Transportation Research Part C-Emerging Technologies最新文献

{"title":"MBSE-Net: multi-view attributed graph model for predicting and evaluating incentive impacts on individual-level behaviour status evolution of multimodal transit users","authors":"Chengcheng Yu ,&nbsp;Yichen Wang ,&nbsp;Wentao Dong ,&nbsp;Haocheng Lin ,&nbsp;Quan Yuan ,&nbsp;Chao Yang","doi":"10.1016/j.trc.2025.105365","DOIUrl":"10.1016/j.trc.2025.105365","url":null,"abstract":"<div><div>Quantifying the incremental effect of incentive strategies on individual Mobility-as-a-Service (Maas) riders’ travel behaviour is vital for developing effective operation policies. Despite the existing effort in rider engagement promotion, the incremental effect is still not quantified clearly since it has not only an immediate impact but also long-term influences on Maas riders’ lifecycle. To address this challenge, this study proposed the MBSE-Net to estimate the incremental effect of incentives in MaaS platforms by designing a dual-channel multi-modal behaviour status evolution path prediction structure, forecasting the evolution paths on counterfactual (incentivised) and factual (non-incentivised) scenarios in coordination. Since the unobservable behaviour dynamics in the counterfactual and factual scenarios in the same rider, this study designed a multi-view attributed graph model in the proposed MBSE-Net to estimate travel behaviour similarities between incentivised and non-incentivised riders for matching to estimate the incremental effect. Our empirical analysis on two kinds of incentive data, i.e., the Weekly-pass discount incentive and the Random post-trip discount incentive, from Shanghai’s Suishenxing MaaS platform has demonstrated that the proposed MBSE-Net achieves high accuracy in identifying status evolution paths and anticipating churn events with an 85.03% churn recall and 80.30% behaviour status evolution path accuracy. Results have revealed that the Weekly-pass discount incentives yield significantly greater uplifts than the random post-trip discount incentives in both short-term (within the incentive week) and long-term (multi-week status evolution path) contexts. Medium-frequency and low-regularity riders exhibit the strongest long-term engagement response to incentives. Moreover, cumulative status evolution path incremental effects (about 0.31) substantially exceed the immediate one-week effects (about 0.10), underscoring the strategic importance of modelling extended behaviour status evolution. This study has further offered actionable view for the MaaS platform based on the findings on targeted and personalised incentive design, showing the benefits of sustained incentive strategies and inventive mixes to improve retention.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105365"},"PeriodicalIF":7.6,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219791","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":"Hybrid method for holistic air traffic demand and capacity balancing optimisation based on sector complexity","authors":"Marc Melgosa ,&nbsp;Andrija Vidosavljevic ,&nbsp;Xavier Prats","doi":"10.1016/j.trc.2025.105306","DOIUrl":"10.1016/j.trc.2025.105306","url":null,"abstract":"<div><div>This paper presents a new hybrid method, based on simulated annealing and dynamic programming, tailored to solve a Demand and Capacity Balancing (DCB) problem that overcomes the limitations of the current Air Traffic Flow and Capacity Management (ATFCM) system by: (a) the introduction of complexity metrics (instead of entry counts) in order to measure the traffic load; (b) the better consideration of the airspace users’ preferences, allowing the possibility of submitting alternative trajectories to avoid congested airspace; and (c) the holistic integration of the demand and capacity management into the same optimisation problem. This new method is compared with the state-of-the-art method for MILP providing better performance principally when the difficulty of the problem increases. Finally, the proposed method is applied to a real-scale scenario, demonstrating its practical applicability in real-world cases.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105306"},"PeriodicalIF":7.6,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219789","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 physics-informed machine learning framework for speed-flow prediction: Integrating an S-shaped traffic stream model with deep learning models","authors":"Feng Shao ,&nbsp;Hu Shao ,&nbsp;Xin Wu ,&nbsp;Qixiu Cheng ,&nbsp;William H.K. Lam","doi":"10.1016/j.trc.2025.105362","DOIUrl":"10.1016/j.trc.2025.105362","url":null,"abstract":"<div><div>In real-world situations, data insufficiency and missingness could significantly compromise the accuracy and reliability of traffic state prediction models. To address the challenge, this study incorporates prior knowledge of the fundamental diagram—which defines the relationship between flow (q) and speed (v)—into a Physics-Informed Machine Learning (PIML) framework to tackle the network-wide speed-flow prediction problem. The PIML model integrates Multi-Graph Convolutional Networks (MGCNs) and Long Short-Term Memory (LSTM) neural networks within a unified Computational Graph (CG) to capture the spatiotemporal dependencies of traffic states across sensor networks. To enhance the interpretability of the learning results, a calibratable S-shaped three-parameter (S3) traffic stream model is embedded into the PIML framework to regulate the relationships between key traffic variables, including speed, density, and flow, ensuring that the estimates and predictions are within a reasonable range satisfying traffic flow theories. The proposed model is validated using data from the Caltrans Performance Measurement System (PeMS), demonstrating superior performance over benchmark models on test datasets and exhibiting stronger generalization capabilities, even with limited data. The inclusion of the S-shaped traffic stream model not only improves predictive performance under conditions of incomplete or sparse data but also ensures inherent consistency with established traffic flow physics. The PIML model is particularly effective for inferring unobservable traffic flow from speed observations, making it a valuable tool for addressing corrupted and missing data points in traffic engineering applications.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105362"},"PeriodicalIF":7.6,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219790","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":"Promoting shared mobility through incentives: Review and prospects","authors":"Rui Guan ,&nbsp;Yaoming Zhou ,&nbsp;Hai Yang","doi":"10.1016/j.trc.2025.105355","DOIUrl":"10.1016/j.trc.2025.105355","url":null,"abstract":"<div><div>The burgeoning field of shared mobility offers a sustainable solution to the challenges of resource inefficiency, traffic congestion, and environmental pollution posed by traditional transportation modes. This paper delves into the strategic use of incentives to influence user behavior and promote the adoption of shared mobility. A comprehensive framework is presented to depict the relationships among stakeholders and the incentives across different market structures. We examine incentives from three dimensions: motivations, forms, and mechanisms, to understand the why, what, and how of implementing incentive strategies. The motivations for implementing incentives are multifaceted, aiming to enhance the attractiveness of shared mobility, improve availability, and optimize resource utilization. The forms of incentives are categorized into monetary and non-monetary types, each with distinct implications for user engagement. The mechanisms of incentives are explored through the characterization of participant behavior and the determination of incentive allocation. Empirical evidence, real-world practices, and implementation challenges are synthesized to provide a critical understanding of incentives in shared mobility. Additionally, potential directions for future research are outlined to guide further exploration in this field. This paper contributes to the development of cost-effective and benefit-maximizing solutions for the shared mobility sector, ultimately supporting its long-term viability and sustainability.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105355"},"PeriodicalIF":7.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219785","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 optimization of capacity expansion timing and increment in airport terminals: addressing stochastic demand and logistic growth","authors":"Ziyue Li ,&nbsp;Qianwen (Vivian) Guo ,&nbsp;Paul Schonfeld","doi":"10.1016/j.trc.2025.105347","DOIUrl":"10.1016/j.trc.2025.105347","url":null,"abstract":"<div><div>Airport terminal capacity expansion planning is important yet challenging due to the stochastic factors inherent in long-term passenger demand growth. Existing studies often assume exponential demand growth, which can oversimplify real-world dynamics. For instance, passenger demand at Phoenix Sky Harbor International Airport (PHX) initially experienced exponential growth, but the demand growth rate has slowed. This trend is more accurately captured by a stochastic logistic growth process. In this paper, we propose a framework that jointly optimizes two related decisions: the expansion timing and the capacity increment, to maximize expected cumulative cost savings under stochastic logistic demand growth. Recognizing that airport authorities hold an “option” to invest in capacity expansion, granting them the right but not the obligation to do so, we adopt a real options approach. Numerical experiments for PHX validate the approach, revealing a congestion effect where added capacity initially reduces congestion and increases cost savings; but as demand approaches the expanded capacity, cost savings decline. Additionally, findings suggest interrelations between variables: a higher demand growth rate correlates with a smaller trigger demand but a larger capacity level, while higher volatility rates result in larger values for both trigger demand and capacity level. Compared to capacity expansion decisions under geometric Brownian motion (GBM) demand modeling, which tends to overestimate future demand growth, our approach better captures long-term saturation effects and provides more realistic results. This methodology can be effectively applied to other capacity expansion planning and investment decision problems in transportation.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105347"},"PeriodicalIF":7.6,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219788","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":"MNT-TNN: spatiotemporal traffic data imputation via compact multimode nonlinear transform-based tensor nuclear norm","authors":"Yihang Lu ,&nbsp;Mahwish Yousaf ,&nbsp;Xianwei Meng ,&nbsp;Enhong Chen","doi":"10.1016/j.trc.2025.105348","DOIUrl":"10.1016/j.trc.2025.105348","url":null,"abstract":"<div><div>Imputation of random or non-random missing data is a long-standing research topic and a crucial application for Intelligent Transportation Systems (ITS). However, with the advent of modern communication technologies such as Global Satellite Navigation Systems (GNSS), traffic data collection has introduced new challenges in random missing value imputation and increasing demands for spatiotemporal dependency modelings. To address these issues, we propose a novel spatiotemporal traffic imputation method based on a Multimode Nonlinear Transformed Tensor Nuclear Norm (MNT-TNN), which can effectively capture the intrinsic multimode spatiotemporal correlations and low-rankness of the traffic tensor, represented as location <span><math><mo>×</mo></math></span> location <span><math><mo>×</mo></math></span> time. To solve the nonconvex optimization problem, we design a proximal alternating minimization (PAM) algorithm with theoretical convergence guarantees. We also suggest an Augmented Transform-based Tensor Nuclear Norm Families (ATTNNs) framework to enhance the imputation results of TTNN techniques, especially at very high miss rates. Extensive experiments on real datasets demonstrate that our proposed MNT-TNN and ATTNNs can outperform the compared state-of-the-art imputation methods, completing the benchmark of random missing traffic value imputation.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105348"},"PeriodicalIF":7.6,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219786","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":"Macro-micro integration of game-theoretic trajectory planning and tactical lane control for mixed traffic control at motorway bottlenecks","authors":"Yuanxiang Yang ,&nbsp;Yu Liu ,&nbsp;Claudio Roncoli","doi":"10.1016/j.trc.2025.105356","DOIUrl":"10.1016/j.trc.2025.105356","url":null,"abstract":"<div><div>This paper presents an integrated approach to mitigate traffic congestion and improve road utilization at motorway bottlenecks in a mixed traffic environment with human-driven vehicles and connected automated vehicles (CAVs). The proposed methodology consists of two essential elements: a tactical lane controller and a game theory-based trajectory planner. The lane controller, based on macroscopic traffic characteristics, proactively redistributes traffic flow into an optimal configuration prior to reaching and activating potential bottlenecks, thereby identifying and directing suitable CAVs to execute lane-changing maneuvers. To achieve this, the (microscopic) trajectory planner anticipates vehicle interactions and quantifies the loss induced by lane-changing maneuvers, feeding this information back to the lane controller. Considering the heterogeneous nature of mixed traffic, game theory models are designed for realistic prediction and assessment. Numerical experiments demonstrate the proposed approach’s effectiveness in reducing traffic congestion and travel delays, considering lane-drop and diverging scenarios. Moreover, results show that the efficacy and robustness improve as the CAV penetration rate increases.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105356"},"PeriodicalIF":7.6,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219787","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":"Unlocking the potential of cooperative staggered shifts in urban networks","authors":"Wenbin Yao ,&nbsp;Xinyi Shen ,&nbsp;Zhengbing He ,&nbsp;Yong Liu ,&nbsp;Xin Yang ,&nbsp;Jiaqi Zeng ,&nbsp;Chunqin Zhang ,&nbsp;Sheng Jin","doi":"10.1016/j.trc.2025.105354","DOIUrl":"10.1016/j.trc.2025.105354","url":null,"abstract":"<div><div>Staggered shifts strategies effectively alleviate traffic pressure and promote the rational allocation of traffic resources by dispersing peak-hour traffic demands. The development of advanced traveler information systems (ATIS) platforms has facilitated the rapid transmission and precise delivery of traffic information. Current studies have combined ATIS platforms with staggered shifts strategies to propose cooperative staggered shifts (CSS) strategies, which can enhance the sophistication of staggered shifts strategies and, consequently, improve their effectiveness. However, current studies on CSS inadequately consider the heterogeneity in the willingness of travelers with different travel behaviors to adjust their departure times. Additionally, existing studies have used traffic state optimization as the sole objective function, without considering system costs. To fill this gap, this study integrates multi-source spatiotemporal big data and survey data to analyze the willingness of travelers with different travel behaviors to adjust their departure times. Based on this analysis, a modeling framework for CSS that considers system costs is constructed. The framework is designed with the dual objectives of optimizing traffic conditions and minimizing system costs. Using the fast-solving algorithm proposed in this study for large-scale scenarios, the Pareto front of the CSS framework is analyzed. Taking Hangzhou city, China as an example, the results indicates that an 11.1% optimization effect on the traffic state can be achieved with only 2.4% of the maximum system cost; As the system cost increases, the marginal benefits of CSS diminish. The research findings can provide effective support for the modeling and policy formulation of CSS strategies.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105354"},"PeriodicalIF":7.6,"publicationDate":"2025-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158024","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":"Hybrid data-model driven trajectory prediction on highways: Integrating anticipatory interaction awareness and personalized driving preferences","authors":"Congcong Bai ,&nbsp;Xi Gao ,&nbsp;Mengdi Chen ,&nbsp;Wentong Guo ,&nbsp;Donglei Rong ,&nbsp;Chengcheng Yang ,&nbsp;Sheng Jin","doi":"10.1016/j.trc.2025.105351","DOIUrl":"10.1016/j.trc.2025.105351","url":null,"abstract":"<div><div>Accurate trajectory prediction of human-driven vehicles (HDVs) in mixed traffic environments is critical for enabling safe and efficient interactions between connected autonomous vehicles (CAVs) and human-driven vehicles on highways. The coexistence of HDVs and CAVs introduces complex dynamics: HDVs exhibit heterogeneous driving preferences influenced by driver behavior patterns, while CAVs’ planned trajectories create anticipatory interactions that reshape HDV motion patterns. Existing methods often overlook the dual challenges of personalized driving preference modelling and anticipatory interaction awareness, particularly in scenarios where CAV trajectories are dynamically integrated into HDV prediction frameworks. To address these challenges, we propose a hybrid data–model driven framework that integrates physics-based behavioral calibration with data-driven interaction modeling. At the core of this framework is the Kepler Optimization-based Temporal Attention Fusion Transformer Network (KO-TAFTN), which enables unified modeling of dynamic historical interactions, anticipatory interactions, and static driving preferences. A driving preference extraction module first derives individualized behavioral traits using Kepler-based physical modeling. These preferences are encoded into context vectors via a static encoder and static enhancement layers, and then incorporated into the network. To improve interpretability and robustness, a variable selection module is applied to evaluate the relevance of input features. A dynamic encoder and a temporal attention fusion module jointly capture and fuse historical and anticipatory interactions by modeling temporal dependencies. Finally, a multimodal trajectory prediction module generates diverse candidate trajectories that reflect potential future motion patterns of HDVs. Experiments demonstrate that the proposed framework consistently outperforms benchmark methods in mixed traffic environments, particularly under complex and congested scenarios. Visualization results further validate the effectiveness of integrating human driving preferences and anticipatory interaction cues. These findings underscore the framework’s potential to improve interaction safety and trajectory accuracy during the transitional evolution of mixed traffic systems.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105351"},"PeriodicalIF":7.6,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145157901","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":"Hypergraph-based motion generation with multi-modal interaction relational reasoning","authors":"Keshu Wu ,&nbsp;Yang Zhou ,&nbsp;Haotian Shi ,&nbsp;Dominique Lord ,&nbsp;Bin Ran ,&nbsp;Xinyue Ye","doi":"10.1016/j.trc.2025.105349","DOIUrl":"10.1016/j.trc.2025.105349","url":null,"abstract":"<div><div>The intricate nature of real-world driving environments, characterized by dynamic and diverse interactions among multiple vehicles and their possible future states, presents considerable challenges in accurately predicting the motion states of vehicles and handling the uncertainty inherent in the predictions. Addressing these challenges requires comprehensive modeling and reasoning to capture the implicit relations among vehicles and the corresponding diverse behaviors. This research introduces an integrated framework for autonomous vehicles (AVs) motion prediction to address these complexities, utilizing a novel <strong>R</strong>elational <strong>H</strong>ypergraph <strong>I</strong>nteraction-informed <strong>N</strong>eural m<strong>O</strong>tion generator (<span>RHINO</span>). <span>RHINO</span> leverages hypergraph-based relational reasoning by integrating a multi-scale hypergraph neural network to model group-wise interactions among multiple vehicles and their multi-modal driving behaviors, thereby enhancing motion prediction accuracy and reliability. Experimental validation using real-world datasets demonstrates the superior performance of this framework in improving predictive accuracy and fostering socially aware automated driving in dynamic traffic scenarios. The source code is publicly available at <span><span>https://github.com/keshuw95/RHINO-Hypergraph-Motion-Generation</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105349"},"PeriodicalIF":7.6,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158023","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}