[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122744-en":3,"doc-seo-122744-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122744,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Effects of Buffer Size on Associations Between the Built Environment and Metro Ridership - A Machine Learning-Based Sensitive Analysis","Uncertainty about the relevant buffer size of metro station catchment areas can cause inconsistent conclusions about how the built environment relates to metro ridership. This study addresses the issue using finer-grained big data and non-parametric machine learning to run sensitivity analysis across four radial buffers (300 m, 600 m, 800 m, 1000 m). Results show limited impact on ordinary least squares predictive power, but substantial effects for machine learning. A 600 m buffer yields the best model fit. Relative importance and nonlinear relationships also vary when the spatial delineation deviates from the true context. The findings guide benchmark selection for station-area planning and demand forecasting and stress careful analytical unit choice.","Effects of buffer size on associations between the built environment and metro ridership: A machine learning-based sensitive analysis  \nXiang Liua, Xiaohong Chena,b,􀀍 , Mingshu Tianb,􀀍 , Jonas De Vosc  \na Urban Mobility Institute, Tongji University, Shanghai, China  \nb Key Laboratory of Road and Traffic Engineering of the Ministry of Education, School of Transportation Engineering, Tongji University, Shanghai, China  \nc Bartlett School of Planning, University College London, London, UK  \nAbstract  \nUncertainty in the relevant buffer size of metro station catchment areas may drive inconsistencies in the findings on the built environment and metro ridership. Although previous studies estimate the effect of this uncertainty, the results are far from definitive. By utilizing finer-grained big data and non-parametric machine learning approaches, this study conducted a sensitivity analysis defining built environment factors within four radial buffer sizes: 300 m, 600 m, 800 m, and 1000 m on associations with metro ridership. The results suggest that: (1) different buffer sizes have little influence on the ordinary least-squares model’s predictive power, but significant influence on the machine learning model; (2) the use of a 600 m buffer size around the transit station demonstrates the best model fit and variation explanation compared to others; (3) findings on the relative importance, ranks, and nonlinear associations with metro ridership can be impacted as the choice of geographic delineation of buffer sizes deviate from the true relevant geographic context of built environment variables. The results assist planners in setting a benchmark for metro catchment areas for station-area planning and demand forecasting, more importantly, the findings highlight the importance of meticulously selecting the analytical spatial unit for area-based variables, especially when utilizing non-parametric machine learning approaches in research.  \nKeywords: buffer size; catchment area; sensitive analysis; built environment; metro ridership; XGBoost  \n􀀍 Corresponding author at: 4800 Cao’an Road, Shanghai 201804, China  \nE-mail [addresses: xliu02@tongji.edu.cn](addresses: xliu02@tongji.edu.cn) (X. Liu), [tongjicxh@163.com](tongjicxh@163.com) (X. Chen), [2133372@tongji.edu.cn](2133372@tongji.edu.cn) (M.  \nTian), [jonas.devos@ucl.ac.uk](jonas.devos@ucl.ac.uk) (J. De Vos).  \n1 1. Introduction  \n2 Many countries around the world have experienced rapid urbanization and  \n3 increased motorization over the past decades, while negative externalities such as urban  \n4 sprawl, traffic congestion, and environmental pollution are pervasive throughout many  \n5 megacities (Batty et al., 2003) . Since the early 1990s, the concept of transit-oriented  \n6 development (TOD) has garnered widespread attention (Calthorpe, 1993) and has  \n7 emerged as a promising instrument for mitigating automobile dependence and urban  \n8 sprawl in numerous countries (Cervero, 1998; Cervero et al., 2002; Bertolini et al., 2012;  \n9 Nasri and Zhang, 2014; Papa and Bertolini, 2015; Xu et al., 2017) .  \n10 To understand the determinants of metro ridership and to forecast metro demand, 11 many studies use the direct ridership model (DRM) to investigate the relationship  \n12 between the station-area built environment and metro ridership (An et al., 2019; Ding  \n13 et al., 2019; Loo et al., 2010) . Compared to the conventional four-step model (i.e., trip 14 generation, trip distribution, mode choice, and traffic assignment), the DRM offers a 15 cost-effective alternative because of ‘‘rapid response, simplicity of use, ease of results 16 interpretation, low information requirements and low cost’’(Cardozo et al., 2012: 556) .  \n17 Beyond forecasting, the elasticity values in the DRM expose the potential consequences  \n18 of urban planning strategies on transit ridership, such as the introduction of new urban  \n19 developments or the densification of existing ones, which are particularly crucial","cbCain9dng6wlmyV","https://ap.wps.com/l/cbCain9dng6wlmyV","pdf",1720331,1,41,"English","en",105,"# Introduction\n# Methodology\n## Sensitivity analysis with radial buffers\n## Non-parametric machine learning approach\n# Results\n## Model fit and predictive power\n## Relative importance and nonlinear associations\n# Implications for planning and demand forecasting","[{\"question\":\"What uncertainty does the study focus on regarding metro station catchment areas?\",\"answer\":\"The study focuses on uncertainty in the relevant buffer size used to define metro station catchment areas, which can lead to inconsistent findings about the built environment and ridership.\"},{\"question\":\"How does the research conduct the sensitivity analysis?\",\"answer\":\"It defines built environment factors within four radial buffer sizes around stations (300 m, 600 m, 800 m, 1000 m) and evaluates associations with metro ridership using non-parametric machine learning approaches.\"},{\"question\":\"Which buffer size provides the best model performance and why is spatial unit selection important?\",\"answer\":\"A 600 m buffer shows the best model fit and variation explanation. The study also finds that relative importance, ranks, and nonlinear associations can change when the chosen geographic delineation diverges from the true contextual area.\"}]","Effects of Buffer Size on Associations Between the Built Environment and Metro Ridership - A Machine Learning-Based Sensitive Analysis | PDF",1785812651,103,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"effects-of-buffer-size-on-associations-between-the-built-environment-and-metro-ridership-a-machine-learning-based-sensitive-analysis","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/effects-of-buffer-size-on-associations-between-the-built-environment-and-metro-ridership-a-machine-learning-based-sensitive-analysis/122744/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What uncertainty does the study focus on regarding metro station catchment areas?","Question",{"text":75,"@type":76},"The study focuses on uncertainty in the relevant buffer size used to define metro station catchment areas, which can lead to inconsistent findings about the built environment and ridership.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the research conduct the sensitivity analysis?",{"text":80,"@type":76},"It defines built environment factors within four radial buffer sizes around stations (300 m, 600 m, 800 m, 1000 m) and evaluates associations with metro ridership using non-parametric machine learning approaches.",{"name":82,"@type":73,"acceptedAnswer":83},"Which buffer size provides the best model performance and why is spatial unit selection important?",{"text":84,"@type":76},"A 600 m buffer shows the best model fit and variation explanation. The study also finds that relative importance, ranks, and nonlinear associations can change when the chosen geographic delineation diverges from the true contextual area.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]