Shared bicycles are becoming increasingly popular as a primary mode of micro-mobility due to easy accessibility in urban areas and ability to integrate with other public transportation systems. Understanding the travel patterns and modal characteristics of shared bicycles is essential for developing sustainable and eco-friendly urban transportation systems. Although the recent advance of GeoAIs has enabled the exploration of complex, nonlinear relationships in shared mobility patterns, these studies often provide a temporally aggregated view. Consequently, they tend to overlook the dynamics of these nonlinear effects, specifically how the influence of built environment, demographic, and public transit factors shifts across different times of day and seasons. This study addresses this gap by emphasizing a LightGBM model enhanced with a robust SHapley Additive Explanation (SHAP) framework, explicitly capturing these nonlinear effects and distinguishing spatiotemporal dynamics. As an empirical case study, we examine the shared bicycle system in Seoul. The findings reveal distinct differences in travel patterns and influencing factors between weekdays and weekends. Also, it is empirically shown that shared bicycles can be served mainly as an alternative means of connecting the first- and last-mile gaps, effectively integrating with the public transportation network. This study contributes to clarify personal mobility patterns and inform sustainable transport policy by demonstrating shared bicycles’ urban potential.
Bachand-MarleauJLeeBHEl-GeneidyAM (2012) Better understanding of factors influencing likelihood of using shared bicycle systems and frequency of use. Transportation Research Record: Journal of the Transportation Research Board2314(1): 66–71.
2.
CaigangZShaoyingLZhangzhiT, et al. (2022) Nonlinear and threshold effects of traffic condition and built environment on dockless bike sharing at street level. Journal of Transport Geography102: 103375.
3.
CampbellAACherryCRRyersonMS, et al. (2016) Factors influencing the choice of shared bicycles and shared electric bikes in Beijing. Transportation Research Part C: Emerging Technologies67: 399–414.
4.
CaspiOSmartMJNolandRB (2020) Spatial associations of dockless shared e-scooter usage. Transportation Research Part D: Transport and Environment86: 102396.
5.
ChenEYeZ (2021) Identifying the nonlinear relationship between free-floating bike sharing usage and built environment. Journal of Cleaner Production280: 124281.
6.
ChenPZhouJSunF (2017) Built environment determinants of bicycle volume: a longitudinal analysis. Journal of Transport and Land Use10(1): 655–674.
7.
ChoSLeeG (2021) Spatiotemporal multi-objective optimization for competitive mobile vendors’ location and routing using de facto population demands. Geographical Analysis54: 294–308.
8.
CorcoranJLiTRohdeD, et al. (2014) Spatio-temporal patterns of a Public Bicycle Sharing Program: the effect of weather and calendar events. Journal of Transport Geography41: 292–305.
9.
DillJVorosK (2007) Factors affecting bicycling demand: initial survey findings from the Portland, Oregon, region. Transportation Research Record: Journal of the Transportation Research Board2031(1): 9–17.
10.
El-AssiWSalah MahmoudMNurul HabibK (2017) Effects of built environment and weather on bike sharing demand: a station level analysis of commercial bike sharing in Toronto. Transportation44: 589–613.
11.
Faghih-ImaniAEluruN (2016) Incorporating the impact of spatio-temporal interactions on bicycle sharing system demand: a case study of New York CitiBike system. Journal of Transport Geography54: 218–227.
12.
Faghih-ImaniAEluruNEl-GeneidyAM, et al. (2014) How land-use and urban form impact bicycle flows: evidence from the bicycle-sharing system (BIXI) in Montreal. Journal of Transport Geography41: 306–314.
13.
FanAChenXWanT (2019) How have travelers changed mode choices for first/last mile trips after the introduction of bicycle-sharing systems: an empirical study in Beijing, China. Journal of Advanced Transportation2019: 1–16.
14.
GuoJYBhatCRCoppermanRB (2007) Effect of the built environment on motorized and nonmotorized trip making: substitutive, complementary, or synergistic?Transportation Research Record: Journal of the Transportation Research Board2010(1): 1–11.
15.
HsuCYLiW (2023) Explainable GeoAI: can saliency maps help interpret artificial intelligence’s learning process? An empirical study on natural feature detection. International Journal of Geographical Information Science37(5): 963–987.
16.
HuYGoodchildMZhuAX, et al. (2024) A five-year milestone: reflections on advances and limitations in GeoAI research. Annals of GIS30(1): 1–14.
17.
HuoJYangHLiC, et al. (2021) Influence of the built environment on E-scooter sharing ridership: a tale of five cities. Journal of Transport Geography93: 103084.
18.
JanowiczKGaoSMcKenzieG, et al. (2020) GeoAI: spatially explicit artificial intelligence techniques for geographic knowledge discovery and beyond. International Journal of Geographical Information Science34(4): 625–636.
19.
JiangRHuMBWuQS, et al. (2017) Traffic dynamics of bicycle flow: experiment and modeling. Transportation Science51(3): 998–1008.
20.
JinSTWangLSuiD (2023) How the built environment affects E-scooter sharing link flows: a machine learning approach. Journal of Transport Geography112: 103687.
21.
KeGMengQFinleyT, et al. (2017) Lightgbm: a highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems30: 3149–3157.
22.
KimMChoGH (2021) Analysis on bike-share ridership for origin-destination pairs: effects of public transit route characteristics and land-use patterns. Journal of Transport Geography93: 103047.
23.
KongHJinSTSuiDZ (2020) Deciphering the relationship between bikesharing and public transit: modal substitution, integration, and complementation. Transportation Research Part D: Transport and Environment85: 102392.
24.
KouZCaiH (2019) Understanding bike sharing travel patterns: an analysis of trip data from eight cities. Physica A: Statistical Mechanics and its Applications515: 785–797.
25.
LathiaNAhmedSCapraL (2012) Measuring the impact of opening the London shared bicycle scheme to casual users. Transportation Research Part C: Emerging Technologies22: 88–102.
26.
LeeSLeeG (2021) Development and application of the flow cluster detection method: a case of public transit trips in Seoul. Journal of the Korean Cartographic Association21(2): 129–144.
27.
LeeMHwangSParkY, et al. (2022) Factors affecting bike-sharing system demand by inferred trip purpose: integration of clustering of travel patterns and geospatial data analysis. International Journal of Sustainable Transportation16(9): 847–860.
28.
LiZ (2022) Extracting spatial effects from machine learning model using local interpretation method: an example of SHAP and XGBoost. Computers, Environment and Urban Systems96: 101845.
29.
LinPWengJHuS, et al. (2020) Revealing spatio-temporal patterns and influencing factors of dockless bike sharing demand. IEEE Access8: 66139–66149.
30.
LundbergSMLeeSI (2017) A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems30: 4768–4777.
31.
LvHLiHChenY, et al. (2023) An origin-destination level analysis on the competitiveness of bike-sharing to underground using explainable machine learning. Journal of Transport Geography113: 103716.
32.
MaXJiYYuanY, et al. (2020) A comparison in travel patterns and determinants of user demand between docked and dockless bike-sharing systems using multi-sourced data. Transportation Research Part A: Policy and Practice139: 148–173.
33.
MunkácsyAMonzónA (2017) Potential user profiles of innovative bike-sharing systems: the case of BiciMAD (Madrid, Spain). Asian Transport Studies4(3): 621–638.
34.
QiuWChangH (2021) The interplay between dockless bikeshare and bus for small-size cities in the US: a case study of Ithaca. Journal of Transport Geography96: 103175.
35.
ReckDJAxhausenKW (2021) Who uses shared micro-mobility services? Empirical evidence from Zurich, Switzerland. Transportation Research Part D: Transport and Environment94: 102803.
36.
SchimohrKDoeblerPScheinerJ (2023) Prediction of bike-sharing trip counts: comparing parametric spatial regression models to a geographically weighted XGBoost algorithm. Geographical Analysis55(4): 651–684.
37.
ShelatSHuismanRvan OortN (2018) Analysing the trip and user characteristics of the combined bicycle and transit mode. Research in Transportation Economics69: 68–76.
38.
SiminiFBarlacchiGLucaM, et al. (2021) A deep gravity model for mobility flows generation. Nature Communications12(1): 6576.
39.
SongYHuangY (2020) Investigating complementary and competitive relationships between bikeshare service and public transit: a spatial-temporal framework. Transportation Research Record: Journal of the Transportation Research Board2674(1): 260–271.
40.
SongYMerlinLRodriguezD (2013) Comparing measures of urban land use mix. Computers, Environment and Urban Systems42: 1–13.
41.
SongJZhangLQinZ, et al. (2021) A spatiotemporal dynamic analyses approach for dockless bike-share system. Computers, Environment and Urban Systems85: 101566.
42.
UddinMHwangHLHasnineMS (2023) An interpretable machine learning framework to understand bikeshare demand before and during the COVID-19 pandemic in New York City. Transportation Planning and Technology46(4): 482–498.
43.
XinRAiTDingL, et al. (2022) Impact of the COVID-19 pandemic on urban human mobility-A multiscale geospatial network analysis using New York bike-sharing data. Cities126: 103677.
44.
YinGHuangZFuC, et al. (2024) Examining active travel behavior through explainable machine learning: insights from Beijing, China. Transportation Research Part D: Transport and Environment127: 104038.
45.
ZhangJPanXLiM, et al. (2016) Bicycle-sharing system analysis and trip prediction. In 2016 17th IEEE International Conference on Mobile Data Management (MDM) (Vol. 1, pp. 174–179). IEEE.
46.
ZhaoDOngGPWangW, et al. (2021) Estimating public bicycle trip characteristics with consideration of built environment data. Sustainability13(2): 500.
47.
ZhouX (2015) Understanding spatiotemporal patterns of biking behavior by analyzing massive bike sharing data in Chicago. PLoS One10(10): e0137922.
48.
ZuoTWeiHChenN, et al. (2020) First-and-last mile solution via bicycling to improving transit accessibility and advancing transportation equity. Cities99: 102614.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
