Transportation Research Part C-Emerging Technologies最新文献

{"title":"Adaptive inference for dynamic passenger route usage patterns in a metro network considering time-varying and heavy-tailed travel times","authors":"Zhuangbin Shi ,&nbsp;Wei Shen ,&nbsp;Paul Schonfeld ,&nbsp;Yang Liu ,&nbsp;Ning Zhang","doi":"10.1016/j.trc.2025.105007","DOIUrl":"10.1016/j.trc.2025.105007","url":null,"abstract":"<div><div>Due to the dynamic changes in timetables, passenger demand, and passenger composition, the distribution of passengers within a metro system becomes quite complex. Many studies divide a day into intervals to account for the dynamics of travel time. However, the intervals used in these studies are insufficient to capture the gradual and fine-grained changes in passenger travel patterns. This study proposes an adaptive dynamic route inference model (ADRIM) that overcomes these limitations. In the ADRIM, we introduce a constrained Expectation Maximization algorithm (CEM) by confining the parameters of the mixture log-normal distribution model (MLND) within confidence intervals, thereby reducing anomalous estimations. We use the concept of Hidden Markov Models (HMMs) to achieve a parameter-adaptive characterization for the dynamics of route choice and travel time distributions for MLND through an iterative process. For a Nanjing metro case study, the proposed model exhibits superior performance in fitting the actual distribution of travel times and accurately captures the dynamic trends in route travel times. Besides, it is revealed that the maximum difference in expected travel times among multiple valid routes for the same origin–destination (OD) pair primarily falls within the interval [5 min, 15 min], and the distribution range of the maximum ratio is mainly between [1.1, 1.6]. The high consistency in passenger route choice proportions observed for two consecutive weeks, along with an analysis of route choice patterns under dynamic conditions, serves as strong evidence supporting the reliability and practical utility of the dynamic route inference model in understanding and managing metro passenger flows.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"171 ","pages":"Article 105007"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096522","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 novel game approach to integrating traffic assignment and signal control for enhanced efficiency and environmental performance in mixed networks","authors":"Hang Yang ,&nbsp;Wanjing Ma ,&nbsp;Rongjun Cheng ,&nbsp;Bing Wu ,&nbsp;Yibing Wang ,&nbsp;Pengjun Zheng","doi":"10.1016/j.trc.2025.105017","DOIUrl":"10.1016/j.trc.2025.105017","url":null,"abstract":"<div><div>The combined traffic assignment and signal control (CAC) has proven to be effective in enhancing the wholistic performance of mixed networks, which includes both expressways and surface streets. This study focuses on addressing the limitations of traditional Stackelberg game-based CAC models, particularly the rigid leader–follower dynamic. We propose an integrated Level-Change-MPC (Model Predictive Control)-VT-Meso-Emission Model (LCMVTM), which incorporates a dynamic role-change function triggered by the compliance rate of users to variable message signs (VMS). This role-change mechanism offers greater flexibility under varying road conditions and simplifies the authority’s task of predicting user routing behavior. Additionally, a Q-learning-based algorithm is developed to balance travel costs and emissions by managing the rate of emission accumulation across control horizons. The results demonstrate a reduction in total travel costs by 11% to over 30%, while emissions decrease by 16.98% to approximately 40% compared to the other different combination of control strategies and MAS/non MAS structured network. The emission accumulation rate also drops by 20% to 43.69%. LCMVTM outperformed the other benchmarks by reducing the number of stop&amp;go per vehicle, resulting in improved efficiency and environmental outcomes.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"171 ","pages":"Article 105017"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096523","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":"Planning charging stations for mixed docked and dockless operations of shared electric micromobility systems","authors":"Yining Liu,&nbsp;Yanfeng Ouyang","doi":"10.1016/j.trc.2024.104989","DOIUrl":"10.1016/j.trc.2024.104989","url":null,"abstract":"<div><div>Dockless electric micro-mobility services (e.g., shared e-scooters and e-bikes) have been increasingly popular in the recent decade, and a variety of charging technologies have emerged for these services. The use of charging stations, to/from which service vehicles are transported by the riders for charging, poses as a promising approach because it reduces the need for dedicated staff or contractors. However, unique challenges also arise, as it introduces docked vehicles at these stations to the existing dockless systems, and now riders can pick up and drop off e-scooters at both random locations and fixed charging stations. This requires incentives for riders to drop off vehicles at the stations and management strategies to efficiently utilize the vehicles at the stations. This paper focuses on such mixed operations of docked and dockless e-scooters as an example. It develops a new aspatial queuing network model for vehicle sharing and charging to capture the steady-state e-scooter service cycles, battery consumption and charging processes, and the associated pricing and management mechanisms in a region with uniform demand. Building upon this model, a system of closed-form equations is formulated and incorporated into a constrained nonlinear program to optimize the deployment of the service fleet, the design of charging stations (i.e., number, location, and capacity), user-based charging price promotions and priorities, and repositioning truck operations (i.e., headway and truck load). The proposed queuing network model is found to match very well with agent-based simulations. It is applied to a series of numerical experiments to draw insights into the optimal designs and the system performance. The numerical results reveal strong advantages of using charging stations for shared dockless electric micro-mobility services as compared to state-of-the-art alternatives. The proposed model can also be used to analyze other micromobility services and other charging approaches.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"171 ","pages":"Article 104989"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust trajectory optimization under arbitrary uncertainty using ensemble weather forecasting and statistical aircraft performance model","authors":"Yoshinori Matsuno,&nbsp;Haruki Matsuda","doi":"10.1016/j.trc.2025.104999","DOIUrl":"10.1016/j.trc.2025.104999","url":null,"abstract":"<div><div>Aircraft trajectory optimization can improve delay absorption and fuel efficiency; however, existing methods suffer from problems such as insufficient adaptability to uncertainty. This paper introduces a robust trajectory optimization algorithm for optimizing flight profiles in the presence of arbitrary uncertainties in weather forecasting and aircraft performance models. Ensemble forecast data are used to provide the uncertainty in the weather forecasts, and a statistical aircraft performance model based on flight data is utilized to provide the uncertainty in the aircraft performance model. Arbitrary polynomial chaos expansion is applied to efficiently quantify arbitrary uncertainties in aircraft dynamics, and incorporated into the trajectory optimization algorithm. The <span><math><mi>β</mi></math></span>-hill climbing algorithm, a stochastic local search algorithm developed recently, is employed to determine the optimal flight profiles. By conducting numerical simulations on a popular domestic flight route in Japan during time-based metering operations, this study assesses potential fuel savings by the optimal trajectories with speed control and step descent along the planned route, as opposed to radar vectoring. Actual flight data from past flights are utilized for evaluation, and average fuel savings of approximately 2% are expected. Based on the analysis conducted in this study, the effectiveness of the robust trajectory optimization algorithm and fuel savings for time-based metering operations are evaluated and demonstrated.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"171 ","pages":"Article 104999"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Incorporating domain knowledge in deep neural networks for discrete choice models","authors":"Shadi Haj-Yahia,&nbsp;Omar Mansour,&nbsp;Tomer Toledo","doi":"10.1016/j.trc.2025.105014","DOIUrl":"10.1016/j.trc.2025.105014","url":null,"abstract":"<div><div>This paper explores the integration of domain knowledge into deep neural network (DNN) models to support the interpretability of travel demand predictions in the context of discrete choice models (DCMs). Traditional DCMs, formed as random utility models (RUM), are widely employed in travel demand analysis as a powerful theoretical econometric framework. But, they are often limited by subjective and simplified utility function specifications, which may not capture complex behaviors. This led to a growing interest in data-driven approaches. Due to their flexible architecture, DNNs offer a promising alternative for learning unobserved non-linear relationships in DCMs. But they are often criticized for their “black box” nature and potential deviations from established economic theory.</div><div>This paper proposes a framework that incorporates domain knowledge constraints into DNNs, guiding the models toward behaviorally realistic outcomes while retaining predictive flexibility. The framework’s effectiveness is demonstrated through a synthetic dataset and an empirical study using the Swissmetro dataset. The synthetic study confirms that domain knowledge constraints enhance consistency and economic plausibility, while the Swissmetro application shows that constrained models avoid implausible outcomes, such as negative values of time, and provide stable market share predictions. The proposed approach is independent of the model structure, making it applicable on different model architectures. The methodology was applied on both standard DNN and an alternative-specific utility DNN (ASU-DNN). Although constrained models exhibit a slight reduction in predictive fit, they generalize better to unseen data and produce interpretable results. This study offers a pathway for combining the flexibility of machine learning with domain expertise for DCMs, across diverse model architectures and datasets.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"171 ","pages":"Article 105014"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A data-driven approach for determining airport declared capacity","authors":"Ziming Wang ,&nbsp;Yanjun Wang ,&nbsp;Weishan Xu ,&nbsp;Hai Wang ,&nbsp;Fangzi Liu","doi":"10.1016/j.trc.2025.105012","DOIUrl":"10.1016/j.trc.2025.105012","url":null,"abstract":"<div><div>Slot-control policies have been widely implemented in congested airports worldwide to manage air transportation demand and airport capacity. These airports, known as slot-coordinated airports or Level 3 airports, provide a certain number of airport slots to airlines. The number of slots in a given time period — for example, 15 min or 1 h — is generally referred to as declared capacity. Only those airlines that obtain airport slots can schedule regular flights at the given airport for the next summer or winter season. Much effort has been made to optimize allocation schemes for the slot coordinator, such that airport slots are distributed to airlines efficiently and effectively. However, few attempts have been made to determine optimal airport declared capacity, mainly because of two challenges. First, the stochastic nature of airport operations due to uncertainty. Second, the unclear relationship between the economic benefits gained by scheduled flights and the possible cost induced by congestion or lost revenue due to unused airport capacity. This paper presents a novel approach for determining airport declared capacity. First, we present a K-medoids-DTW method to cluster airport capacity scenarios and a step-queuing pricing mechanism based on the zero-queuing pricing model to quantify the cost of operations in different time periods of the day. A two-stage stochastic programming model is then developed to determine the number of slots at the airport. A busy international Level 3 airport in Asia is used as a case study to demonstrate the applicability of this model. Our results highlight the advantages of the step-queuing pricing model (SPM) compared with the uniform pricing model (UPM). The SPM allows more slots to be created. Our method can be a useful tool for airport authorities or other related aviation authorities seeking to assign the optimal number of slots at different levels of service.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"171 ","pages":"Article 105012"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096520","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":"Freeway real-time crash prediction using floating car data","authors":"Yifan Wang ,&nbsp;Xuesong Wang ,&nbsp;Tonggen Wang ,&nbsp;Mohammed Quddus","doi":"10.1016/j.trc.2025.105009","DOIUrl":"10.1016/j.trc.2025.105009","url":null,"abstract":"<div><div>The likelihood of traffic crashes is significantly affected by the short-term turbulence of traffic flow, a common phenomenon on freeways due to high traffic volume and speed. Real-time traffic safety models have the potential to capture this variation in traffic flow to predict crashes reliably, but data collection methods used in previous studies cannot effectively reflect the necessary spatio-temporal traffic dynamics. Floating car data (FCD), utilizing the kinematics information collected by multiple single vehicles, provides a way to acquire this information on traffic flow before crashes occur. This study aims to develop a real-time crash prediction model based on FCD from the Jiading-Jinshan and Outer Ring Freeways in Shanghai, China. A map matching technique is employed for freeway FCD without heading direction. Both dynamic and static features are constructed, and the variations of dynamic features before the crash are analyzed. The non-parameter tests (Mann–Whitney U and Fligner–Killeen tests) are applied to identify the heterogeneity between crash and non-crash cases. The bidirectional long short-term memory network (LSTM) with a multi-head attention mechanism combined with dynamic and static features is built and showed the best performance. Different histogram-based threshold selection methods are compared. The trained model is applied to all the data for validation, and the matched case-control technique can well predict crashes in this study. The main findings are: (1) the multi-head attention and bidirectional mechanisms can significantly improve model performance, while the static features combination is not as effective; (2) volume is the most important dynamic feature, then is the speed standard deviation followed by the average speed. This model can be applied in providing alerts to drivers and evaluating real-time intervention measures.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"171 ","pages":"Article 105009"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143135753","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 choice-based optimization approach for service operations in multimodal mobility systems","authors":"Haoye Chen ,&nbsp;Jan Kronqvist ,&nbsp;Zhenliang Ma","doi":"10.1016/j.trc.2024.104954","DOIUrl":"10.1016/j.trc.2024.104954","url":null,"abstract":"<div><div>Multimodal mobility systems provide seamless travel by integrating different types of transportation modes. Most existing studies model service operations and users’ travel choices independently or iteratively and constrained with pre-defined multimodal travel options. The paper proposes a choice-based optimization approach that optimizes service operations with explicitly embedded travelers’ choices described by the multinomial logit (MNL) model. It allows the flexible combination of travel modes and routes in multimodal mobility systems. We propose a computationally efficient linearization method for transformed MNL constraints with bounded errors to solve the choice-based optimization model. The model is validated using a mobility on demand and public transport network by comparing it with a simulation sampling-based MNL linearization method. The results show that the mixed-integer formulation provides a high-quality solution in terms of both the estimated choice probability errors and computational speed. We also conduct an error analysis and a sensitivity analysis to explore the behavior of the proposed approach. The real-world case study in Stockholm further illustrates that the analytical formulation achieves a better system operation performance than the traditional iterative supply–demand updating optimization method. The choice-based optimization model and solution formulation are highly adaptable for operations decision support integrating stochastic travel choices in multimodal mobility systems.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"171 ","pages":"Article 104954"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143135755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The VCG pricing policy with unit reserve prices for ride-sourcing is 34-individual compatibility","authors":"Ruijie Li ,&nbsp;Haiyuan Chen ,&nbsp;Xiaobo Liu ,&nbsp;Kenan Zhang","doi":"10.1016/j.trc.2024.104991","DOIUrl":"10.1016/j.trc.2024.104991","url":null,"abstract":"<div><div>We consider a customized matching and pricing mechanism for ride-sourcing services in which drivers and riders disclose their willingness to accept (WTA) per unit distance and their willingness to pay (WTP) per unit distance, respectively. The platform then matches drivers and riders based on their reports to maximize the total social surplus. While this strategy is motivated to promote transparency, fair pricing, and participant satisfaction, it faces a particular challenge to ensure riders and drivers truthfully report their valuations, which are considered private information. To encourage truthful reports, we implement the Vickrey–Clarke–Groves pricing policy augmented with unit reserve prices, referred to as VCG-URP. For the riders, the reserve price is set as the minimum WTP per unit distance, while for the drivers, it is the maximum WTA per unit distance. We demonstrate that VCG-URP ensures that riders provide truthful valuations. However, it does not guarantee the same level of honesty from drivers in reporting their valuations. While drivers cannot enhance their utility by overstating their unit WTA, they may benefit from understating it. These theoretical results are confirmed by numerical experiments with several additional findings: (i) although the under-reporting strategy of the drivers theoretically has an opportunity to achieve a higher utility, it always leads to a decrease in expected utility over randomly generated matching scenarios; (ii) the introduction of reserve prices has larger impacts on riders than drivers and benefits the platform in excluding less profitable trips; and (iii) the performance of VCG-URP is reasonably robust towards the market density, while the VCG price is less applied when the market becomes sparse, mainly due to the loss of substitutability among participants. All these findings bring valuable insights into ride-sourcing services in practice.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"171 ","pages":"Article 104991"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mitigating cascading effects of vehicle lane changes: A hyperedge game approach","authors":"Yunfei Li,&nbsp;Dongyu Luo,&nbsp;Jiangfeng Wang,&nbsp;Weidong Ding,&nbsp;Yuchao Song","doi":"10.1016/j.trc.2024.104971","DOIUrl":"10.1016/j.trc.2024.104971","url":null,"abstract":"<div><div>The lane-changing behavior of Connected and Automated vehicles (CAVs) exemplifies a collective interoperability phenomenon in which the lane change of a target vehicle prompts collaborative responses from neighboring vehicles, resulting in traffic oscillations throughout the transportation network, commonly referred to as cascading effects. To accurately characterize and mitigate these cascading effects during the collaborative lane-changing process of CAVs, we propose an Intentional Hyperedge Game Model (IHGM) grounded in hypergraph theory. The model consists of three critical modes: gap sorting, the intention boundary, and the hyperedge game. First, gap sorting prioritizes the order of gap selection for the target vehicle by assessing the benefits. Second, the intention boundary delineates the safety constraints associated with lane changes, integrating the lane change intentions of the target vehicle with the driving statuses of neighboring vehicles. Finally, the hyperedge game effectively simulates the cascading effects generated by CAVs throughout the lane-changing process. The traffic flow data of Beijing’s Second Ring Road, which were collected in 2019 for a period of seven days, were used as inputs in our case study. The results show that the IHGM significantly reduces the cascading effects and improves the lane-changing success rate by approximately 10 % in high-density scenarios, ensuring safety and comfort. The lane-changing success rate is related to the Lane-changing Position (LP), which is the distance between the target vehicle and the no lane-changing area. When the LP is 50 m, the probability of identifying a feasible path for the target vehicle exceeds 30 %, and the lane-changing success rate is 100 % when there is a feasible path. Furthermore, when the first three lane-changing target gaps are evaluated, the model effectively solves more than 92 % of the actual lane-changing scenarios and greatly reduces the impact of cascading effects. The model meets the lane-changing requirements in 98 % of the cases in which the first four gaps are evaluated.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"171 ","pages":"Article 104971"},"PeriodicalIF":7.6,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143096043","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}