Transportation Research Part E-Logistics and Transportation Review最新文献

{"title":"Task-splitting in home healthcare routing and scheduling","authors":"Loek van Montfort,&nbsp;Wout Dullaert,&nbsp;Markus Leitner","doi":"10.1016/j.tre.2025.104235","DOIUrl":"10.1016/j.tre.2025.104235","url":null,"abstract":"<div><div>This paper introduces the concept of task-splitting into home healthcare (HHC) routing and scheduling. It focuses on the design of routes and timetables for caregivers providing services at patients’ homes. Task-splitting is the division of a (lengthy) patient visit into separate visits that can be performed by different caregivers at different times. The resulting split parts may have reduced caregiver qualification requirements, relaxed visiting time windows, or a shorter/longer combined duration. However, additional temporal dependencies can arise between them. To incorporate task-splitting decisions into the planning process, we introduce two different mixed integer linear programming formulations, a Miller–Tucker–Zemlin and a time-indexed variant. These formulations aim to minimize operational costs while simultaneously deciding which visits to split and imposing a potentially wide range of temporal dependencies. We also propose pre-processing routines for the time-indexed formulation and two heuristic procedures. These methods are embedded into the branch-and-bound approach as primal and improvement heuristics. The results of our computational study demonstrate the additional computational difficulty introduced by task-splitting possibilities and the associated additional synchronization, and the usefulness of the proposed heuristic procedures. From a planning perspective, our results indicate that integrating task-splitting decisions into the planning process reduces staff requirements, decreases HHC operational costs, and allows caregivers to spend relatively more time on tasks aligned with their qualifications.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104235"},"PeriodicalIF":8.3,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144632412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Joint rescheduling for timetable and platform assignment of High-Speed Railways via graph neural network-based Deep Reinforcement Learning","authors":"Xuan Liu ,&nbsp;Min Zhou ,&nbsp;Hairong Dong","doi":"10.1016/j.tre.2025.104277","DOIUrl":"10.1016/j.tre.2025.104277","url":null,"abstract":"<div><div>Virtual coupling enables trains to travel in convoys with reduced headway, significantly enhancing operational efficiency. Joint rescheduling for High-Speed Railways (HSRs) timetable and platform assignment allows for more efficient utilization of station resources, thereby maximizing the benefits of virtual coupling. This study analyzes the operation processes of high-speed trains occupying routes and platforms under virtual coupling, and develops a joint rescheduling model for timetable and platform assignment under virtual coupling, considering a detailed decomposition of station structures. A Deep Reinforcement Learning (DRL)-based method is proposed to solve the joint rescheduling problem. The state of track occupancy by trains is represented using a heterogeneous graph. Based on this graph, a Markov Decision Process (MDP) is designed according to the constructed joint rescheduling model, achieving platforming and timetabling through track assignment, enabling end-to-end rescheduling. Graph Neural Networks (GNN) integrated with an attention mechanism are employed to effectively address the challenge of applying trained policies to train rescheduling problems of varying scales. The GNN efficiently captures node and edge features within the heterogeneous graph, resulting in size-agnostic performance. The numerical experiments are conducted based on real data from the Beijing–Shanghai High-Speed Railway. The proposed method can reduce total train delay by an average of 9.8% compared to the commonly used scheduling rules. It also shows high solving efficiency and stability compared to CPLEX and Genetic Algorithm (GA). Moreover, the solution time grows approximately linearly with the problem size. In particular, the learned policies can still achieve good results when solving large-scale and cross-line rescheduling problems that have not previously been encountered, demonstrating strong generalization capabilities.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104277"},"PeriodicalIF":8.3,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144614515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing operational impacts of large-scale disruptions in urban rail transit: An improved multilayer interdependent network cascading failure model by data calibration","authors":"Meiling Ding ,&nbsp;Tianlei Zhu ,&nbsp;Wenbin Lian ,&nbsp;Yun Wei ,&nbsp;Jianjun Wu","doi":"10.1016/j.tre.2025.104314","DOIUrl":"10.1016/j.tre.2025.104314","url":null,"abstract":"<div><div>Large-scale disruptions in urban rail transit can severely disrupt operations, causing significant economic losses, adverse social impacts, and even casualties. Existing impact analysis methods often depend on assumptions or are constrained by small data, which impede accurate inference of the outcomes of large-scale disruptions. In this study, different systems within the urban rail transit network are modeled as a multilayer interdependent network. Based on historical failure data, the impact of major emergency events is inferred using an improved node-edge joint cascading failure model. The results show that, after calibrating model parameters with historical failure data, the proposed model can accurately estimate the consequences of large-scale disruptions, while other benchmark models often fail to produce accurate results. We also find a negative correlation between train capacity and the severity of event impact. These findings provide valuable insights for emergency management in urban rail transit. Additionally, the inputs and outputs of the proposed model can enhance historical accident data, offering a new tool for inferring accident impacts via machine learning methods.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104314"},"PeriodicalIF":8.3,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144614811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Supply chain coordination of counter-seasonal fresh produce under the farmer’s overconfidence","authors":"Haoxiong Yang,&nbsp;Yang Liu,&nbsp;Xiaoju Zhang","doi":"10.1016/j.tre.2025.104293","DOIUrl":"10.1016/j.tre.2025.104293","url":null,"abstract":"<div><div>This paper examines a counter-seasonal fresh produce supply chain considering the farmer’s overconfidence. The market demand expected by the farmer depends on freshness-keeping effort and the level of the farmer’s overconfidence. The “ cost-sharing and two-part tariff ” hybrid contract is supposed to tackle the negative impacts of the farmer’s overconfidence on supply chain members and to realize system coordination. The findings of the study are as follows: (1) Complete overconfidence increases the gap between retailer profit growth rates and farmer profit growth rates, and consumer quality sensitivity does not always positively affect the profits of the overconfident farmer, which depends on the degree of farmer overconfidence. (2) The freshness-keeping effort level and price decisions are all positively associated with the farmer’s overconfidence, and when the farmer’s overconfidence surpasses a specific threshold, decentralized decisions will have a greater freshness-keeping effort level than centralized decisions. (3) Adopting the “ cost-sharing and two-part tariff ” hybrid contract mitigates the negative effects of overconfidence on members’ returns, achieves the Pareto zone within a certain range of transfers, and provides better coordination than a single contract.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104293"},"PeriodicalIF":8.3,"publicationDate":"2025-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144605198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-period risk-aware procurement optimization under COVID-19 disruption","authors":"Jonathan Chase ,&nbsp;Hoong Chuin Lau ,&nbsp;Jinfeng Yang ,&nbsp;Lu Liu","doi":"10.1016/j.tre.2025.104272","DOIUrl":"10.1016/j.tre.2025.104272","url":null,"abstract":"<div><div>Supply chain resilience has been a topic of active research in the operations research and AI communities for several years, but the COVID-19 pandemic threw the frailties of global supply chains into sharp relief. Disruptions and delays caused by fresh outbreaks leading to lockdowns, put severe strain on supply chains in many industries. In this work we develop lockdown-resilient procurement capabilities for a global technology company. First, through analysis of lockdown data from China we develop a logarithmic regression-based lockdown prediction method to complement a supplier risk metric for conventional risks. Second, we develop a multi-period stochastic optimization model that generates a medium-term risk-resilient procurement strategy through supplier diversification and carefully managed stock surplus. The strategy produced by this model is able to out-perform an earlier risk-constrained optimization by up to 50% expected cost when exposed to COVID-19 lockdown disruptions, and proves effective under sensitivity analysis of warehouse cost increases of up to 60%. The real-world viability of the approach is demonstrated by a real use case from IBM Manufacturing in Singapore.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104272"},"PeriodicalIF":8.3,"publicationDate":"2025-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144605199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrated order splitting, allocation, and delivery problem with a synchronized truck and drone fleet","authors":"Ruiguang Yang,&nbsp;Xiangyong Li","doi":"10.1016/j.tre.2025.104217","DOIUrl":"10.1016/j.tre.2025.104217","url":null,"abstract":"<div><div>In this paper, we study the integrated order splitting, allocation, and delivery problem with a synchronized fleet of trucks and drones (OSADP-STD), a pervasive challenge in the online retail industry that presents significant operational complexities for retailers. By leveraging inventories spread across multiple geographi- cally distributed fulfillment centers, retailers use a fleet of trucks and drones to collaboratively fulfill customer orders, which may consist of one or multiple products. The successful execution of the OSADP-STD relies heavily on the strict coordination and synchronization of the fulfillment resources. We first present a mixed integer linear programming model for the OSADP-STD, which poses significant challenges in obtaining high- quality solutions within reasonable time. To tackle these challenges, we propose a heuristic based on adaptive large neighborhood search. We then validate the effectiveness of the proposed approach through extensive experiments. We finally present sensitivity analyses that demonstrate how the integrated fulfillment strategy can optimize order fulfillment performance, providing a more cost-effective solution and highlighting the key factors that influence a retailer’s fulfillment operations.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104217"},"PeriodicalIF":8.3,"publicationDate":"2025-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144611821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Modeling supply chain disruptions due to geopolitical Reasons: A systematic literature review","authors":"C. López ,&nbsp;M.F. Morales-Contreras ,&nbsp;I.M. Langella ,&nbsp;J. Alonso-Monge","doi":"10.1016/j.tre.2025.104290","DOIUrl":"10.1016/j.tre.2025.104290","url":null,"abstract":"<div><div>This article aims to improve understanding of how to manage supply chain threats from geopolitical disruptions. To achieve this, the work conducted a systematic literature review and content analysis of 80 articles, examining both the impacts of geopolitical disruptions and the supply chain management decisions made in response. The analysis identifies six distinct types of geopolitical supply chain disruptions, along with their respective effects and corresponding managerial decisions. Their connections are illustrated through specific models tailored to each geopolitical disruption. Accordingly, the article also provides a framework summarizing strategies for mitigating, responding to, and recovering from each geopolitical disruption. This reveals that financial management, collaboration, resilience and, viable supply chain management are effective strategies for dealing with all geopolitical disruptions. However, digitalization, financial innovation management, location management, security management, risk management, circular economy, and sustainable supply chain management have a limited effect on some geopolitical disruptions. The article concludes by suggesting 16 directions for future research and offering practical insights for managers and policymakers.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104290"},"PeriodicalIF":8.3,"publicationDate":"2025-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144605197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A spatial–temporal dynamic attention-based Mamba model for multi-type passenger demand prediction in multimodal public transit systems","authors":"Zhiqi Shao ,&nbsp;Haoning Xi ,&nbsp;David A. Hensher ,&nbsp;Ze Wang ,&nbsp;Xiaolin Gong ,&nbsp;Junbin Gao","doi":"10.1016/j.tre.2025.104282","DOIUrl":"10.1016/j.tre.2025.104282","url":null,"abstract":"<div><div>Predicting passenger demand across multiple socio-demographic groups, such as adults, seniors, pensioners, and students, is essential for improving the operational efficiency, equity, inclusivity, and sustainability of multimodal public transit (PT) systems. Traditional demand prediction models, however, often fail to effectively capture the complex spatial–temporal variability inherent in heterogeneous socio-demographic groups. To bridge this gap, we propose a novel spatial–temporal dynamic attention-based state–space model, i.e., <span>STDAtt-Mamba</span>, tailored for multi-type passenger demand prediction in multimodal PT systems. The proposed <span>STDAtt-Mamba</span> model consists of three key components: an adaptive embedding layer that integrates station-level, passenger-type-specific, and temporal embeddings into a unified representation for efficient data processing; a spatial–temporal dynamic attention (<em>STDAtt</em>) module that employs sparse attention mechanisms to selectively capture crucial global spatial–temporal dynamics; and a spatial–temporal dynamic Mamba (<em>STDMamba</em>) module that extends the state–space modeling framework to fuse spatial and temporal dependencies dynamically. We prove that <span>STDAtt-Mamba</span> is a kind of spatial–temporal dual-path attention mechanism and theoretically validate the complementarity of <em>STDMamba</em> and <em>STDAtt</em> in capturing local and global dependencies, thereby improving the interpretability of the proposed <span>STDAtt-Mamba</span>. Extensive experiments are conducted on a large-scale multimodal PT dataset, including over 1.58 million passengers across nine distinct passenger groups (i.e., adults, seniors, pensioners, tertiary students, children, job seekers, school passengers, youth, and Gold Repat passengers) using travel modes such as bus, rail, and ferry, in Queensland, Australia, from January 2021 to January 2023. Experimental results demonstrate that the prediction performance of the proposed <span>STDAtt-Mamba</span> is superior to the19 baseline models with manageable computational costs, setting it as a state-of-the-art benchmark model for predicting the multi-type passenger demand in multimodal PT systems. This study offers an adaptive, scalable, robust, inclusive, and efficient predictive tool for transit authorities.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104282"},"PeriodicalIF":8.3,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144596509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Boosting column generation with graph neural networks for joint rider trip planning and crew shift scheduling","authors":"Jiawei Lu,&nbsp;Tinghan Ye,&nbsp;Wenbo Chen,&nbsp;Pascal Van Hentenryck","doi":"10.1016/j.tre.2025.104281","DOIUrl":"10.1016/j.tre.2025.104281","url":null,"abstract":"<div><div>Optimizing service schedules is pivotal to the reliable, efficient, and inclusive on-demand mobility. This pressing challenge is further exacerbated by the increasing needs of an aging population, the oversubscription of existing services, and the lack of effective solution methods. This study addresses the intricacies of service scheduling, by jointly optimizing rider trip planning and crew scheduling for a complex dynamic mobility service. The resulting optimization problems are extremely challenging computationally for state-of-the-art methods.</div><div>To address this fundamental gap, this paper introduces the Joint Rider Trip Planning and Crew Shift Scheduling Problem (<span>JRTPCSSP</span>) and a novel solution method, called Attention and Gated GNN-Informed Column Generation (<span>AGGNNI-CG</span>), that hybridizes column generation and machine learning to obtain near-optimal solutions to the <span>JRTPCSSP</span> with real-life constraints of the application. The key idea of the machine-learning component is to dramatically reduce the number of paths to explore in the pricing problem, accelerating the most time-consuming component of the column generation. The machine learning component is a graph neural network with an attention mechanism and a gated architecture, which is particularly suited to cater for the different input sizes coming from daily operations.</div><div><span>AGGNNI-CG</span> has been applied to a challenging, real-world dataset from the Paratransit system of Chatham County in Georgia. It produces substantial improvements compared to the baseline column generation approach, which typically cannot produce high-quality feasible solutions in reasonable time on large-scale complex instances. <span>AGGNNI-CG</span> also produces significant improvements in service quality compared to the existing system.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104281"},"PeriodicalIF":8.3,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144604196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Learning for routing: A guided review of recent developments and future directions","authors":"Fangting Zhou ,&nbsp;Attila Lischka ,&nbsp;Balázs Kulcsár ,&nbsp;Jiaming Wu ,&nbsp;Morteza Haghir Chehreghani ,&nbsp;Gilbert Laporte","doi":"10.1016/j.tre.2025.104278","DOIUrl":"10.1016/j.tre.2025.104278","url":null,"abstract":"<div><div>This paper reviews the current progress in applying machine learning (ML) tools to solve NP-hard combinatorial optimization problems, with a focus on routing problems such as the traveling salesman problem (TSP) and the vehicle routing problem (VRP). Due to the inherent complexity of these problems, exact algorithms often require excessive computational time to find optimal solutions, while heuristics can only provide approximate solutions without guaranteeing optimality. With the recent success of machine learning models, there is a growing trend in proposing and implementing diverse ML techniques to enhance the resolution of these challenging routing problems. We propose a taxonomy categorizing ML-based routing methods into construction-based and improvement-based approaches, highlighting their applicability to various problem characteristics. This review aims to integrate traditional OR methods with state-of-the-art ML techniques, providing a structured framework to guide future research and address emerging VRP variants.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104278"},"PeriodicalIF":8.3,"publicationDate":"2025-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144596508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}