{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T07:00:17Z","timestamp":1778223617789,"version":"3.51.4"},"reference-count":37,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["42101464"],"award-info":[{"award-number":["42101464"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["BX20220237"],"award-info":[{"award-number":["BX20220237"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["42101464"],"award-info":[{"award-number":["42101464"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["BX20220237"],"award-info":[{"award-number":["BX20220237"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>Station-level ridership is an important indicator for understanding the relationship between land use and rail transit, which is crucial for building more sustainable urban mobility systems. However, the nonlinear effects of the built environment on metro ridership, particularly concerning temporal heterogeneity, have not been adequately explained. To address this gap, this study proposes a versatile methodology that employs the eXtreme gradient boosting (XGBoost) tree to analyze the effects of factors on station-level ridership variations and compares these results with those of a multiple regression model. In contrast to conventional feature interpretation methods, this study utilized Shapley additive explanations (SHAP) to detail the nonlinear effects of each factor on station-level ridership across temporal dimensions (weekdays and weekends). Using Shanghai as a case study, the findings confirmed the presence of complex nonlinear and threshold effects of land-use, transportation, and station-type factors on station-level ridership in the association. The factor \u201cCommercial POI\u201d represents the most significant influence on ridership changes in both the weekday and weekend models; \u201cPublic Facility Station\u201d plays a role in increasing passenger flow in the weekend model, but it shows the opposite effect on the change in ridership in the weekday model. This study highlights the importance of explainable machine learning methods for comprehending the nonlinear influences of various factors on station-level ridership.<\/jats:p>","DOI":"10.3390\/ijgi13100365","type":"journal-article","created":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T03:49:34Z","timestamp":1729136974000},"page":"365","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Nonlinear and Threshold Effects on Station-Level Ridership: Insights from Disproportionate Weekday-to-Weekend Impacts"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8765-1639","authenticated-orcid":false,"given":"Yanyan","family":"Gu","sequence":"first","affiliation":[{"name":"School of Statistics and Data Science, Ningbo University of Technology, Ningbo 315211, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingxuan","family":"Dou","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,10,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"103783","DOI":"10.1016\/j.tust.2020.103783","article-title":"An overview of recent developments in China\u2019s metro systems","volume":"111","author":"Lin","year":"2021","journal-title":"Tunn. Undergr. Space Technol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.trc.2019.01.027","article-title":"DeepPF: A deep learning based architecture for metro passenger flow prediction","volume":"101","author":"Liu","year":"2019","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"102862","DOI":"10.1016\/j.apgeog.2022.102862","article-title":"Assess the non-linear relationship between built environment and active travel around light-rail transit stations","volume":"151","author":"Xiao","year":"2023","journal-title":"Appl. Geogr."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"732","DOI":"10.1177\/03611981231186595","article-title":"Evaluating the Nonlinear Impacts of Built Environment on Online Car-Hailing: Focus on the Whole Day","volume":"2678","author":"Zhou","year":"2023","journal-title":"Transp. Res. Rec."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"103728","DOI":"10.1016\/j.tra.2023.103728","article-title":"Substitutes or complements? Examining effects of urban rail transit on bus ridership using longitudinal city-level data","volume":"174","author":"Yang","year":"2023","journal-title":"Transp. Res. Part A Policy Pract."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.trc.2016.12.001","article-title":"Impacts of weather on public transport ridership: Results from mining data from different sources","volume":"75","author":"Zhou","year":"2017","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/j.cities.2019.05.013","article-title":"Understanding the impact of built environment on metro ridership using open source in Shanghai","volume":"93","author":"An","year":"2019","journal-title":"Cities"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.jtrangeo.2019.04.011","article-title":"How does the station-area built environment influence Metrorail ridership? Using gradient boosting decision trees to identify non-linear thresholds","volume":"77","author":"Ding","year":"2019","journal-title":"J. Transp. Geogr."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Aprigliano, V., Seriani, S., Toro, C., Rojas, G., Fukushi, M., Cardoso, M., Silva, M.A.V.D., Cucumides, C., de Oliveira, U.R., and Henr\u00edquez, C. (2024). Built Environment Effect on Metro Ridership in Metropolitan Area of Valpara\u00edso, Chile, un-der Different Influence Area Approaches. Isprs Int. J. Geo-Inf., 13.","DOI":"10.3390\/ijgi13080266"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"103301","DOI":"10.1016\/j.apgeog.2024.103301","article-title":"Non-linear impact of the built environment on metro commuter flows before and after the COVID-19 outbreak: A case study in Guangzhou","volume":"168","author":"Zang","year":"2024","journal-title":"Appl. Geogr."},{"key":"ref_11","unstructured":"Lundberg, S.M., and Lee, S. (2017). Consistent feature attribution for tree ensembles. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Yan, J., Wan, Q., Feng, J., Wang, J., Hu, Y., and Yan, X. (2023). The Non-Linear Influence of Built Environment on the School Commuting Metro Ridership: The Case in Wuhan, China. Isprs Int. J. Geo-Inf., 12.","DOI":"10.3390\/ijgi12050193"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Yin, J., Zhao, F., Tang, W., and Ma, J. (2024). The Nonlinear and Threshold Effect of Built Environment on Ride-Hailing Travel Demand. Appl. Sci., 14.","DOI":"10.20944\/preprints202404.0763.v1"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.tbs.2022.02.007","article-title":"Association between built environment characteristics and metro usage at station level with a big data approach","volume":"28","author":"Chen","year":"2022","journal-title":"Travel Behav. Soc."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"103380","DOI":"10.1016\/j.jtrangeo.2022.103380","article-title":"Spatiotemporal exploration of the non-linear impacts of accessibility on metro ridership","volume":"102","author":"Du","year":"2022","journal-title":"J. Transp. Geogr."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Liu, X., Li, Y., Fan, J., Shao, X., Lai, Z., and Li, Q. (2024). Spatiotemporal Analysis of Ridesourcing and Metro Transit Integration Considering Heterogeneity. Transp. Res. Rec., 355347707.","DOI":"10.1177\/03611981241242373"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"103856","DOI":"10.1016\/j.trd.2023.103856","article-title":"Nonlinear, threshold and synergistic effects of first\/last-mile facilities on metro ridership","volume":"121","author":"Peng","year":"2023","journal-title":"Transp. Res. Part D Transp. Environ."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhang, H., Cui, Y., Liu, Y., Jia, J., Shi, B., and Yu, X. (2024). Exploring Travel Mobility in Integrated Usage of Dockless Bike-Sharing and the Metro Based on Multisource Data. Isprs Int. J. Geo-Inf., 13.","DOI":"10.3390\/ijgi13040108"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"103134","DOI":"10.1016\/j.jtrangeo.2021.103134","article-title":"Uncovering the spatially heterogeneous effects of shared mobility on public transit and taxi","volume":"95","author":"Tang","year":"2021","journal-title":"J. Transp. Geogr."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"105148","DOI":"10.1016\/j.tust.2023.105148","article-title":"Understanding the time-dependent effect of built environment attributes on station-level metro ridership uncertainty in Beijing: A big data analytic approach","volume":"137","author":"Ding","year":"2023","journal-title":"Tunn. Undergr. Space Technol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"103899","DOI":"10.1016\/j.jtrangeo.2024.103899","article-title":"The impacts of extreme hot weather on metro ridership: A case study of Shenzhen, China","volume":"117","author":"Wang","year":"2024","journal-title":"J. Transp. Geogr."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.trc.2018.10.012","article-title":"Estimating historical hourly traffic volumes via machine learning and vehicle probe data: A Maryland case study","volume":"97","author":"Sadabadi","year":"2018","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"33","DOI":"10.5198\/jtlu.v6i2.268","article-title":"Development of a temporal and spatial linkage between transit demand and land-use patterns","volume":"6","author":"Lee","year":"2013","journal-title":"J. Transp. Land Use"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"103264","DOI":"10.1016\/j.apgeog.2024.103264","article-title":"Exploring interactive and nonlinear effects of key factors on intercity travel mode choice using XGBoost","volume":"166","author":"Li","year":"2024","journal-title":"Appl. Geogr."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"103032","DOI":"10.1016\/j.apgeog.2023.103032","article-title":"Incorporating neighborhoods with explainable artificial intelligence for modeling fine-scale housing prices","volume":"158","author":"Dou","year":"2023","journal-title":"Appl. Geogr."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"105405","DOI":"10.1016\/j.aap.2019.105405","article-title":"Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis","volume":"136","author":"Parsa","year":"2020","journal-title":"Accid. Anal. Prev."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"101039","DOI":"10.1016\/j.ecoinf.2019.101039","article-title":"Shapley additive explanations for NO2 forecasting","volume":"56","author":"Aznarte","year":"2020","journal-title":"Ecol. Inform."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"8761","DOI":"10.1021\/acs.jmedchem.9b01101","article-title":"Interpretation of Compound Activity Predictions from Complex Machine Learning Models Using Local Approximations and Shapley Values","volume":"63","author":"Bajorath","year":"2020","journal-title":"J. Med. Chem."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Xi, Y., Hou, Q., Duan, Y., Lei, K., Wu, Y., and Cheng, Q. (2024). Exploring the Spatiotemporal Effects of the Built Environment on the Nonlinear Impacts of Metro Ridership: Evidence from Xi\u2019an, China. Isprs Int. J. Geo-Inf., 13.","DOI":"10.3390\/ijgi13030105"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"104506","DOI":"10.1016\/j.cities.2023.104506","article-title":"Impacts of a new urban rail transit line and its interactions with land use on the ridership of existing stations","volume":"141","author":"Du","year":"2023","journal-title":"Cities"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3141\/2145-01","article-title":"Direct Ridership Model of Bus Rapid Transit in Los Angeles County, California","volume":"2145","author":"Cervero","year":"2010","journal-title":"Transp. Res. Rec."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"4016017","DOI":"10.1061\/(ASCE)UP.1943-5444.0000340","article-title":"How to Increase Rail Ridership in Maryland: Direct Ridership Models for Pol-icy Guidance","volume":"142","author":"Liu","year":"2016","journal-title":"J. Urban Plan. Dev."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/s11116-013-9492-3","article-title":"Analysis of Metro ridership at station level and station-to-station level in Nanjing: An approach based on direct demand models","volume":"41","author":"Zhao","year":"2014","journal-title":"Transportation"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1080\/10095020.2022.2161425","article-title":"How to determine city hierarchies and spatial structure of a megaregion?","volume":"27","author":"Gu","year":"2024","journal-title":"Geo-Spat. Inf. Sci."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Liu, B., Xu, Y., Guo, S., Yu, M., Lin, Z., and Yang, H. (2023). Examining the Nonlinear Impacts of Origin-Destination Built Environment on Metro Ridership at Station-to-Station Level. Isprs Int. J. Geo-Inf., 12.","DOI":"10.3390\/ijgi12020059"},{"key":"ref_37","first-page":"1278","article-title":"Geographically weighted regression modeling for multiple outcomes","volume":"112","author":"Chen","year":"2022","journal-title":"Ann. Am. Assoc. Geogr."}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/13\/10\/365\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:14:56Z","timestamp":1760112896000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/13\/10\/365"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,17]]},"references-count":37,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2024,10]]}},"alternative-id":["ijgi13100365"],"URL":"https:\/\/doi.org\/10.3390\/ijgi13100365","relation":{},"ISSN":["2220-9964"],"issn-type":[{"value":"2220-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,17]]}}}