R, Kockelman K. Travel demand and the 3Ds: density, diversity, and design. Transp Res D Transp Environ. 1997, 23199-219.
|
| [13] |
Ewing R, Cervero R. Travel and the built environment: a synthesis. Transp Res Rec. 2001, 1780187-114.
|
| [14] |
Gan ZX, Yang M, Feng T, Timmermans H. Understanding urban mobility patterns from a spatiotemporal perspective: daily ridership profiles of metro stations. Transportation. 2020, 47: 315-336.
|
| [15] |
Yang J, Xing SM, Rao HY, Wang YX. Impact of station land use on the occupational and residential functions of metro stations. Sci Technol Eng. 2024, 24(23): 10050-10056(In Chinese)
|
| [16] |
Korf JL, Demetsky MJ. Analysis of rapid transit access mode choice. Transp Res Rec. 1981, 817: 29-35
|
| [17] |
Fu BF, Wu JR, Chen XH. Method of classification of suburban rail transit station sites. J China Railway Soc. 2008, 30(6): 19-23(In Chinese)
|
| [18] |
Yu LJ, Li Y, Chen KM. Using spectral clustering for urban rail station classification. J Traffic Inf Saf. 2014, 32(1): 122-125+129(In Chinese)
|
| [19] |
Yin Q, Meng B, Zhang LY. Classification of subway stations in Beijing based on passenger flow characteristics. Prog Geogr. 2016, 35(1): 126-134(In Chinese)
|
| [20] |
Yue ZH, Chen F, Wang ZJet al. . Classifications of metro stations by clustering smart card data using the gaussian mixture model. Urban Rapid Rail Transit. 2017, 30(2): 48-51+107(In Chinese)
|
| [21] |
Kim T, Sohn DW, Choo S. An analysis of the relationship between pedestrian traffic volumes and built environment around metro station in Seoul. KSCE J Civ Eng. 2017, 21(4): 1443-1452.
|
| [22] |
Tan ZZ, li SY, Li Xet al. . Clustering of metro stations in Guangzhou based on passenger flow. Trop Geogr. 2017, 37(1): 102-111(In Chinese)
|
| [23] |
Ma ZL, Yang X, Tan XW. Classification of urban rail transit stations based on passenger flow time series. J Chang’an Univ (Nat Sci Ed). 2021, 41(6): 113-126(In Chinese)
|
| [24] |
Jiang YS, Yu GS, Hu L, Li Y. Refined classification of urban rail transit stations based on clustered station's passenger traffic flow features. J Transp Syst Eng Inf Technol. 2022, 22(4): 106-112(In Chinese)
|
| [25] |
Deng J, Xu M (2015) Characteristics of subway station ridership with surrounding land use: A case study in Beijing. In: 2015 International Conference on Transportation Information and Safety (ICTIS), 330-336
|
| [26] |
Chen JJ. Changes characteristics of weekend passenger flow of Guangzhou metro based on cluster analysis. Traffic Transp. 2019, 32(S1): 141-147(In Chinese)
|
| [27] |
Lu DL, He M, Shuai CY (2019) Metro stations classification based on clustering analysis—A case study of Beijing metro. In: The 19th COTA International Conference of Transportation Professional (CICTP), 1707-1717
|
| [28] |
Zhao X, Wu YP, Ren G, Ji K, Qian WW. Clustering analysis of ridership patterns at subway stations: a case in Nanjing, China. J Urban Plann Dev. 2019, 145(2. 04019005
|
| [29] |
Yang J, Wu K, Zhang HL, Dai SX, Wang YL. Classification of subway stations based on land use and passenger flow characteristics. J Transp Syst Eng Inf Technol. 2021, 215): 228-234(In Chinese).
|
| [30] |
Li ZH, Tian XL, Li ZWet al. . Risk analysis of metro station passenger flow based on passenger flow patterns. J Tsinghua Univ (Sci Technol). 2019, 59(10): 854-860(In Chinese)
|
| [31] |
Yan R, Ding SQ. Study on the relationship between working and housing balance and built environment in the area around rail transit and BRT: a case study of Hefei City. J Hunan Univ Nat Sci. 2023, 32(4): 47-53(In Chinese)
|
| [32] |
Estupiñán N, Rodriguez DA. The relationship between urban form and station boardings for Bogota’s BRT. Transp Res Part A Policy Pract. 2008, 42(2): 296-306.
|
| [33] |
Choi J, Lee YJ, Kim T, Sohn K. An analysis of Metro ridership at the station-to-station level in Seoul. Transportation. 2012, 39: 705-722.
|
| [34] |
Li SY, Lyu DJ, Huang GPet al. . Spatially varying impacts of built environment factors on rail transit ridership at station level: a case study in Guangzhou, China. J Transp Geogr. 2020, 82. 102631
|
| [35] |
Wang J, Wan F, Dong CJ, Yin CY, Chen XY. Spatiotemporal effects of built environment factors on varying rail transit station ridership patterns. J Transp Geogr. 2023, 109: 103597.
|
| [36] |
Sohn K, Shim H. Factors generating boardings at metro stations in the Seoul metropolitan area. Cities. 2010, 27(5): 358-368.
|
| [37] |
Cardozo OD, García-Palomares JC, Gutiérrez J. Application of geographically weighted regression to the direct forecasting of transit ridership at station-level. Appl Geogr. 2012, 34: 548-558.
|
| [38] |
Jun MJ, Choi K, Jeong JE, Kwon KH, Kim HJ. Land use characteristics of subway catchment areas and their influence on subway ridership in Seoul. J Transp Geogr. 2015, 48: 30-40.
|
| [39] |
Ding C, Liu TT, Yao BZ, Zhang Y, Qiao XY. Understanding the time-dependent effect of built environment attributes on station-level metro ridership uncertainty in Beijing: a big data analytic approach. Tunn Undergr Space Technol. 2023, 137: 105148.
|
| [40] |
Shi YJ, Zeng LH. How do built environment characteristics influence metro-bus transfer patterns across metro station types in Shanghai?. J Transp Geogr. 2025, 123104137.
|
| [41] |
Kong XJ, Xu ZZ, Shen GJet al. . Urban traffic congestion estimation and prediction based on floating car trajectory data. Future Gener Comput Syst. 2016, 6197-107.
|
| [42] |
Wang XQ, Shao CF, Yin CY, Guan L. Exploring the relationships of the residential and workplace built environment with commuting mode choice: a hierarchical cross-classified structural equation model. Transp Lett. 2022, 143274-281.
|
| [43] |
Jackson JE. A user’s guide to principal components. 1991, New York, John Wiley & Sons.
|
| [44] |
Hopkins B, Skellam JG. A new method for determining the type of distribution of plant individuals. Ann Bot. 1954, 18(2): 213-227.
|
| [45] |
Bagirov AM, Aliguliyev RM, Sultanova N. Finding compact and well-separated clusters: clustering using silhouette coefficients. Pattern Recognit. 2023, 135: 109144.
|
| [46] |
Davies DL, Bouldin DW. A cluster separation measure. IEEE Trans Pattern Anal Mach Intell. 1979, 2224-227.
|
| [47] |
Caliński T, Harabasz J. A dendrite method for cluster analysis. Commun Stat Theory Methods. 1974, 3(1): 1-27
|
| [48] |
McFadden D (1974) Conditional logit analysis of qualitative choice behavior. Paul Zarembka (ed.) Frontieres in Econometrics, pp. 105–142. Academic Press, New York
|
| [49] |
Aziz HA, Nagle NN, Morton AMet al. . Exploring the impact of walk–bike infrastructure, safety perception, and built-environment on active transportation mode choice: a random parameter model using New York City commuter data. Transportation. 2018, 45: 1207-1229.
|
| [50] |
Ortúzar J, Willumsen LG. Modelling transport. 2011John Wiley & Sons.
|
| [51] |
Wan TY, Lu W, Na X. Quantifying the social equity of economic performance for different groups of residents in rail transit station areas. Urban Rail Transit. 2025, 11: 28-52.
|
| [52] |
Yang H, Peng JD, Zhang YH, Luo X, Yan XX. Understanding the spatiotemporal impacts of the built environment on different types of metro ridership: a case study in Wuhan, China. Smart Cities. 2023, 6(5): 2282-2307.
|
Funding
Nature Science Basic Research Program of Shaanxi Province, China(2024JC-YBMS-359)
Scientific Innovation Practice Project of Postgraduates of Chang’an University(300103725058)
RIGHTS & PERMISSIONS
The Author(s)
PDF
