[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126287-en":3,"doc-seo-126287-105":30,"detail-sidebar-cat-0-en-105":92},{"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":11,"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},126287,2336475104736,"Quinn","https://ap-avatar.wpscdn.com/avatar/22000c4c5e0e5b17e70?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786591360781797222",8,"Research & Report","Machine Learning Predictions for Traffic Equilibria in Road Renovation Scheduling","Accurately estimating the impact of road maintenance schedules on traffic conditions is crucial because poorly planned operations can significantly worsen congestion. Since analytical prediction of congestion increases is difficult, traffic simulations are widely used, but long-term planning with many overlapping projects makes them prohibitively expensive. This study evaluates machine-learning surrogate models that predict network-wide congestion from engineered traffic features and one-hot encodings, using an online learning setup. Results show XGBoost achieves the best accuracy, notably MAPE of 11%, reducing computational burden in large-scale maintenance planning.","1  \narXiv :2506 .05933v 1 [ cs .LG] 6 Jun 2025  \nAbstract. Accurately estimating the impact of road maintenance schedules on traffic conditions is important because maintenance operations can substantially worsen congestion if not carefully planned. Reliable estimates allow planners to avoid excessive delays during periods of roadwork. Since the exact increase in congestion is difficult to predict analytically, traffic simulations are commonly used to assess the redistribution of the flow of traffic. However, when applied to long-term maintenance planning involving many overlapping projects and scheduling alternatives, these simulations must be run thousands of times, resulting in a significant computational burden. This paper investigates the use of machine learning-based surrogate models to predict network-wide congestion caused by simultaneous road renovations. We frame the problem as a supervised learning task, using one-hot encodings, engineered traffic features, and heuristic approximations. A range of linear, ensemble-based, probabilistic, and neural regression models is evaluated under an online learning framework in which data progressively becomes available. The experimental results show that the Costliest Subset Heuristic provides a reasonable approximation when limited training data is available, and that most regression models fail to outperform it, with the exception of XGBoost, which achieves substantially better accuracy. In overall performance, XGBoost significantly outperforms alternatives in a range of metrics, most strikingly Mean Absolute Percentage Error (MAPE) and Pinball loss, where it achieves a MAPE of 11% and outperforms the nextbest model by 20% and 38% respectively. This modeling approach has the potential to reduce the computational burden of large-scale traffic assignment problems in maintenance planning.  \nKeywords: Traffic simulation · Surrogate modeling · Machine learning · Quantile regression · Road renovation scheduling  \nMachine Learning Predictions for Traffic Equilibria in Road Renovation Scheduling  \nRobbert Bosch [0009−0006−8807−1031], Wouter van Heeswijk [0000−0002−5413−9660], Patricia Rogetzer [0000−0001−9582−6320], and Martijn Mes [0000−0001−9676−5259]  \nUniversity of Twente, Department of High Tech Business and Entrepeneurship, The  \nNetherlands  \n{[r.r.bosch](r.r.bosch) , w.j.a.vanheeswijk, p.b.rogetzer, [m.r.k.mes](m.r.k.mes}@utwente.nl)[}](m.r.k.mes}@utwente.nl)[@utwente.nl](m.r.k.mes}@utwente.nl)  \n1 Introduction  \nThis study is motivated by the need to efficiently evaluate maintenance schedules by predicting the traffic impact of simultaneous road renovations. The inspiration for this work is the Road Network Maintenance Scheduling Problem (RNMSP), which involves determining the optimal timing of maintenance activities on a road network to minimize disruption while respecting budgetary, resource, and deadline constraints. We specifically address the computational burden of traffic simulations through surrogate modeling, focusing on a fixed instance in which a predefined set of roads must be renovated. Due to the urgency of many renovation tasks, multiple projects must be scheduled simultaneously, with the objective of minimizing overall congestion while adhering to project deadlines.  \nAs a case study, we use the Sioux Falls traffic network, which represents a simplified highway system with predefined traffic demand. The network is modeled as a directed graph, where each link represents a road with a given free flow travel time (FFT) and capacity. Renovation of a road temporarily reduces its capacity and increases its FFT, causing traffic to reroute and potentially increasing congestion throughout the network. Figure 1 shows the Sioux Falls network, with uncongested traffic flows in green and congested flows in red. The right network illustrates the effect of removing two roads, redistributing traffic.  \nEach schedule specifies which maintenance projects are active in each time","cbCaikFDpSburGSu","https://ap.wps.com/l/cbCaikFDpSburGSu","pdf",396596,1,15,"English","en",105,"# Abstract\n# Introduction\n## Road Network Maintenance Scheduling Problem (RNMSP)\n## Case Study: Sioux Falls Network\n## Scenario Simulation and Performance Measure\n## Traffic Assignment Problem (TAP) and Computational Cost\n## Surrogate Models for Traffic Impact Prediction","[{\"question\":\"Why are road maintenance scheduling evaluations computationally expensive?\",\"answer\":\"Traffic simulations, modeled as Traffic Assignment Problems, are accurate but costly to run. Long-term plans with many overlapping projects require thousands of alternatives, multiplying the total simulation time.\"},{\"question\":\"How does the surrogate modeling approach work in this study?\",\"answer\":\"The method frames prediction as supervised learning to estimate total travel time for unevaluated scenarios. It supports early discarding of schedules likely to produce high congestion without running additional simulations.\"},{\"question\":\"Which model performed best and what were the key results?\",\"answer\":\"XGBoost outperformed other regression models under the evaluated metrics. It achieved the strongest overall accuracy, including a Mean Absolute Percentage Error (MAPE) of 11% and improvements in Pinball loss relative to the next-best model.\"}]","Machine Learning Predictions for Traffic Equilibria in Road Renovation Scheduling | PDF",1785904269,38,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"machine-learning-predictions-for-traffic-equilibria-in-road-renovation-scheduling","",{"@graph":36,"@context":86},[37,54,69],{"@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/machine-learning-predictions-for-traffic-equilibria-in-road-renovation-scheduling/126287/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":11},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why are road maintenance scheduling evaluations computationally expensive?","Question",{"text":76,"@type":77},"Traffic simulations, modeled as Traffic Assignment Problems, are accurate but costly to run. Long-term plans with many overlapping projects require thousands of alternatives, multiplying the total simulation time.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the surrogate modeling approach work in this study?",{"text":81,"@type":77},"The method frames prediction as supervised learning to estimate total travel time for unevaluated scenarios. It supports early discarding of schedules likely to produce high congestion without running additional simulations.",{"name":83,"@type":74,"acceptedAnswer":84},"Which model performed best and what were the key results?",{"text":85,"@type":77},"XGBoost outperformed other regression models under the evaluated metrics. It achieved the strongest overall accuracy, including a Mean Absolute Percentage Error (MAPE) of 11% and improvements in Pinball loss relative to the next-best model.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]