[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122846-en":3,"doc-seo-122846-105":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},122846,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Leveraging Probe Data and Machine Learning to Derive and Interpret Macroscopic Fundamental Diagrams Across U.S. Cities","Macroscopic fundamental diagram (MFD) formalizes the relationship among traffic flow, density, and speed at the network level, enabling network-wide understanding to allocate demand and improve performance while reducing congestion. Historical data have limited empirical MFD modeling, particularly for U.S. cities. This study uses large-scale, granular census-tract flow and density from vehicle probe data to create a machine-learning framework that derives MFD models and explains differences across urban networks. XGBoost delivers the best prediction for flow given density and location attributes. SHAP interaction values interpret drivers such as land use, transportation infrastructure, and network topology, supporting data-driven, location-specific MFDs for transportation planning and management decisions.","Lawrence Berkeley National Laboratory  \nLBL Publications  \nTitle  \nLeveraging Probe Data and Machine Learning to Derive and Interpret Macroscopic Fundamental Diagrams Across U.S. Cities  \nPermalink  \n[https://escholarship.org/uc/item/42m2q3s6](https://escholarship.org/uc/item/42m2q3s6)  \nISBN  \n9798350324457  \nAuthors  \nJin, Ling  \nXu, Xiaodan Wang, Yuhan et al.  \nPublication Date  \n2023-12-18  \nDOI  \n10.1109/bigdata59044.2023.10386591  \nCopyright Information  \nThis work is made available under the terms of a Creative Commons Attribution License, available at [https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)  \nPeer reviewed  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \n2023 IEEE International Conference on Big Data (BigData) | 979-8-3503-2445-7/23/$3 1.00 ©2023 IEEE | DOI: 10. 1 109/BigData59044.2023. 10386591  \n2023 IEEE International Conference on Big Data (BigData)  \nLeveraging Probe Data and Machine Learning to Derive and Interpret Macroscopic Fundamental Diagrams Across U.S. Cities  \nLing Jin, Xiaodan Xu, Yuhan Wang Energy Technology Area, Berkeley National Laboratory Berkeley, CA 94720 ljin, xiaodanxu, [yuhan_wang@lbl.gov](yuhan_wang@lbl.gov)  \nKaveh Farokhi Sadabadi Center for Advanced Transportation Technology University of Maryland College Park, MD 20742 [kfarokhi@umd.edu](kfarokhi@umd.edu)  \nAlina Lazar Youngstown State University Department of Computer Science and Information Youngstown, OH 44555 Email: [alazar@lbl.gov](alazar@lbl.gov)  \nDuleep Rathgamage Don Kennesaw State University School of Data Science and Analytics Marietta, GA 30060 [drathgam@kennesaw.edu](drathgam@kennesaw.edu)  \nZachary Needell, C Anna Spurlock Energy Analysis and Environmental Impacts Division Lawrence Berkeley National Laboratory Berkeley, CA 94720 ZANeedell, [caspurlock@lbl.gov](caspurlock@lbl.gov)  \nMahyar Amirgholy, Kennesaw State University Civil and Environmental Engineering Department Marietta, GA 30060 [mahyar.amirgholy@kennesaw.edu](mahyar.amirgholy@kennesaw.edu)  \nMona Asudegi Office of Transportation Policy Studies  \nFederal Highway Administration Washington DC, D.C. 20590 [mona.asudegi@dot.gov](mona.asudegi@dot.gov)  \nAbstract—Macroscopic fundamental diagram (MFD) captures an orderly relationship among traffic flow, density, and speed at the network level. Understanding network-wide traffic through MFDs can optimally allocate demand to existing networks, improving performance by maximizing network production and avoiding congestion. However, due to historical data limitations, empirically derived MFD models are sparse in the literature, especially for the U.S. cities. Leveraging a large-scale and granular census-tract-level flow and density derived from vehicle probe data, this research is the first to develop a machine learning approach to both derive MFD models and interpret their underlying difference among urban networks across the entire United States. Among the four machine learning methods tested here XGBoost is found to deliver the best performance to predict the network traffic flow for given vehicular density and location attributes. Interaction Shapley Additive explanation (SHAP) values are used to interpret the factors, such as land use, transportation infrastructure, and network topology, that influence the flow-density relationships among locations. The analysis framework developed in this work can generate datadriven MFDs and a deeper understanding of their shape dependence on network, infrastructure, and land use characteristics, which can be used by transportation authorities to derive and optimize location-specific MFDs facilitating more informed management and planning decisions at the network level.  \nKeywords—macroscopic fundamental diagram, United States, vehicle probe data, machine learning models, TreeExplainer, Interaction Shapley values.  \nI. INTRODUCTION  \nTraffic in an urban network becomes cong","cbCaisBXkkJaAv0K","https://ap.wps.com/l/cbCaisBXkkJaAv0K","pdf",4416714,1,11,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"What does a macroscopic fundamental diagram (MFD) capture in this study?\",\"answer\":\"An MFD captures an orderly relationship among traffic flow, density, and speed at the network level, distinguishing uncongested and congested traffic regimes.\"},{\"question\":\"How does the research derive MFD models for U.S. cities?\",\"answer\":\"It leverages large-scale census-tract-level flow and density derived from vehicle probe data and trains machine learning models to derive and interpret MFDs.\"},{\"question\":\"Which machine learning method performs best, and how are influential factors interpreted?\",\"answer\":\"XGBoost delivers the best performance for predicting network traffic flow, and SHAP interaction values are used to interpret how land use, infrastructure, and topology influence flow-density relationships.\"}]","Leveraging Probe Data and Machine Learning to Derive and Interpret Macroscopic Fundamental Diagrams Across U.S. Cities | PDF",1785813236,28,{"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},"leveraging-probe-data-and-machine-learning-to-derive-and-interpret-macroscopic-fundamental-diagrams-across-us-cities","",{"@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/leveraging-probe-data-and-machine-learning-to-derive-and-interpret-macroscopic-fundamental-diagrams-across-us-cities/122846/",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 does a macroscopic fundamental diagram (MFD) capture in this study?","Question",{"text":75,"@type":76},"An MFD captures an orderly relationship among traffic flow, density, and speed at the network level, distinguishing uncongested and congested traffic regimes.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the research derive MFD models for U.S. cities?",{"text":80,"@type":76},"It leverages large-scale census-tract-level flow and density derived from vehicle probe data and trains machine learning models to derive and interpret MFDs.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning method performs best, and how are influential factors interpreted?",{"text":84,"@type":76},"XGBoost delivers the best performance for predicting network traffic flow, and SHAP interaction values are used to interpret how land use, infrastructure, and topology influence flow-density relationships.","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"]