Communications in Transportation Research最新文献

{"title":"On the stochastic fundamental diagram: A general micro-macroscopic traffic flow modeling framework","authors":"Xiaohui Zhang,&nbsp;Jie Sun,&nbsp;Jian Sun","doi":"10.1016/j.commtr.2025.100163","DOIUrl":"10.1016/j.commtr.2025.100163","url":null,"abstract":"<div><div>The stochastic fundamental diagram (SFD), which describes the stochasticity of the macroscopic relations of traffic flow, plays a crucial role in understanding the uncertainty of traffic flow evolution and developing robust traffic control strategies. Although many efforts have been made to reproduce the SFD via various methods, few studies have focused on the analytical modeling of the SFD, particularly linking the macroscopic relations with microscopic behaviors. This study fills this gap by proposing a general micro-macroscopic modeling approach, which uses probabilistic leader–follower behavior to derive the macroscopic relations of a platoon and is referred to as the leader–follower conditional distribution-based stochastic traffic modeling (LFCD-STM) framework. Specifically, we first define a conditional probability distribution of speed for the leader‒follower pair according to Brownian dynamics, which is proven to be a general representation of the longitudinal interaction and compatible with classical car-following models. As a result, we can describe the joint distribution of vehicle speeds of the platoon through Markov chain modeling and further derive the macroscopic relations (e.g., the mean flow‒density relation and its variance) under equilibrium conditions. On the basis of this general micro-macroscopic framework, we utilize the maximum entropy approach to theoretically derive the SFD model, in which we provide a specific conditional distribution for longitudinal interaction and thus solve the analytical functions of the mean and variance of FD. The performance of the maximum entropy-based SFD model is thoroughly validated with the NGSIM I-80, US-101 and HighD datasets. The high consistency between the theoretical results and empirical results demonstrates the soundness of the LFCD-STM framework and the maximum entropy-based SFD model. Finally, the proposed SFD model has practical implications for promoting smoother driving behaviors to suppress stochasticity and improve traffic flow.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100163"},"PeriodicalIF":12.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143394682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Urban visual clusters and road transport fatalities: A global city-level image analysis","authors":"Zhuangyuan Fan,&nbsp;Becky P.Y. Loo","doi":"10.1016/j.commtr.2025.100193","DOIUrl":"10.1016/j.commtr.2025.100193","url":null,"abstract":"<div><div>Road traffic crashes are among the leading causes of death and injury worldwide. While urban planning and design are known to influence road safety, it is not clear how features of the built environment contribute to traffic fatalities. In this study, we analyze road fatality data from 106 cities across six continents via a combination of computer vision and unsupervised clustering on 26.8 million Google Street View images. We use deep learning tools to extract 25 features from the images. Among these features, 19 are relatively static built environment features, and 6 are dynamic usage-related features (such as pedestrians, cars, buses, and bikes). On the basis of the built environment features, we group the urban streetscapes into six distinct visual clusters. We then examine how these clusters are related to city-level road fatality rates when various control variables (e.g., population size, carbon emissions, income, road length, road safety policy, and continent) and dynamic features are combined. Our findings show that cities with Open Arterials streetscape (extensive road surface, open-sky views, and railings) tend to have higher road fatality rates. After accounting for differences in the built environment, cities with better public transit (proxied by buses detected) tend to have fewer traffic deaths—specifically, a 1% increase in bus presence is linked to a 0.35% decrease in fatalities per 100,000 people. This study demonstrates the power of using widely available street view imagery to uncover global disparities in urban design and their connection to road safety.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100193"},"PeriodicalIF":12.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144535777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"From global open multi-source data to network-wide traffic flow: A large-scale case study across multiple cities","authors":"Zijian Hu ,&nbsp;Zhenjie Zheng ,&nbsp;Monica Menendez ,&nbsp;Wei Ma","doi":"10.1016/j.commtr.2025.100222","DOIUrl":"10.1016/j.commtr.2025.100222","url":null,"abstract":"<div><div>Network-wide traffic flow, which captures dynamic traffic volume on each link of a general network, is fundamental to smart mobility applications. However, the observed traffic flow from sensors is usually limited across the entire network due to the associated high installation and maintenance costs. To address this issue, existing research uses various supplementary data sources to compensate for insufficient sensor coverage and estimate the unobserved traffic flow. Although these studies have shown promising results, the inconsistent availability and quality of supplementary data across cities make their methods typically face a trade-off challenge between accuracy and generality. In this research, we first advocate using the global open multi-source (GOMS) data within an advanced deep learning framework to break the trade-off. The GOMS data mainly refers to publicly available multi-type datasets, including road topology, building footprints, and population density, which can be consistently collected across cities. More importantly, these GOMS data are closely related to the traffic flow dynamics, thereby creating opportunities for accurate network-wide flow estimation. Furthermore, we use map images to represent GOMS data, instead of traditional tabular formats, to capture richer and more comprehensive geographical and demographic information. To address multi-source data fusion, we develop an attention-based graph neural network that effectively extracts and synthesizes information from GOMS maps while simultaneously capturing spatiotemporal traffic dynamics from observed traffic data. A large-scale case study across 15 cities in Europe and North America was conducted. The results demonstrate stable and satisfactory estimation accuracy across these cities, which suggests that the trade-off challenge can be successfully addressed using our approach.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100222"},"PeriodicalIF":14.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145571111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhanced trajectory reconstruction from sparse and noisy GPS data: A progressive chunked transformer approach","authors":"Yonghui Liu ,&nbsp;Qian Li ,&nbsp;Inhi Kim","doi":"10.1016/j.commtr.2025.100200","DOIUrl":"10.1016/j.commtr.2025.100200","url":null,"abstract":"<div><div>Trajectory reconstruction from sparse and noisy GPS data is critical for applications such as urban mobility analysis, transportation planning, and navigation systems. However, large sampling intervals and the typically long output sequences required to reconstruct coherent travel trajectories significantly increase computational complexity, particularly in the presence of noise. To address these challenges, we propose a progressive chunked transformer (ProChunkFormer), which is a deep learning method for trajectory reconstruction that employs self-attention mechanisms and chunked processing to balance efficiency with accuracy. ProChunkFormer first generates intermediate trajectories at a semi-high frequency from low-frequency sampled data, and then the remaining trajectory is divided into manageable blocks and reconstructed parallelly in the condition of the semi-high-frequency trajectory. By combining progressive reconstruction with chunk processing, ProChunkFormer not only mitigates the cumulative errors commonly observed in autoregressive models but also alleviates the rapid increase in complexity associated with reconstructing ultralong trajectories. Specifically, our approach achieves quadratic optimization in time and space for attention modules, with cubic time savings compared with autoregressive decoding. A case study using an open-source taxi trajectory dataset confirms the effectiveness of our approach. The performance of ProChunkFormer is comparable to that of autoregressive transformers while offering better running efficiency. It improves the accuracy, F1 score (F1), mean absolute error (MAE), and road network mean absolute error (MAE_RN) by 23.1%, 18.6%, 22.3%, and 25.1%, respectively, for trajectories with a long interval time of up to 240 ​s. Furthermore, we investigate incorporating heuristic information to guide trajectory reconstruction for each block. The experimental results indicate an improvement in both the overall performance and convergence speed of the model.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100200"},"PeriodicalIF":14.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144757300","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Situational awareness using set-based estimation and vehicular communication: An occluded pedestrian-crossing scenario","authors":"Vandana Narri ,&nbsp;Amr Alanwar ,&nbsp;Jonas Mårtensson ,&nbsp;Henrik Pettersson ,&nbsp;Fredrik Nordin ,&nbsp;Karl Henrik Johansson","doi":"10.1016/j.commtr.2025.100190","DOIUrl":"10.1016/j.commtr.2025.100190","url":null,"abstract":"<div><div>The safety of unprotected road-users is crucial in any urban traffic. Occlusions and blind spots in the field-of-view of a vehicle can lead to unsafe situations. In this work, a specific pedestrian-crossing scenario is considered with an occlusion in the ego-vehicle's field-of-view. A novel framework is presented to enhance situational awareness based on vehicle-to-everything (V2X) communication to share perception data between vehicle and roadside units. It leverages set-based estimation utilizing a computationally efficient algorithm, for which the pedestrian is guaranteed to be located in a constrained zonotope. The proposed method has been validated through both simulation and real experiments. The real experiments are carried out on a test track using Scania autonomous vehicles.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100190"},"PeriodicalIF":12.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144254007","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Customized recursive model for drivers’ navigation compliance behaviors under abnormal events","authors":"Kaijie Zou,&nbsp;Yaming Guo,&nbsp;Ke Zhang,&nbsp;Meng Li","doi":"10.1016/j.commtr.2025.100187","DOIUrl":"10.1016/j.commtr.2025.100187","url":null,"abstract":"<div><div>In recent years, the resilience of road traffic during abnormal events has drawn considerable attention. Intelligent navigation systems, which proactively guide drivers along optimal routes in such situations, are viewed as a promising solution to facilitate recovery of road network performance. A key question arises: How do drivers choose routes when guided by navigation systems? This study addresses that question by modeling drivers’ decision-making behavior at each decision point using a nested framework. At the upper level, drivers decide whether to strictly follow the route recommended by the navigation system, while at the lower levels, they make route choices in the absence of guidance. A Customized Nested Dynamic Recursive Logit (C-NDRL) model was developed to capture these behaviors. Parameters for both decision levels were jointly estimated using a Broyden-Fletcher-Goldfarb-Shanno (BFGS) ​Method-based algorithm, and the model was verified on the Sioux-Falls network. The model was then applied to real navigation route and driving trajectory data from Canton, China, for parameter estimation and the analysis of the additional utility provided by navigation. The results indicate that the C-NDRL model significantly outperformed other models. Furthermore, the study quantifies the substantial impact of external environmental factors and navigation-related internal factors on drivers’ compliance on navigation systems, highlighting that during rainstorm days, the additional utility from navigation increases by 17%.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100187"},"PeriodicalIF":12.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144364486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A causality-based explainable AI method for bus delay propagation analysis","authors":"Qi Zhang ,&nbsp;Zhenliang Ma ,&nbsp;Zhiyong Cui","doi":"10.1016/j.commtr.2025.100178","DOIUrl":"10.1016/j.commtr.2025.100178","url":null,"abstract":"<div><div>Public transportation networks are highly interconnected, where disruptions like traffic congestion propagate bus delays and impact performance. Identifying delay causes is crucial, yet most studies rely on correlation-based methods rather than causal analysis. Attribution methods like the Shapley value quantify factor contributions but often overlook causal dependencies, leading to potential bias. This study uses a causal discovery model to uncover causal relationships between bus delays and various factors (e.g., operational factors, calendar, and weather). Based on this causal graph, an explainable Artificial Intelligence (AI) method quantifies each factor's contribution to delays, focusing on how these contributions vary at different stops along a route. By integrating scheduled route data and real-time vehicle locations, we analyze factor contributions over time and space, exploring various scenarios along the route. Cross-validation is conducted by comparing the importance ranking of factors with the Seemingly Unrelated Regression Equations (SURE). Results show significant variations in factors contributing to delays along the route. Delays at upstream stops propagate downstream, indicating a cascading effect. Operational factors dominate, accounting for 50%–83% of delays. Notably, delays from the preceding two to three stops have a larger impact than just the immediately preceding one stop, and origin delays strongly affect the first half of the route.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100178"},"PeriodicalIF":12.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating micro and macro traffic control for mixed autonomy traffic","authors":"Tingting Fan ,&nbsp;Jieming Chen ,&nbsp;Edward Chung","doi":"10.1016/j.commtr.2025.100188","DOIUrl":"10.1016/j.commtr.2025.100188","url":null,"abstract":"<div><div>During the transition to fully autonomous traffic systems, managing mixed traffic consisting of connected automated vehicles (CAVs) and human-driven vehicles (HDVs) is imperative. Existing macroscopic and microscopic strategies have shown effectiveness in alleviating highway congestion. However, the integration of these strategies for mixed autonomy traffic remains under-explored. This study proposes a hybrid flow and trajectory control (HFTC) strategy that combines a macroscopic control, ramp metering (RM), with a microscopic control, cooperative merging (CM) for CAV trajectory optimization in mixed traffic scenarios. Specifically, the RM control considers CAV-penetration-dependent dynamics to regulate ramp flow, and the CM utilizes a centralized optimization model to enhance CAV merging trajectories. Independently implementing RM or CM proved effective only under heavy or moderate traffic flow, whereas our proposed integrated strategy, HFTC, demonstrated greater adaptability and suitability under various traffic conditions. Additionally, the impacts of CAV penetration rates and traffic flows on performance of different control strategies are thoroughly explored. Simulation results indicate that under low and moderate traffic conditions, microscopic control can be comparable to macroscopic control given sufficient CAV integration, while under heavy traffic flows, macroscopic control cannot be replaced by microscopic control.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100188"},"PeriodicalIF":12.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144243257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A knowledge-informed deep learning paradigm for generaliz-able and stability-optimized car-following models","authors":"Chengming Wang ,&nbsp;Dongyao Jia ,&nbsp;Wei Wang ,&nbsp;Dong Ngoduy ,&nbsp;Bei Peng ,&nbsp;Jianping Wang","doi":"10.1016/j.commtr.2025.100211","DOIUrl":"10.1016/j.commtr.2025.100211","url":null,"abstract":"<div><div>Car-following models (CFMs) are fundamental to traffic flow analysis and autonomous driving. Although calibrated physics-based and trained data-driven CFMs can replicate human driving behavior, their reliance on specific datasets limits generalization across diverse scenarios and reduces reliability in real-world deployment. In addition to behavioral fidelity, ensuring traffic stability is increasingly critical for the safe and efficient operation of autonomous vehicles (AVs), requiring CFMs that jointly address both objectives. However, existing models generally do not support a systematic integration of these goals. To bridge this gap, we propose a knowledge-informed deep learning (KIDL) paradigm that distills the generalization capabilities of pre-trained large language models (LLMs) into a lightweight and stability-aware neural architecture. LLMs are used to extract fundamental car-following knowledge beyond dataset-specific patterns, and this knowledge is transferred to a reliable, tractable, and computationally efficient model through knowledge distillation. KIDL also incorporates stability constraints directly into its training objective, ensuring that the resulting model not only emulates human-like behavior but also satisfies the local and string stability requirements essential for real-world AV deployment. We evaluate KIDL on the real-world NGSIM and HighD datasets, comparing its performance with representative physics-based, data-driven, and hybrid CFMs. Both empirical and theoretical results consistently demonstrate KIDL’s superior behavioral generalization and traffic flow stability, offering a robust and scalable solution for next-generation traffic systems.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100211"},"PeriodicalIF":14.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MetaSSC: Enhancing 3D semantic scene completion for autonomous driving through meta-learning and long-sequence modeling","authors":"Yansong Qu ,&nbsp;Zixuan Xu ,&nbsp;Zilin Huang ,&nbsp;Zihao Sheng ,&nbsp;Sikai Chen ,&nbsp;Tiantian Chen","doi":"10.1016/j.commtr.2025.100184","DOIUrl":"10.1016/j.commtr.2025.100184","url":null,"abstract":"<div><div>Semantic scene completion (SSC) plays a pivotal role in achieving comprehensive perceptions of autonomous driving systems. However, existing methods often neglect the high deployment costs of SSC in real-world applications, and traditional architectures such as three-dimensional (3D) convolutional neural networks (3D CNNs) and self-attention mechanisms struggle to efficiently capture long-range dependencies within 3D voxel grids, limiting their effectiveness. To address these challenges, we propose MetaSSC, a novel meta-learning-based framework for SSC that leverages deformable convolution, large-kernel attention, and the Mamba (D-LKA-M) model. Our approach begins with a voxel-based semantic segmentation (SS) pretraining task, which is designed to explore the semantics and geometry of incomplete regions while acquiring transferable meta-knowledge. Using simulated cooperative perception datasets, we supervise the training of a single vehicle's perception via the aggregated sensor data from multiple nearby connected autonomous vehicles (CAVs), generating richer and more comprehensive labels. This meta-knowledge is then adapted to the target domain through a dual-phase training strategy—without adding extra model parameters—ensuring efficient deployment. To further enhance the model's ability to capture long-sequence relationships in 3D voxel grids, we integrate Mamba blocks with deformable convolution and large-kernel attention into the backbone network. Extensive experiments show that MetaSSC achieves state-of-the-art performance, surpassing competing models by a significant margin while also reducing deployment costs.</div></div>","PeriodicalId":100292,"journal":{"name":"Communications in Transportation Research","volume":"5 ","pages":"Article 100184"},"PeriodicalIF":12.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144154446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}