Transportation Research Interdisciplinary Perspectives最新文献_第10页

Policy-driven life-cycle emissions and climate resilience of highway pavements: an LCA-optimization and scenario analysis 政策驱动的公路路面全生命周期排放与气候适应能力：lca优化与情景分析

IF 3.8 Q2 TRANSPORTATION

Transportation Research Interdisciplinary Perspectives

Pub Date : 2026-03-01 Epub Date: 2026-01-06 DOI: 10.1016/j.trip.2025.101811

Musab Abuaddous , Odey Alshboul , Ali Shehadeh

This study quantifies the environmental and economic implications of highway pavement construction and management in Jordan’s arid and semi-arid regions and evaluates policy-relevant adaptation pathways for 2025–2065, linking pavement engineering decisions to transportation-system sustainability and reliability. We couple a process-based life-cycle assessment (LCA) with a climate-driven deterioration–maintenance optimization model using projected stressors (+2.3 °C mean warming, +20 % extreme-heat days >40 °C, and higher rainfall variability). Under Business-as-Usual (BAU), phase contributions to total life-cycle emissions are: raw materials 45 %, construction 30 %, transport 15 %, maintenance 7 %, and end-of-life 3 %. Baseline emissions equal ∼300 tCO₂e km⁻¹ (asphalt) and ∼180 tCO₂e km⁻¹ (concrete). Optimization reduces emissions to ∼225 tCO₂e km⁻¹ (–25 %) and ∼150 tCO₂e km⁻¹ (–17 %), while lowering life-cycle costs by 22 % (asphalt) and 18 % (concrete). Policy packages amplify benefits: a Moderate Sustainability pathway reduces emissions by ∼20 % versus BAU, while a High Sustainability pathway achieves >40 % reduction and yields an 18 % net cost saving over 40 years despite 15–25 % higher upfront costs. Climate stress increases damage rates (asphalt 0.015 → 0.019 y⁻¹; concrete 0.008 → 0.011 y⁻¹), raising thermal cracking by 18 % and moisture-driven rutting by 15 %. Spatially, emissions are lowest in the Jordan Valley and highest in the Northern Highlands/Eastern Desert due to terrain and haul distances. Findings translate into actionable transport-policy levers—performance-grade upgrades, minimum recycled-content mandates, broad warm-mix adoption, and regionalized specifications—supporting lower-carbon, more climate-resilient networks with an estimated ≈30 % resilience/structural integrity gain under fiscally viable investment strategies.

本研究量化了约旦干旱和半干旱地区公路路面建设和管理的环境和经济影响，并评估了2025-2065年政策相关的适应途径，将路面工程决策与交通系统的可持续性和可靠性联系起来。我们将基于过程的生命周期评估（LCA）与气候驱动的退化维护优化模型结合起来，该模型使用了预测的压力源（平均升温+2.3°C，极端高温天数+ 20% >；40°C，以及更高的降雨量变异性）。在“一切照旧”（BAU）模式下，各个阶段对整个生命周期排放的贡献如下：原材料占45%，建筑占30%，运输占15%，维护占7%，生命周期结束占3%。基线排放量等于（沥青）约300吨二氧化碳当量公里−1，（混凝土）约180吨二氧化碳当量公里−1。优化后的排放量分别减少至~ 225吨二氧化碳当量km - 1（- 25%）和~ 150吨二氧化碳当量km - 1(- 17%)，同时生命周期成本分别降低22%（沥青）和18%（混凝土）。一揽子政策可扩大效益：与BAU相比，中等可持续性途径可减少约20%的排放量，而高可持续性途径可减少40%的排放量，并在40年内节省18%的净成本，尽管前期成本高出15 - 25%。气候应力增加了损伤率（沥青0.015→0.019 y - 1；混凝土0.008→0.011 y - 1），使热裂率增加18%，水分导致车辙率增加15%。在空间上，由于地形和运输距离的原因，约旦河谷的排放量最低，北部高地/东部沙漠的排放量最高。研究结果转化为可操作的交通政策杠杆——性能等级升级、最低再循环含量规定、广泛采用暖混合燃料和区区化规范——支持低碳、更具气候适应性的交通网络，在财政上可行的投资策略下，预计可获得约30%的弹性/结构完整性增益。

{"title":"Policy-driven life-cycle emissions and climate resilience of highway pavements: an LCA-optimization and scenario analysis","authors":"Musab Abuaddous , Odey Alshboul , Ali Shehadeh","doi":"10.1016/j.trip.2025.101811","DOIUrl":"10.1016/j.trip.2025.101811","url":null,"abstract":"<div><div>This study quantifies the environmental and economic implications of highway pavement construction and management in Jordan’s arid and semi-arid regions and evaluates policy-relevant adaptation pathways for 2025–2065, linking pavement engineering decisions to transportation-system sustainability and reliability. We couple a process-based life-cycle assessment (LCA) with a climate-driven deterioration–maintenance optimization model using projected stressors (+2.3 °C mean warming, +20 % extreme-heat days >40 °C, and higher rainfall variability). Under Business-as-Usual (BAU), phase contributions to total life-cycle emissions are: raw materials 45 %, construction 30 %, transport 15 %, maintenance 7 %, and end-of-life 3 %. Baseline emissions equal ∼300 tCO<sub>2</sub>e km<sup>−1</sup> (asphalt) and ∼180 tCO<sub>2</sub>e km<sup>−1</sup> (concrete). Optimization reduces emissions to ∼225 tCO<sub>2</sub>e km<sup>−1</sup> (–25 %) and ∼150 tCO<sub>2</sub>e km<sup>−1</sup> (–17 %), while lowering life-cycle costs by 22 % (asphalt) and 18 % (concrete). Policy packages amplify benefits: a Moderate Sustainability pathway reduces emissions by ∼20 % versus BAU, while a High Sustainability pathway achieves >40 % reduction and yields an 18 % net cost saving over 40 years despite 15–25 % higher upfront costs. Climate stress increases damage rates (asphalt 0.015 → 0.019 y<sup>−1</sup>; concrete 0.008 → 0.011 y<sup>−1</sup>), raising thermal cracking by 18 % and moisture-driven rutting by 15 %. Spatially, emissions are lowest in the Jordan Valley and highest in the Northern Highlands/Eastern Desert due to terrain and haul distances. Findings translate into actionable transport-policy levers—performance-grade upgrades, minimum recycled-content mandates, broad warm-mix adoption, and regionalized specifications—supporting lower-carbon, more climate-resilient networks with an estimated ≈30 % resilience/structural integrity gain under fiscally viable investment strategies.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"36 ","pages":"Article 101811"},"PeriodicalIF":3.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145897911","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}

引用次数: 0

Unveiling emerging communities: a network approach on transport decarbonisation technology 揭示新兴社区：交通脱碳技术的网络方法

IF 3.8 Q2 TRANSPORTATION

Transportation Research Interdisciplinary Perspectives

Pub Date : 2026-03-01 Epub Date: 2026-01-17 DOI: 10.1016/j.trip.2025.101833

Joao Tiago Aparicio , Elisabete Arsenio , Rui Henriques

What are the latent thematic communities driving transport decarbonisation research across road, rail, maritime, and crossmodal domains? To answer this central question, this work proposes an integrated network model that fuses bibliographic coupling with Sentence-BERT semantic similarities, followed by a statistical analysis using state-of-the-art community detection algorithms. We assess partitions via four complementary metrics, modularity, silhouette, density, and NF1, and compare weighted versus unweighted graphs. Our analysis of mode-specific corpora uncovers distinct clusters: road research splits into urban last-mile automation and rural logistics; rail coalesces around a synchromodal scheduling hub with biofuel and corridor electrification offshoots; maritime divides into green fuels, autonomous safety, and shore-power streams; and crossmodal studies form overlapping triads of electrification, data analytics, and blockchain. Weighted edge integration uniformly enhances thematic clarity without altering algorithm rankings. These findings yield actionable algorithm-selection heuristics and tie each community to specific SDG targets, transforming aspirational goals into a concrete, community-by-community policy roadmap for green logistics.

推动公路、铁路、海运和跨联运领域交通脱碳研究的潜在主题群体是什么？为了回答这个核心问题，这项工作提出了一个集成的网络模型，该模型融合了书目耦合和句子- bert语义相似性，然后使用最先进的社区检测算法进行统计分析。我们通过四个互补的指标来评估分区：模块化、轮廓、密度和NF1，并比较加权和未加权的图。我们对特定模式语料库的分析揭示了不同的集群：道路研究分为城市最后一英里自动化和农村物流；铁路围绕着一个具有生物燃料和走廊电气化分支的同步调度中心进行合并；海上分为绿色燃料、自主安全和岸电流；跨模式研究形成了电气化、数据分析和区块链的重叠三位一体。加权边缘积分统一提高主题清晰度，而不改变算法排名。这些发现产生了可操作的算法选择启发式方法，并将每个社区与具体的可持续发展目标联系起来，将理想目标转化为具体的、逐社区的绿色物流政策路线图。

{"title":"Unveiling emerging communities: a network approach on transport decarbonisation technology","authors":"Joao Tiago Aparicio , Elisabete Arsenio , Rui Henriques","doi":"10.1016/j.trip.2025.101833","DOIUrl":"10.1016/j.trip.2025.101833","url":null,"abstract":"<div><div>What are the latent thematic communities driving transport decarbonisation research across road, rail, maritime, and crossmodal domains? To answer this central question, this work proposes an integrated network model that fuses bibliographic coupling with Sentence-BERT semantic similarities, followed by a statistical analysis using state-of-the-art community detection algorithms. We assess partitions via four complementary metrics, modularity, silhouette, density, and NF1, and compare weighted versus unweighted graphs. Our analysis of mode-specific corpora uncovers distinct clusters: road research splits into urban last-mile automation and rural logistics; rail coalesces around a synchromodal scheduling hub with biofuel and corridor electrification offshoots; maritime divides into green fuels, autonomous safety, and shore-power streams; and crossmodal studies form overlapping triads of electrification, data analytics, and blockchain. Weighted edge integration uniformly enhances thematic clarity without altering algorithm rankings. These findings yield actionable algorithm-selection heuristics and tie each community to specific SDG targets, transforming aspirational goals into a concrete, community-by-community policy roadmap for green logistics.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"36 ","pages":"Article 101833"},"PeriodicalIF":3.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146023527","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}

引用次数: 0

Study on the synergistic development efficiency of Guangzhou under the rail transit Networks: A dual-dimensional perspective of inter-district and inter-industry 轨道交通网络下广州市协同发展效率研究——基于跨区、跨行业的双重视角

IF 3.8 Q2 TRANSPORTATION

Transportation Research Interdisciplinary Perspectives

Pub Date : 2026-03-01 Epub Date: 2026-02-23 DOI: 10.1016/j.trip.2026.101885

Zhichen Yang , Qianlin Yin , Yuzhen Li , Fangfang Wang , Ling Cen

In recent years, promoting regional synergistic development has become a key objective for the next stage of global city development. The rapid construction and continuous improvement of rail transit networks (RTNs) have significantly reshaped urban spatial organization and the flow of resources, profoundly affecting synergistic development. This study aims to enrich the theoretical and empirical literature on regional coordinated development in China at a micro scale, taking Guangzhou—a major economic hub in China—as the research object. Under the context of RTNs, we employ quantitative modeling and big data analysis to measure synergistic development levels along two dimensions: inter-district and inter-industry. The evolution of Guangzhou’s synergistic development is further analyzed. Results show that Guangzhou’s overall development level continues to improve, inter-district disparities exhibit dynamic convergence, and the overall synergistic development level is continuously optimized. RTN connectivity and agglomeration levels have significantly increased, while cross-district rail connections still require enhancement. Districts such as Yuexiu and Liwan serve as core nodes, whereas Nansha has not yet assumed a sub-central city role. The spatial layouts of manufacturing and productive service industries (PSIs) show considerable similarity; the spatial similarity is strongest between transportation service industries and manufacturing, followed by science and technology(S&T) services.

近年来，促进区域协同发展已成为下一阶段全球城市发展的重要目标。轨道交通网络的快速建设和不断完善，极大地重塑了城市空间组织和资源流动，深刻地影响着协同发展。本研究以中国主要经济枢纽广州为研究对象，旨在丰富微观尺度下中国区域协调发展的理论和实证文献。在RTNs背景下，我们采用定量建模和大数据分析方法，从区域间和产业间两个维度衡量协同发展水平。进一步分析了广州协同发展的演变过程。结果表明：广州市整体发展水平持续提升，区际差异呈现动态收敛，整体协同发展水平不断优化。RTN连通性和集聚水平显著提高，但跨区铁路连接仍需加强。越秀、荔湾等区是核心节点，南沙尚未担当副中心城市的角色。制造业与生产性服务业的空间布局具有相当的相似性；交通运输服务业与制造业的空间相似性最强，科技服务业次之。

{"title":"Study on the synergistic development efficiency of Guangzhou under the rail transit Networks: A dual-dimensional perspective of inter-district and inter-industry","authors":"Zhichen Yang , Qianlin Yin , Yuzhen Li , Fangfang Wang , Ling Cen","doi":"10.1016/j.trip.2026.101885","DOIUrl":"10.1016/j.trip.2026.101885","url":null,"abstract":"<div><div>In recent years, promoting regional synergistic development has become a key objective for the next stage of global city development. The rapid construction and continuous improvement of rail transit networks (RTNs) have significantly reshaped urban spatial organization and the flow of resources, profoundly affecting synergistic development. This study aims to enrich the theoretical and empirical literature on regional coordinated development in China at a micro scale, taking Guangzhou—a major economic hub in China—as the research object. Under the context of RTNs, we employ quantitative modeling and big data analysis to measure synergistic development levels along two dimensions: inter-district and inter-industry. The evolution of Guangzhou’s synergistic development is further analyzed. Results show that Guangzhou’s overall development level continues to improve, inter-district disparities exhibit dynamic convergence, and the overall synergistic development level is continuously optimized. RTN connectivity and agglomeration levels have significantly increased, while cross-district rail connections still require enhancement. Districts such as Yuexiu and Liwan serve as core nodes, whereas Nansha has not yet assumed a sub-central city role. The spatial layouts of manufacturing and productive service industries (PSIs) show considerable similarity; the spatial similarity is strongest between transportation service industries and manufacturing, followed by science and technology(S&T) services.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"36 ","pages":"Article 101885"},"PeriodicalIF":3.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147385357","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}

引用次数: 0

Impact of congestion pricing on taxi travel patterns 挤塞收费对的士出行模式的影响

IF 3.8 Q2 TRANSPORTATION

Transportation Research Interdisciplinary Perspectives

Pub Date : 2026-03-01 Epub Date: 2026-02-19 DOI: 10.1016/j.trip.2026.101908

Atusa Javaheri , Apurva Pamidimukkala , Sharareh Kermanshachi , Jay Michael Rosenberger

Urban congestion continues to challenge large metropolitan areas, often exacerbating travel times, air pollution, and economic inefficiencies. In 2025, in an effort to combat these challenges, a major U.S. metropolitan city introduced a congestion pricing policy that targets congestion reduction, emission control, and transit funding. This study used pre- and post-policy taxi trip data to assesses the effectiveness of that policy on taxi travel within the city’s central business district and used a two-prong approach involving Multiple Linear Regression (MLR) and machine learning-based XGBoost models to quantify its impact. Both models were trained on historical data that was gathered prior to the policy’s implementation and incorporated temporal features and external demand signals to forecast trip counts. A comparison of their forecasts with the actual trip counts observed during the policy period revealed a significant reduction in taxi trips within the charged zone, with the XGBoost model providing forecasting accuracy superior to the MLR model. The study also emphasizes the advantages of using machine learning techniques to improve forecasting and evaluations of urban transportation systems policies, providing key insights for cities considering similar interventions.

城市拥堵继续给大都市地区带来挑战，通常会加剧出行时间、空气污染和经济效率低下。2025年，为了应对这些挑战，美国一个主要大都市推出了一项拥堵收费政策，旨在减少拥堵，控制排放，并为交通提供资金。本研究使用政策前和政策后的出租车出行数据来评估该政策对城市中央商务区出租车出行的有效性，并使用双管齐下的方法，包括多元线性回归（MLR）和基于机器学习的XGBoost模型来量化其影响。这两个模型都是根据政策实施前收集的历史数据进行训练的，并结合了时间特征和外部需求信号来预测出行次数。将他们的预测与政策期间观察到的实际出行次数进行比较，发现收费区域内的出租车出行次数显著减少，XGBoost模型的预测精度优于MLR模型。该研究还强调了使用机器学习技术来改进城市交通系统政策的预测和评估的优势，为考虑类似干预措施的城市提供了关键见解。

{"title":"Impact of congestion pricing on taxi travel patterns","authors":"Atusa Javaheri , Apurva Pamidimukkala , Sharareh Kermanshachi , Jay Michael Rosenberger","doi":"10.1016/j.trip.2026.101908","DOIUrl":"10.1016/j.trip.2026.101908","url":null,"abstract":"<div><div>Urban congestion continues to challenge large metropolitan areas, often exacerbating travel times, air pollution, and economic inefficiencies. In 2025, in an effort to combat these challenges, a major U.S. metropolitan city introduced a congestion pricing policy that targets congestion reduction, emission control, and transit funding. This study used pre- and post-policy taxi trip data to assesses the effectiveness of that policy on taxi travel within the city’s central business district and used a two-prong approach involving Multiple Linear Regression (MLR) and machine learning-based XGBoost models to quantify its impact. Both models were trained on historical data that was gathered prior to the policy’s implementation and incorporated temporal features and external demand signals to forecast trip counts. A comparison of their forecasts with the actual trip counts observed during the policy period revealed a significant reduction in taxi trips within the charged zone, with the XGBoost model providing forecasting accuracy superior to the MLR model. The study also emphasizes the advantages of using machine learning techniques to improve forecasting and evaluations of urban transportation systems policies, providing key insights for cities considering similar interventions.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"36 ","pages":"Article 101908"},"PeriodicalIF":3.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147385358","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}

引用次数: 0

Traffic police gesture detection by autonomous vehicle driving to act using hybrid architecture combining baseline CNN, MobileNet and DenseNet 使用混合架构结合基线CNN， MobileNet和DenseNet，自动驾驶车辆进行交警手势检测

IF 3.8 Q2 TRANSPORTATION

Transportation Research Interdisciplinary Perspectives

Pub Date : 2026-03-01 Epub Date: 2026-02-12 DOI: 10.1016/j.trip.2026.101894

El houssine Amraouy , Ali Yahyaouy , Sanaa Faquir , Hicham Chaoui , Hamid Gualous

Autonomous vehicle (AV) technology development has driven up the need for systems which recognize human signals including traffic police gestures with reliability. A deep learning hybrid framework based on baseline CNN, MobileNetV2 and DenseNet121 demonstrates promising capabilities for accurate traffic police gesture recognition systems. The specialized dataset contains ten gesture categories including left over, right over, stop signal, move straight, right turn, left turn, right, left, lane left which are followed by lane right also exist as separate categories. This specialized dataset includes few images that were captured under different lighting conditions and ambient situations during gesture performance to enhance model generalization capabilities. The proposed hybrid architecture combines DenseNet121, due to its strength and robustness in discovering complex high-level patterns, with MobileNetV2 for its fast and efficient mid-level pattern recognition, all together combined with baseline CNN for its basic low-level feature analysis. The model merges different characteristics through its feature aggregation layer to maintain a balance between classification precision and system resource efficiency. During testing with the dataset, the hybrid architecture proved its suitability for real-time applications through achieving 98.7% accuracy at 1.03 s model processing time. The system works to address the challenges involved in traffic police gesture detection. The suggested system allows autonomous vehicles to automatically recognize and appropriately respond to driver gestures during real-life driving scenarios. The research represents a breakthrough in gesture recognition that enables intelligent transportation because it enhances autonomous driving system operational safety and effectiveness.

自动驾驶汽车（AV）技术的发展推动了对可靠识别交通警察手势等人类信号的系统的需求。基于基线CNN、MobileNetV2和DenseNet121的深度学习混合框架展示了准确的交通警察手势识别系统的有前途的能力。该专用数据集包含10个手势类别，包括左转弯、右转弯、停车信号、直行、右转弯、左转弯、右转弯、左转弯、车道左，车道右也作为单独的类别存在。这个专门的数据集包括在手势表演过程中不同光照条件和环境情况下捕获的少量图像，以增强模型的泛化能力。提出的混合架构结合了DenseNet121，由于其在发现复杂的高级模式方面的强度和鲁棒性，与MobileNetV2结合了其快速高效的中级模式识别，所有这些都结合了基线CNN进行基本的低级特征分析。该模型通过特征聚合层对不同的特征进行融合，以保持分类精度和系统资源效率之间的平衡。在对数据集的测试中，混合架构在1.03 s的模型处理时间内达到了98.7%的准确率，证明了它适合于实时应用。该系统致力于解决交警手势检测所面临的挑战。该系统允许自动驾驶汽车在现实驾驶场景中自动识别并适当响应驾驶员的手势。此次研究结果提高了自动驾驶系统的运行安全性和有效性，是智能交通领域的重大突破。

{"title":"Traffic police gesture detection by autonomous vehicle driving to act using hybrid architecture combining baseline CNN, MobileNet and DenseNet","authors":"El houssine Amraouy , Ali Yahyaouy , Sanaa Faquir , Hicham Chaoui , Hamid Gualous","doi":"10.1016/j.trip.2026.101894","DOIUrl":"10.1016/j.trip.2026.101894","url":null,"abstract":"<div><div>Autonomous vehicle (AV) technology development has driven up the need for systems which recognize human signals including traffic police gestures with reliability. A deep learning hybrid framework based on baseline CNN, MobileNetV2 and DenseNet121 demonstrates promising capabilities for accurate traffic police gesture recognition systems. The specialized dataset contains ten gesture categories including left over, right over, stop signal, move straight, right turn, left turn, right, left, lane left which are followed by lane right also exist as separate categories. This specialized dataset includes few images that were captured under different lighting conditions and ambient situations during gesture performance to enhance model generalization capabilities. The proposed hybrid architecture combines DenseNet121, due to its strength and robustness in discovering complex high-level patterns, with MobileNetV2 for its fast and efficient mid-level pattern recognition, all together combined with baseline CNN for its basic low-level feature analysis. The model merges different characteristics through its feature aggregation layer to maintain a balance between classification precision and system resource efficiency. During testing with the dataset, the hybrid architecture proved its suitability for real-time applications through achieving 98.7% accuracy at 1.03 s model processing time. The system works to address the challenges involved in traffic police gesture detection. The suggested system allows autonomous vehicles to automatically recognize and appropriately respond to driver gestures during real-life driving scenarios. The research represents a breakthrough in gesture recognition that enables intelligent transportation because it enhances autonomous driving system operational safety and effectiveness.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"36 ","pages":"Article 101894"},"PeriodicalIF":3.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147385122","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}

引用次数: 0

Transportation, ride-hailing and discrimination among the blind and low vision community 交通、网约车以及对盲人和低视力群体的歧视

IF 3.8 Q2 TRANSPORTATION

Transportation Research Interdisciplinary Perspectives

Pub Date : 2026-03-01 Epub Date: 2026-01-06 DOI: 10.1016/j.trip.2026.101837

Sylvia A. Brady , Nels Grevstad , Sarah A. Schliemann , C. Glatthar

Individuals with disabilities, including those who are blind or have low vision (BLV), travel less frequently than non-disabled individuals due to persistent barriers across transportation modes. Ride-hailing services such as Uber and Lyft offer the potential to enhance mobility for the BLV community by providing flexible, on-demand travel options. However, many BLV individuals also experience discrimination when using these services, and there is a lack of research on their transportation and discrimination experiences. This study used an online survey as the first part of a mixed-methods research project to document and quantify the transportation experiences of BLV individuals, with a focus on ride-hailing. We explored differences in user satisfaction and perceptions of discrimination between Uber and Lyft and examined whether guide dog use contributes to higher rates of service denial or mistreatment. Our findings indicate that while ride-hailing services significantly improve access to destinations for BLV users, they are also the mode in which discrimination is most frequently reported. Guide dog users face notably higher rates of ride refusals. Respondents expressed slightly greater satisfaction with Lyft than with Uber. These findings underscore the dual nature of ride-hailing for BLV individuals: it offers greater independence but also introduces new challenges. This research has implications for ride-hailing companies seeking to improve accessibility, and for public agencies partnering with these platforms to deliver equitable, on-demand transportation services.

由于各种交通方式之间存在障碍，残疾人（包括盲人或低视力者）的出行频率低于非残疾人。Uber和Lyft等叫车服务通过提供灵活的按需出行选择，为BLV社区提供了增强移动性的潜力。然而，许多BLV个体在使用这些服务时也遭受了歧视，并且缺乏对其交通和歧视经历的研究。本研究采用在线调查作为混合方法研究项目的第一部分，记录和量化BLV个人的交通体验，重点是叫车服务。我们探讨了优步和Lyft在用户满意度和歧视感知方面的差异，并研究了导盲犬的使用是否会导致更高的服务拒绝率或虐待率。我们的研究结果表明，虽然网约车服务显着改善了BLV用户到达目的地的机会，但它们也是最常被报道的歧视模式。导盲犬使用者面临明显更高的乘坐拒绝率。受访者对Lyft的满意度略高于优步。这些发现强调了叫车服务对BLV个人的双重性质：它提供了更大的独立性，但也带来了新的挑战。这项研究对寻求改善可达性的网约车公司，以及与这些平台合作提供公平、按需交通服务的公共机构都有影响。

{"title":"Transportation, ride-hailing and discrimination among the blind and low vision community","authors":"Sylvia A. Brady , Nels Grevstad , Sarah A. Schliemann , C. Glatthar","doi":"10.1016/j.trip.2026.101837","DOIUrl":"10.1016/j.trip.2026.101837","url":null,"abstract":"<div><div>Individuals with disabilities, including those who are blind or have low vision (BLV), travel less frequently than non-disabled individuals due to persistent barriers across transportation modes. Ride-hailing services such as Uber and Lyft offer the potential to enhance mobility for the BLV community by providing flexible, on-demand travel options. However, many BLV individuals also experience discrimination when using these services, and there is a lack of research on their transportation and discrimination experiences. This study used an online survey as the first part of a mixed-methods research project to document and quantify the transportation experiences of BLV individuals, with a focus on ride-hailing. We explored differences in user satisfaction and perceptions of discrimination between Uber and Lyft and examined whether guide dog use contributes to higher rates of service denial or mistreatment. Our findings indicate that while ride-hailing services significantly improve access to destinations for BLV users, they are also the mode in which discrimination is most frequently reported. Guide dog users face notably higher rates of ride refusals. Respondents expressed slightly greater satisfaction with Lyft than with Uber. These findings underscore the dual nature of ride-hailing for BLV individuals: it offers greater independence but also introduces new challenges. This research has implications for ride-hailing companies seeking to improve accessibility, and for public agencies partnering with these platforms to deliver equitable, on-demand transportation services.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"36 ","pages":"Article 101837"},"PeriodicalIF":3.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928661","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}

引用次数: 0

Envisioning AI for international cooperation in maritime transport: conceptual insights from short sea shipping and maritime spatial planning 展望人工智能在海上运输中的国际合作：来自短途海运和海上空间规划的概念见解

IF 3.8 Q2 TRANSPORTATION

Transportation Research Interdisciplinary Perspectives

Pub Date : 2026-03-01 Epub Date: 2026-01-10 DOI: 10.1016/j.trip.2025.101819

Vasiliki-Maria Perra, Maria Boile

Artificial Intelligence (AI) can significantly enhance transportation governance, particularly by enabling more effective international cooperation in data-driven decision-making. In maritime transport, AI applications can support complex planning and policy processes, such as maritime spatial planning (MSP), which governs the use of maritime space across overlapping sectors and jurisdictions. Short sea shipping (SSS), a vital mode of regional and intra-regional transport, depends heavily on coordinated planning efforts due to its interactions with other marine uses, its socio-economic role, and the need to maintain connectivity for insular economies.

This study uses a national level case study of Greek SSS to identify structural, data-related, and governance limitations that impede evidence-based policy design. Key performance indicators (KPIs) and composite indices (CIs) are developed to assess connectivity, accessibility, and operational efficiency across the island and between the islands and the mainland. These empirical findings reveal fragmented data, heterogenous service patterns, and gaps in current governance frameworks, highlighting challenges that extend to regional and international coordination.

Building on these insights, the paper proposes a conceptual AI framework to address the identified limitations. Machine learning can forecast SSS performance trands, while natural language processing can harmonize policy documents across jurisdictions. By linking empirical limitations with this forward-looking conceptual approach, the study demonstrates how AI can transform fragmented maritime data into interoperable, collaborative governance mechanisms that enhance MSP implementation and cross-border cooperation.

人工智能（AI）可以显著加强交通管理，特别是通过在数据驱动的决策中实现更有效的国际合作。在海上运输中，人工智能应用可以支持复杂的规划和政策流程，例如海洋空间规划（MSP），该规划管理跨重叠部门和司法管辖区的海洋空间使用。短途海运（SSS）是区域和区域内运输的重要模式，由于其与其他海洋用途的相互作用，其社会经济作用以及保持岛屿经济连通性的需要，在很大程度上取决于协调的规划工作。本研究采用希腊社会保障制度的国家层面案例研究，以确定阻碍循证政策设计的结构性、数据相关和治理限制。制定了关键绩效指标（kpi）和综合指数（ci），以评估全岛以及岛屿与大陆之间的连通性、可达性和运营效率。这些实证研究结果揭示了当前治理框架中支离破碎的数据、异质的服务模式和差距，突出了扩展到区域和国际协调的挑战。在这些见解的基础上，本文提出了一个概念性的人工智能框架来解决已确定的限制。机器学习可以预测SSS的性能趋势，而自然语言处理可以协调跨司法管辖区的政策文件。通过将经验局限性与这种前瞻性概念方法联系起来，该研究展示了人工智能如何将碎片化的海事数据转化为可互操作的协作治理机制，从而加强MSP的实施和跨境合作。

{"title":"Envisioning AI for international cooperation in maritime transport: conceptual insights from short sea shipping and maritime spatial planning","authors":"Vasiliki-Maria Perra, Maria Boile","doi":"10.1016/j.trip.2025.101819","DOIUrl":"10.1016/j.trip.2025.101819","url":null,"abstract":"<div><div>Artificial Intelligence (AI) can significantly enhance transportation governance, particularly by enabling more effective international cooperation in data-driven decision-making. In maritime transport, AI applications can support complex planning and policy processes, such as maritime spatial planning (MSP), which governs the use of maritime space across overlapping sectors and jurisdictions. Short sea shipping (SSS), a vital mode of regional and intra-regional transport, depends heavily on coordinated planning efforts due to its interactions with other marine uses, its socio-economic role, and the need to maintain connectivity for insular economies.</div><div>This study uses a national level case study of Greek SSS to identify structural, data-related, and governance limitations that impede evidence-based policy design. Key performance indicators (KPIs) and composite indices (CIs) are developed to assess connectivity, accessibility, and operational efficiency across the island and between the islands and the mainland. These empirical findings reveal fragmented data, heterogenous service patterns, and gaps in current governance frameworks, highlighting challenges that extend to regional and international coordination.</div><div>Building on these insights, the paper proposes a conceptual AI framework to address the identified limitations. Machine learning can forecast SSS performance trands, while natural language processing can harmonize policy documents across jurisdictions. By linking empirical limitations with this forward-looking conceptual approach, the study demonstrates how AI can transform fragmented maritime data into interoperable, collaborative governance mechanisms that enhance MSP implementation and cross-border cooperation.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"36 ","pages":"Article 101819"},"PeriodicalIF":3.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145929220","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}

引用次数: 0

Adaptive electric vehicle routing and charging with deep reinforcement learning 基于深度强化学习的自适应电动汽车路径与充电

IF 3.8 Q2 TRANSPORTATION

Transportation Research Interdisciplinary Perspectives

Pub Date : 2026-03-01 Epub Date: 2026-01-19 DOI: 10.1016/j.trip.2025.101795

Mandana Farhang Ghahfarokhi , Hyoshin Park , Venktesh Pandey , Gyugeun Yoon

As electric vehicles (EVs) gain popularity, efficient routing and charging solutions remain challenging due to time-dependent travel variability, sparse charging infrastructure, and heterogeneous user preferences. To address these challenges, this paper introduces a decision-support system that integrates three complementary methods: Temporal Multimodal Multivariate Learning (TMML) for real-time characterization of travel time uncertainty, Time-Dependent Shortest Path (TDSP) for reliability-aware route choice, and Deep Q-Network (DQN) reinforcement learning for adaptive charging decisions in sparse infrastructure environments. TMML updates link-level travel time distributions in real-time through Bayesian inference with cluster-based propagation, reducing uncertainties across the network. TDSP leverages these updated distributions to estimate remaining travel time and reliability scores for route planning. DQN learns optimal charging policies by determining when to charge, how much to charge (partial charging at 25%, 50%, 75%, or 100% levels), and which route to take based on battery state, traffic patterns, and available stationary charging stations (SCSs) and mobile charging infrastructure—including Mobile Energy Distributors (MEDs) and Dynamic Inductive Charging (DIC). DQN training uses simulation-based learning from actual traffic patterns of the Washington, DC metropolitan region, allowing the agent to explore charging-route pairs and discover efficient solutions through trial and error. To accommodate heterogeneous user preferences, the system calculates multiple Pareto-optimal solutions that trade off travel time, charging cost, battery safety, and route reliability, enabling users to select alternatives that match their current priorities without specifying preference weights in advance.

随着电动汽车（ev）的普及，由于时间依赖的行驶可变性、充电基础设施的稀疏性和用户偏好的异质性，高效的路由和充电解决方案仍然具有挑战性。为了解决这些挑战，本文介绍了一个决策支持系统，该系统集成了三种互补的方法：用于实时表征旅行时间不确定性的时间多模态多元学习（TMML），用于可靠性感知路径选择的时间相关最短路径（TDSP），以及用于稀疏基础设施环境中自适应收费决策的深度q -网络（DQN）强化学习。TMML通过贝叶斯推理和基于集群的传播实时更新链路级旅行时间分布，减少了网络中的不确定性。TDSP利用这些更新的分布来估计剩余的旅行时间和路线规划的可靠性得分。DQN通过确定何时充电、充电多少（25%、50%、75%或100%的部分充电水平）以及根据电池状态、交通模式、可用的固定充电站（scs）和移动充电基础设施（包括移动能源分销商（med）和动态感应充电（DIC））选择哪条路线来学习最佳充电策略。DQN训练使用基于模拟的学习，从华盛顿特区的实际交通模式中学习，允许代理探索充电路线对，并通过试错发现有效的解决方案。为了适应不同的用户偏好，系统计算了多个帕累托最优解决方案，权衡了旅行时间、充电成本、电池安全性和路线可靠性，使用户能够选择与当前优先级匹配的替代方案，而无需事先指定偏好权重。

{"title":"Adaptive electric vehicle routing and charging with deep reinforcement learning","authors":"Mandana Farhang Ghahfarokhi , Hyoshin Park , Venktesh Pandey , Gyugeun Yoon","doi":"10.1016/j.trip.2025.101795","DOIUrl":"10.1016/j.trip.2025.101795","url":null,"abstract":"<div><div>As electric vehicles (EVs) gain popularity, efficient routing and charging solutions remain challenging due to time-dependent travel variability, sparse charging infrastructure, and heterogeneous user preferences. To address these challenges, this paper introduces a decision-support system that integrates three complementary methods: Temporal Multimodal Multivariate Learning (TMML) for real-time characterization of travel time uncertainty, Time-Dependent Shortest Path (TDSP) for reliability-aware route choice, and Deep Q-Network (DQN) reinforcement learning for adaptive charging decisions in sparse infrastructure environments. TMML updates link-level travel time distributions in real-time through Bayesian inference with cluster-based propagation, reducing uncertainties across the network. TDSP leverages these updated distributions to estimate remaining travel time and reliability scores for route planning. DQN learns optimal charging policies by determining when to charge, how much to charge (partial charging at 25%, 50%, 75%, or 100% levels), and which route to take based on battery state, traffic patterns, and available stationary charging stations (SCSs) and mobile charging infrastructure—including Mobile Energy Distributors (MEDs) and Dynamic Inductive Charging (DIC). DQN training uses simulation-based learning from actual traffic patterns of the Washington, DC metropolitan region, allowing the agent to explore charging-route pairs and discover efficient solutions through trial and error. To accommodate heterogeneous user preferences, the system calculates multiple Pareto-optimal solutions that trade off travel time, charging cost, battery safety, and route reliability, enabling users to select alternatives that match their current priorities without specifying preference weights in advance.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"36 ","pages":"Article 101795"},"PeriodicalIF":3.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146024111","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}

引用次数: 0

An Agent-Based discrete event simulation of teleoperated driving in freight Transport: The fleet sizing problem 基于agent的货运遥控驾驶离散事件仿真：车队规模问题

IF 3.8 Q2 TRANSPORTATION

Transportation Research Interdisciplinary Perspectives

Pub Date : 2026-03-01 Epub Date: 2026-01-22 DOI: 10.1016/j.trip.2026.101864

Bahman Madadi , Ali Nadi , Gonçalo Homem de Almeida Correia , Thierry Verduijn , Lóránt Tavasszy

Teleoperated driving complements automated driving and acts as transitional technology towards full automation. An economic advantage of teleoperated driving in logistics operations lies in managing fleets with fewer teleoperators compared to vehicles with in-vehicle drivers. This alleviates growing truck driver shortage problems in the logistics industry and save costs. However, a trade-off exists between the teleoperator-to-vehicle (TO/V) ratio and the service level of teleoperation. This study designs a simulation framework to explore this trade-off generating multiple performance indicators as proxies for teleoperation service level. By applying the framework, we identify factors influencing the trade-off and optimal TO/V ratios under different scenarios. Our case study on road freight tours in the Netherlands reveals that for any operational settings, a TO/V ratio below one can manage all freight truck tours without delay, while one represents the current situation. The minimum TO/V ratio for zero-delay operations is never above 0.6, implying a minimum of 40% teleoperation labor cost saving. For operations where a small delay is allowed, TO/V ratios as low as 0.4 are shown to be feasible, which indicates potential savings of up to 60%. This confirms great promise for a positive business case for the teleoperated driving as a service.

遥控驾驶是对自动驾驶的补充，是向全自动驾驶的过渡技术。远程操作驾驶在物流运营中的一个经济优势在于，与配备车内驾驶员的车辆相比，远程操作人员较少的车队可以得到更好的管理。这缓解了物流行业日益严重的卡车司机短缺问题，并节省了成本。然而，遥操作人与车辆（TO/V）比率与遥操作服务水平之间存在权衡。本研究设计了一个模拟框架来探讨这种权衡，生成多个性能指标作为遥操作服务水平的代理。通过应用该框架，我们确定了在不同场景下影响权衡和最佳TO/V比率的因素。我们对荷兰公路货运之旅的案例研究表明，对于任何操作设置，低于1的TO/V比率可以毫不延迟地管理所有货运卡车之旅，而1代表当前情况。零延迟操作的最小TO/V比从未超过0.6，这意味着至少可以节省40%的远程操作人工成本。对于允许小延迟的操作，低至0.4的TO/V比率是可行的，这表明潜在的节省高达60%。这证实了远程驾驶作为一种服务的积极商业案例的巨大前景。

{"title":"An Agent-Based discrete event simulation of teleoperated driving in freight Transport: The fleet sizing problem","authors":"Bahman Madadi , Ali Nadi , Gonçalo Homem de Almeida Correia , Thierry Verduijn , Lóránt Tavasszy","doi":"10.1016/j.trip.2026.101864","DOIUrl":"10.1016/j.trip.2026.101864","url":null,"abstract":"<div><div>Teleoperated driving complements automated driving and acts as transitional technology towards full automation. An economic advantage of teleoperated driving in logistics operations lies in managing fleets with fewer teleoperators compared to vehicles with in-vehicle drivers. This alleviates growing truck driver shortage problems in the logistics industry and save costs. However, a trade-off exists between the teleoperator-to-vehicle (TO/V) ratio and the service level of teleoperation. This study designs a simulation framework to explore this trade-off generating multiple performance indicators as proxies for teleoperation service level. By applying the framework, we identify factors influencing the trade-off and optimal TO/V ratios under different scenarios. Our case study on road freight tours in the Netherlands reveals that for any operational settings, a TO/V ratio below one can manage all freight truck tours without delay, while one represents the current situation. The minimum TO/V ratio for zero-delay operations is never above 0.6, implying a minimum of 40% teleoperation labor cost saving. For operations where a small delay is allowed, TO/V ratios as low as 0.4 are shown to be feasible, which indicates potential savings of up to 60%. This confirms great promise for a positive business case for the teleoperated driving as a service.</div></div>","PeriodicalId":36621,"journal":{"name":"Transportation Research Interdisciplinary Perspectives","volume":"36 ","pages":"Article 101864"},"PeriodicalIF":3.8,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146024117","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}

引用次数: 0

Probing urban road network congestion propagation and dissipation 探讨城市道路网络拥堵的传播与消散

IF 3.8 Q2 TRANSPORTATION

Transportation Research Interdisciplinary Perspectives

Pub Date : 2026-03-01 Epub Date: 2026-01-31 DOI: 10.1016/j.trip.2026.101839

Reza Marzban , Meisam Akbarzadeh , Anastasios Kouvelas , Francesco Corman

The spread of congestion in urban road networks is a complex phenomenon with spatial and temporal dimensions; quantitative analysis of the phenomenon would allow traffic managers come up with effective relief measures. In this study, we present three findings from two real urban road networks (Shenzhen and Chengdu in China). First, we show that integration of the re-congestion assumption through Susceptible-Exposed-Infected-Recovered-Susceptible (SEIRS) models markedly enhances the predictive robustness of conventional fragmental propagation models (e.g. SIR and SEIR). Second, we show that links with high betweenness centralities create congestion seeds at the beginning of peak periods which persist through the whole peak period. A component of congestion propagates from such cores and then shrinks and dissolves through them. Third, we demonstrate the impact of congested component sizes on network functionality.

城市道路网络中拥堵的蔓延是一个具有时空维度的复杂现象；对这一现象进行定量分析，可以让交通管理人员提出有效的缓解措施。在这项研究中，我们从两个真实的城市道路网络（中国的深圳和成都）中得出了三个结论。首先，我们证明了通过易感-暴露-感染-恢复-易感（SEIRS）模型整合再拥塞假设显着增强了传统片段传播模型（例如SIR和SEIR）的预测鲁棒性。其次，我们表明，具有高中间度中心性的链接在高峰时期开始时产生拥堵种子，并持续整个高峰时期。拥塞的一个组成部分从这样的核心传播，然后收缩并通过它们溶解。第三，我们展示了拥塞组件大小对网络功能的影响。

引用次数: 0