Yu Wang , Renrong Zheng , Chengji Liang , Jian Shi
{"title":"Inventory routing problem of automotive parts considering time-varying demands: A machine learning enhanced branch-and-price approach","authors":"Yu Wang , Renrong Zheng , Chengji Liang , Jian Shi","doi":"10.1016/j.tre.2025.104297","DOIUrl":"10.1016/j.tre.2025.104297","url":null,"abstract":"<div><div>With the rise of mass customization and smart manufacturing, the automotive industry is rapidly transitioning to improve responsiveness, manage highly diversified customer orders, and reduce inbound logistics costs. To address this challenge, this paper proposes a new variant of the multi-period inventory routing problem, which focuses on coordinating discrete, time-varying demands for auto parts on the assembly line with predetermined packages at suppliers over a finite short-term time horizon (e.g., on an hourly basis). The objective is to minimize the total transportation and inventory cost by making aperiodic decisions on collection quantities and traveling routes simultaneously for an inbound warehouse near the assembly plant. An integer programming (IP) formulation with time-indexed variables is tailored for the problem to analyze the feasibility conditions. Then, a reformulation is designed to make the problem more tractable, based on which a novel machine learning enhanced branch-and-price algorithm (BPL) is proposed, where prediction-based cuts are embedded to accelerate the pricing procedure. Experiments on real-scale instances demonstrate that the algorithm consistently achieves near-optimal solutions, with a gap of 4.42% on average from the best-found lower bound, and reduces computation time by over 90% compared to directly solving the IP model by CPLEX. The proposed learning technique is computationally efficient, capable of shortening the total calculation time by an average of 13%. This work facilitates timely decision-making and offers new insights into multi-period inventory routing for inbound logistics.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104297"},"PeriodicalIF":8.3,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144670407","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":"Demand uncertainty aware curbside space allocation planning in shared-use transportation networks","authors":"Shanjeeda Akter, HM Abdul Aziz","doi":"10.1016/j.tre.2025.104245","DOIUrl":"10.1016/j.tre.2025.104245","url":null,"abstract":"<div><div>Efficient management of curbside space is gaining more attention as cities confront increasing traffic, curbside requirements, and mobility patterns. Given their increasing significance in meeting diverse shared-use mobility requirements, the absence of optimal planning on curbside areas can lead to networkwide negative impacts. This study examines demand uncertainty for planning at several temporal resolutions. Our developed approach identifies the optimal curbside space allocation planning strategies to enhance passenger-level services, considering the <em>Curb Productivity Index</em> and the uncertain arrival distribution of Shared-Use Mobility (SUM) service units throughout the curbside networks. We integrated a core optimization module to adjust capacity over various time scales and find the optimal allocation plan. Further, we integrated a sample-based heuristic to allow decision-making at multiple levels of granularity (allocating space hourly versus adjustments occurring every five minutes due to interconnected infrastructure technologies or analogous factors). The proposed solution methodology is demonstrated for a network of curbsides with known demand distribution parameters (truncated Normal with mean and standard deviation for hourly demand). The results suggest that the allocation plans are highly sensitive to the decision interval (minutes vs. one-hour), and the coarse-resolution decision-making may overestimate the performance of a curbside allocation plan, underscoring the need for fine-resolution allocation plans in cities.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104245"},"PeriodicalIF":8.3,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144670430","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 data-driven approach for spatio-temporal causal analysis in large-scale urban traffic networks","authors":"Pingping Dong , Xiaoning Zhang , Xiaoge Zhang","doi":"10.1016/j.tre.2025.104244","DOIUrl":"10.1016/j.tre.2025.104244","url":null,"abstract":"<div><div>Understanding causal relationships between traffic states throughout the system is of great significance for enhancing traffic management and optimization in urban traffic networks. Unfortunately, few studies in the literature have systematically analyzed causal structure characterizing the evolution of traffic states over time and gauged the importance of traffic nodes from a causal perspective, particularly in the context of large-scale traffic networks. Moreover, the dynamic nature of traffic patterns necessitates a robust method to reliably discover causal relationships, which are often overlooked in existing studies. To address these issues, we propose a Spatio-Temporal Causal Structure Learning and Analysis (STCSLA) framework for analyzing large-scale urban traffic networks at a mesoscopic level from a causal lens. The proposed framework comprises three main components: decomposition of spatio-temporal traffic data into localized traffic subprocesses; a Bayesian Information Criterion-guided spatio-temporal causal structure learning combined with temporal-dependencies preserving sampling for deriving reliable causal graph to uncover time-lagged and contemporaneous causal effects; establishing several causality-oriented indicators to identify causally critical nodes, mediator nodes, and bottleneck nodes in traffic networks. Experimental results on both a synthetic dataset and the real-world Hong Kong traffic dataset demonstrate that the proposed STCSLA framework accurately uncovers time-varying causal relationships and identifies key nodes that play various causal roles in influencing traffic dynamics. These findings underscore the potential of the proposed framework to improve traffic management and provide a comprehensive causality-driven approach for analyzing urban traffic networks.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104244"},"PeriodicalIF":8.3,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144670428","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}
Tao Zhou , Kai Li , Bohai Liu , Fulong Xie , Liping Xu , Han Zhang
{"title":"Competitive strategies in digital service capability: Self-Development vs. Cooperation","authors":"Tao Zhou , Kai Li , Bohai Liu , Fulong Xie , Liping Xu , Han Zhang","doi":"10.1016/j.tre.2025.104291","DOIUrl":"10.1016/j.tre.2025.104291","url":null,"abstract":"<div><div>We examine various competition modes arising from the deployment of the digital service capabilities by two competing digital companies in smart product service systems, and analyze the effects of digital service value-addition, the alignment between smart products and digital services on the operations of rival parties. We construct game-theoretic competition models to derive the optimal deployment strategy for digital companies’ digital service capabilities, as well as to determine the optimal digital service level and pricing strategy. According to the sub-game perfect equilibrium outcomes derived from a specific competition mode, our findings uncover that even if a party’s digital service capability is weaker, its digital company still possesses the potential to outperform its rival in terms of profitability. Additionally, an increase in value-addition offered by digital services can undermine digital companies’ profitability. Likewise, the heightened alignment between smart products and digital services can be detrimental to digital companies. Furthermore, our analysis unveils that when the digital service capabilities of both competitors are strong, one of the digital companies will deviate from the symmetrical digital service capability deployment strategy, resulting in an asymmetrical equilibrium in which one company invests internally to develop a digital service capability, while the other partners with an external provider. On the contrary, when the digital service capabilities are weak, both competing digital companies opt to invest internally to deploy the digital service capability. However, this symmetrical equilibrium strategy ultimately places both digital companies in a prisoner’s dilemma.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104291"},"PeriodicalIF":8.3,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144670429","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":"Platform-empowered collaboration delivery model for express companies and rural passenger transport operators in rural areas","authors":"Weizhen Rao, Xiaohe Miao, Peng Liu, Lu Liu","doi":"10.1016/j.tre.2025.104311","DOIUrl":"10.1016/j.tre.2025.104311","url":null,"abstract":"<div><div>The rapid surge in e-commerce parcel volume has intensified demands for cost-effective and high-quality express delivery services in rural areas. This study proposes a platform-enabled collaborative delivery model that integrates express companies and rural passenger transport operators to improve last-mile logistics. Our goal is to facilitate efficient collaboration among stakeholders through platform-supported route planning and cost-sharing, with cost savings quickly estimated for decision-making. To assess the benefits of shared transport resources, we adopt a Shapley value-based cooperative game approach to determine cost allocation. This requires solving mixed-integer programming models for all possible alliance structures to compute characteristic functions. A mixed-integer linear programming model is formulated to address the multi-owner collaborative delivery vehicle routing problem with combined passenger and freight transport (MOCDVRP-CPFT), which quantifies delivery costs for each alliance configuration. A tailored solution framework is developed, incorporating batch processing, customer clustering, and an adaptive large neighbourhood search (ALNS) algorithm to generate high-quality solutions across all alliances. Six representative case studies in eastern, central, and western China using real-world data confirm the effectiveness of the proposed model, with the most significant savings observed in the western region. Based on the results, we offer region-specific policy suggestions to facilitate the implementation of CPFT in varying rural contexts. This study highlights the potential of digitally enabled, short-term collaborative alliances as a practical approach to improving rural logistics coordination and delivery efficiency.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104311"},"PeriodicalIF":8.3,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144670427","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}
Xin Wu , Xinyu Wang , Taehooie Kim , Khaled Saleh , Huiling Fu , Chenfeng Xiong
{"title":"Simultaneous estimation of induced, diverted, and ex-post demand for railway passengers: an interpretable machine learning framework based on constrained computational graphs","authors":"Xin Wu , Xinyu Wang , Taehooie Kim , Khaled Saleh , Huiling Fu , Chenfeng Xiong","doi":"10.1016/j.tre.2025.104283","DOIUrl":"10.1016/j.tre.2025.104283","url":null,"abstract":"<div><div>Passenger flow on train lines is driven by how travelers respond to service offerings and constraints within the railway system, shaped primarily by three factors: <strong>Diverted demand</strong> refers to a shift in travelers’ choices toward different train lines, quantified by analyzing changes in the probability of selecting a particular train line within a given line plan. <strong>Induced demand</strong> arises when improvements in service quality led to an increase in passenger demand within a railway system. <strong>Ex-post demand</strong> occurs when seat capacity constraints force travelers to make choices that deviate from their initial preferences. This paper aims to develop a systematic and theoretically consistent methodology to estimate the three types of demand that drive overall demand variation. To integrate these estimation modules, a computational graph-based learning architecture is proposed to solve the railway passenger demand estimation (RPDE) problem. The RPDE problem simultaneously estimates passenger boarding and alighting at stations, OD trips between stations, and passenger flows loaded onto train lines. The behavioral parameters associated with travel time, ticket price, and line frequency are also calibrated. A novel four-stage adapted alternating direction method of multipliers (ADMM), enhanced by backpropagation, is proposed to solve the RPDE problem to ensure consistency between modules and enable efficient solutions. We demonstrate the effectiveness of the method through scenario analyses, quantifying the composition of the demand, and revealing their implications for policymaking. A real-world case study in the Beijing-Shanghai high-speed rail corridor is used to demonstrate the applicability of the proposed approach.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104283"},"PeriodicalIF":8.3,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144670409","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":"Expansion of bi-modal express transit networks − a hybrid optimization approach","authors":"Reza Mahmoudi, Saeid Saidi, S.C. Wirasinghe","doi":"10.1016/j.tre.2025.104317","DOIUrl":"10.1016/j.tre.2025.104317","url":null,"abstract":"<div><div>Existing research has predominantly concentrated on designing a new transit network without considering the pre-existing network. However, the majority of problems involve redesigning or extending an already existing network. Considering the pre-existing multi-modal transit network in a city, we have integrated analytical methodologies and mathematical programming to formulate a two-stage approach for addressing the bi-modal express transit network design problem (ETNDP) within the context of a surface express transit system. In the first stage, we use analytical approaches and continuum approximations to identify the optimal locations of new stations. In the second stage, mathematical programming is proposed to simultaneously determine the optimal layout of express transit routes, the technology of each transit route, and the service headway associated with all transit routes (i.e., existing and new routes). Then, a metaheuristic algorithm based on a Genetic Algorithm is introduced to solve the proposed mathematical programming for real-size transit networks. The proposed approach has then been applied to the express transit network of Calgary, Canada, a large-sized bi-modal express network. The bi-modal ETNDP has been solved for Calgary under various scenarios, and the results have been discussed. Analyses show that, in the proposed hybrid approach, solving a part of the problem analytically reduces its complexity significantly and enables parametric analysis, while using mathematical programming helps to address the complexity of ETNDP for real transit networks. The proposed approach stands out from existing similar studies due to its departure from simplifying assumptions concerning network topology, the city’s structure, capturing any type of demand patterns, model flexibility to for existing transit network extension, and multi-modality of the express transit network.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104317"},"PeriodicalIF":8.3,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144663416","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}
Honggang Zhang , Yuyan Wang , Mengyu Jiang , Zefan Huang , King-Wah Pang , Zhiyuan Liu
{"title":"Optimizing land-air collaborative operations with environmental considerations","authors":"Honggang Zhang , Yuyan Wang , Mengyu Jiang , Zefan Huang , King-Wah Pang , Zhiyuan Liu","doi":"10.1016/j.tre.2025.104301","DOIUrl":"10.1016/j.tre.2025.104301","url":null,"abstract":"<div><div>Urban air mobility (UAM) is an emerging transportation concept with the potential to transform urban commuting. By utilizing low-altitude airspace, novel aerial vehicles can provide faster transportation between vertiports in urban and suburban areas, offering a more efficient alternative than traditional surface transport. To successfully integrate UAM into urban environments, it is crucial to effectively connect it with existing road transportation systems, particularly in terms of constructing essential ground infrastructure, such as vertiports. This paper proposes a land-air collaborative network design model that incorporates environmental considerations. Specifically, we develop a bi-objective bi-level programming model to optimize the land-air integrated operations. The upper-level authority aims to minimize both the total travel time of the system and airborne pollutant emissions during UAM operations by selecting the locations and capacities of vertiports. The lower-level model determines the route choices of the multi-class commuters based on the user equilibrium condition. To solve this model, we propose a mixed-integer Bayesian optimization approach, incorporating a path-based solution algorithm using the partial linearization descent method to address the lower-level model. Numerical experiments demonstrate that incorporating environmental considerations significantly influences the design of the land-air collaborative network. In particular, environmental factors play a critical role in shaping commuters’ route choice, which in turn substantially affects key system metrics such as vertiport capacity, total travel time, and air pollutant emissions. This study offers valuable insights into optimizing land-air collaborative operations, maximizing the operational benefits of UAM while minimizing its environmental impact.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104301"},"PeriodicalIF":8.3,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144663418","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":"Dynamic preference-based multi-modal trip planning of public transport and shared mobility","authors":"Yimeng Zhang , Oded Cats , Shadi Sharif Azadeh","doi":"10.1016/j.tre.2025.104286","DOIUrl":"10.1016/j.tre.2025.104286","url":null,"abstract":"<div><div>The shift from private vehicles to public and shared transport is crucial to reducing emissions and meeting climate targets. Consequently, there is an urgent need to develop a multi-modal transport trip planning approach that integrates public transport and shared mobility solutions, offering viable alternatives to private vehicle use. To this end, we propose a preference-based optimization framework for multi-modal trip planning with public transport, ride-pooling services, and shared micro-mobility fleets. We introduce a mixed-integer programming model that incorporates preferences into the objective function of the mathematical model. We present a meta-heuristic framework that incorporates a customized Adaptive Large Neighborhood Search algorithm and other tailored algorithms, to effectively manage dynamic requests through a rolling horizon approach. Numerical experiments are conducted using real transport network data in a suburban area of Rotterdam The Netherlands Model application results demonstrate that the proposed algorithm can efficiently obtain near-optimal solutions. Managerial insights are gained from comprehensive experiments that consider various passenger segments, costs of micro-mobility vehicles, and availability fluctuation of shared mobility.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104286"},"PeriodicalIF":8.3,"publicationDate":"2025-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144663417","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":"Optimization model for large-scale long-term aircraft maintenance scheduling and station assignment","authors":"JohnPaul Adimonyemma, Yanshuo Sun","doi":"10.1016/j.tre.2025.104302","DOIUrl":"10.1016/j.tre.2025.104302","url":null,"abstract":"<div><div>The primary focus of the existing aircraft maintenance optimization literature is on short-term aircraft maintenance routing. By contrast, only a few studies address long-term maintenance planning, which predominantly emphasize scheduling decisions: none of them have examined the critical aspect of assigning aircraft to maintenance stations, a key challenge for major airlines with a network of maintenance facilities. Additional research gaps include (1) insufficient consideration of practical maintenance-related constraints (e.g., station access limit and aircraft rotation requirement) and (2) the absence of scalable algorithms capable of solving real-world problem instances involving hundreds of aircraft and dozens of maintenance stations. To fill those gaps, this study introduces a joint optimization model for aircraft maintenance scheduling and station assignment to assist a U.S.-based airline in creating long-term plans for a fleet of over 800 aircraft of multiple subfleet types. To address the computational challenges, we propose two decomposition approaches: one based on decision types and the other on time horizons. Extensive computational experiments using real-world data from the collaborating airline demonstrate that these approaches can reduce computation time by up to 80% with a minimal increase in the optimization objective (less than 2%). The proposed model is expected to streamline maintenance planning efforts and enhance outcomes for aircraft maintenance professionals.</div></div>","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"202 ","pages":"Article 104302"},"PeriodicalIF":8.3,"publicationDate":"2025-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144653902","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}