Transportation Research Part D-transport and Environment最新文献

英文中文

Resilience analysis of electric vehicle charging infrastructure: a Bayesian network approach 电动汽车充电基础设施弹性分析：贝叶斯网络方法

IF 7.7 1区工程技术 Q1 ENVIRONMENTAL STUDIES

Transportation Research Part D-transport and Environment

Pub Date : 2025-12-23 DOI: 10.1016/j.trd.2025.105178

Ning Guo , Mengying Li , Zhe George Zhang , Xi Chen , Bingfeng Xie

With the widespread adoption of electric vehicles, charging infrastructure has become indispensable to transportation systems. However, various unavoidable disruptive events, such as natural hazards and cyber threats, severely impact the operation of charging infrastructure. To better handle these risks, charging infrastructure should be maintained for high resilience—sustaining service under disturbance and recovering quickly. This study, therefore, conducts a comprehensive resilience analysis of charging infrastructure. First, the study identifies key drivers of charging infrastructure resilience, organized along three inherent capacity dimensions—absorptive, adaptive, and restorative. A Bayesian network is then employed to model charging infrastructure resilience. Furthermore, resilience quantification is analyzed using advanced methods: sensitivity analysis and both forward and backward inference. Lastly, the insights drawn from study will benefit practitioners who wish to improve the charging infrastructure resilience.

随着电动汽车的广泛采用，充电基础设施已成为交通系统不可或缺的一部分。然而，各种不可避免的破坏性事件，如自然灾害和网络威胁，严重影响了充电基础设施的运行。为了更好地应对这些风险，应该维护充电基础设施，使其能够在干扰下提供高弹性持续服务并快速恢复。因此，本研究对充电基础设施进行了全面的弹性分析。首先，该研究确定了充电基础设施弹性的关键驱动因素，并按照三个固有的能力维度进行组织——吸收性、适应性和恢复性。然后采用贝叶斯网络对充电基础设施的弹性进行建模。在此基础上，采用灵敏度分析和前向推理相结合的方法对弹性进行量化分析。最后，从研究中得出的见解将有利于希望提高充电基础设施弹性的从业者。

{"title":"Resilience analysis of electric vehicle charging infrastructure: a Bayesian network approach","authors":"Ning Guo , Mengying Li , Zhe George Zhang , Xi Chen , Bingfeng Xie","doi":"10.1016/j.trd.2025.105178","DOIUrl":"10.1016/j.trd.2025.105178","url":null,"abstract":"<div><div>With the widespread adoption of electric vehicles, charging infrastructure has become indispensable to transportation systems. However, various unavoidable disruptive events, such as natural hazards and cyber threats, severely impact the operation of charging infrastructure. To better handle these risks, charging infrastructure should be maintained for high resilience—sustaining service under disturbance and recovering quickly. This study, therefore, conducts a comprehensive resilience analysis of charging infrastructure. First, the study identifies key drivers of charging infrastructure resilience, organized along three inherent capacity dimensions—absorptive, adaptive, and restorative. A Bayesian network is then employed to model charging infrastructure resilience. Furthermore, resilience quantification is analyzed using advanced methods: sensitivity analysis and both forward and backward inference. Lastly, the insights drawn from study will benefit practitioners who wish to improve the charging infrastructure resilience.</div></div>","PeriodicalId":23277,"journal":{"name":"Transportation Research Part D-transport and Environment","volume":"152 ","pages":"Article 105178"},"PeriodicalIF":7.7,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145823198","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}

引用次数: 0

Beyond adoption: Adaptation and usage patterns among electric vehicle drivers 超越采用：电动汽车驾驶员的适应和使用模式

IF 7.7 1区工程技术 Q1 ENVIRONMENTAL STUDIES

Transportation Research Part D-transport and Environment

Pub Date : 2025-12-22 DOI: 10.1016/j.trd.2025.105175

Anne Voigt , Christina Kurpiers , Stefan Brandenburg

Battery electric vehicle (BEV) technology continues to advance, offering longer driving ranges. As the market shifts from early adopters to mainstream consumers, who differ in their characteristics, understanding their adaptation process becomes crucial. With advanced BEVs and more diverse users, questions arise about how current BEV drivers use their vehicles, adapt to them, and whether past issues like range anxiety remain significant. To explore these questions, we conducted qualitative interviews with N = 24 BEV owners. Findings reveal diverse usage patterns, from multi-car households using BEVs for short commutes to single-car households relying on them for long trips. Despite improved technical capabilities, concerns about range and charging persist, even as actual range meets daily needs for most drivers. The adaptation process of the drivers involves developing new habits and behaviours, with gained experience reducing initial concerns. Understanding these individual adaptation processes becomes increasingly important to facilitate widespread BEV adoption.

纯电动汽车（BEV）技术不断进步，提供了更长的行驶里程。随着市场从早期采用者转变为特征不同的主流消费者，了解他们的适应过程变得至关重要。随着先进的纯电动汽车和更多样化的用户，关于当前纯电动汽车司机如何使用他们的车辆，适应它们，以及过去的问题（如里程焦虑）是否仍然严重的问题出现了。为了探讨这些问题，我们对N = 24名纯电动汽车车主进行了定性访谈。调查结果揭示了不同的使用模式，从多辆车的家庭使用纯电动汽车进行短途通勤，到单辆车的家庭依靠纯电动汽车进行长途旅行。尽管技术能力有所提高，但对续航里程和充电的担忧仍然存在，即使实际续航里程满足了大多数司机的日常需求。驾驶员的适应过程包括发展新的习惯和行为，获得的经验减少了最初的担忧。了解这些个体适应过程对于促进纯电动汽车的广泛采用变得越来越重要。

{"title":"Beyond adoption: Adaptation and usage patterns among electric vehicle drivers","authors":"Anne Voigt , Christina Kurpiers , Stefan Brandenburg","doi":"10.1016/j.trd.2025.105175","DOIUrl":"10.1016/j.trd.2025.105175","url":null,"abstract":"<div><div>Battery electric vehicle (BEV) technology continues to advance, offering longer driving ranges. As the market shifts from early adopters to mainstream consumers, who differ in their characteristics, understanding their adaptation process becomes crucial. With advanced BEVs and more diverse users, questions arise about how current BEV drivers use their vehicles, adapt to them, and whether past issues like range anxiety remain significant. To explore these questions, we conducted qualitative interviews with <em>N</em> = 24 BEV owners. Findings reveal diverse usage patterns, from multi-car households using BEVs for short commutes to single-car households relying on them for long trips. Despite improved technical capabilities, concerns about range and charging persist, even as actual range meets daily needs for most drivers. The adaptation process of the drivers involves developing new habits and behaviours, with gained experience reducing initial concerns. Understanding these individual adaptation processes becomes increasingly important to facilitate widespread BEV adoption.</div></div>","PeriodicalId":23277,"journal":{"name":"Transportation Research Part D-transport and Environment","volume":"152 ","pages":"Article 105175"},"PeriodicalIF":7.7,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145823204","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}

引用次数: 0

Decarbonizing last-mile delivery: A life cycle comparison of low-altitude and traditional logistics 脱碳最后一英里配送：低空与传统物流的生命周期比较

IF 7.7 1区工程技术 Q1 ENVIRONMENTAL STUDIES

Transportation Research Part D-transport and Environment

Pub Date : 2025-12-21 DOI: 10.1016/j.trd.2025.105176

Jun-jie Dong , Yuan-kai Huang

With growing environmental concerns in e-commerce logistics, this research employs life cycle assessment to evaluate the carbon footprint of last-mile delivery options by comparing multi-rotor drones, electric tricycles, and fuel-powered minivans. Results show electric tricycles offer the best environmental performance under current conditions. While drones outperform conventional minivans, their manufacturing embodied carbon exceeds that of tricycles, highlighting limitations in operational emission reductions alone. Sensitivity analysis identifies payload capacity, service life, and daily operational frequency as key influencing factors. The research proposes extending vehicle lifespan, improving operational efficiency, and optimizing payload design to reduce emissions. These findings provide valuable insights for logistics operators in vehicle selection, manufacturers in eco-design, and policymakers in sustainable urban planning, contributing to the development of low-carbon delivery systems.

随着电子商务物流对环境问题的日益关注，本研究通过比较多旋翼无人机、电动三轮车和燃油驱动的小型货车，采用生命周期评估来评估最后一英里交付选项的碳足迹。结果表明，在当前条件下，电动三轮车具有最佳的环保性能。尽管无人机的性能优于传统的小型货车，但其制造过程中的碳含量超过了三轮车，这凸显了仅在运营减排方面的局限性。灵敏度分析确定有效载荷能力、使用寿命和日常运行频率是关键的影响因素。研究建议延长车辆寿命，提高运行效率，优化有效载荷设计以减少排放。这些发现为物流运营商在车辆选择方面、制造商在生态设计方面以及政策制定者在可持续城市规划方面提供了有价值的见解，有助于发展低碳运输系统。

引用次数: 0

Shifting gears? The CO2-emission impact of Austria’s car purchase and use policies 将齿轮吗?奥地利汽车购买和使用政策对二氧化碳排放的影响

IF 7.7 1区工程技术 Q1 ENVIRONMENTAL STUDIES

Transportation Research Part D-transport and Environment

Pub Date : 2025-12-21 DOI: 10.1016/j.trd.2025.105160

Tobias Eibinger , Hans Manner , Karl W. Steininger

Policy makers likely have to resort to a mix of complementary policies to achieve global carbon-neutrality targets. To support effective policy design, we analyse the effect of environmental policies targeting vehicle use and purchase decisions on CO₂ emissions from passenger cars in Austria from 1965 to 2019. First, we propose a novel environmental policy stringency index tailored to the Austrian transport sector. Second, we analyse the effect of policies on transport-related CO₂ emissions using a structural vector autoregressive model to account for interdependencies between variables. We find that policies targeting the investment decision to buy new cars reduce emissions in Austria in the long run, but their effect materializes with a delay. In terms of stringency levels implemented, the annual engine-related tax shows the strongest impact, while the new vehicle registration tax shows a weaker effect. In contrast, policies targeting car usage produce immediate effects that fade over time.

为了实现全球碳中和目标，政策制定者可能不得不采取多种互补政策。为了支持有效的政策设计，我们分析了1965年至2019年奥地利针对车辆使用和购买决策的环境政策对乘用车二氧化碳排放的影响。首先，我们提出了一个新的环境政策严格指数量身定制奥地利运输部门。其次，我们使用结构向量自回归模型来分析政策对交通相关二氧化碳排放的影响，以解释变量之间的相互依赖性。我们发现，从长期来看，针对购买新车的投资决策的政策减少了奥地利的排放，但其效果的实现是延迟的。就实施的严格程度而言，年度发动机相关税的影响最大，而新车辆登记税的影响较弱。相比之下，针对汽车使用的政策会产生立竿见影的效果，但随着时间的推移会逐渐消退。

引用次数: 0

Drivers and barriers to automated vehicle Adoption: A systematic review 自动驾驶汽车采用的司机和障碍：系统回顾

IF 7.7 1区工程技术 Q1 ENVIRONMENTAL STUDIES

Transportation Research Part D-transport and Environment

Pub Date : 2025-12-20 DOI: 10.1016/j.trd.2025.105177

Kai Jin, Junwei Zhao, Qiang Jiang, Xia Zhong

As automated vehicles move from concept to reality, public attitudes have become a key determinant of their adoption in developed countries. However, a comprehensive synthesis of existing evidence remains lacking. This study systematically reviews 38 empirical studies from developed economies, including the United States, the United Kingdom, Australia, Germany, Norway, and Japan. The review identifies a complex interplay of psychological factors, prior experience, attitudes, and trust shaping public willingness to adopt automated vehicles. Findings highlight that promoting automated vehicles requires an integrated, human-centric, and trust-based policy approach beyond technological advancement. The study proposes an integrative framework emphasizing legal and regulatory readiness, transparent and reliable human–machine interfaces, and targeted public education. These insights provide valuable guidance for policymakers, automakers, and technology developers to foster societal acceptance and sustainable deployment of automated driving technologies.

随着自动驾驶汽车从概念走向现实，公众态度已成为发达国家采用自动驾驶汽车的关键决定因素。然而，对现有证据的全面综合仍然缺乏。本研究系统回顾了来自美国、英国、澳大利亚、德国、挪威和日本等发达经济体的38项实证研究。该报告指出，心理因素、先前的经验、态度和信任等复杂的相互作用影响着公众采用自动驾驶汽车的意愿。研究结果强调，推广自动驾驶汽车需要一种综合的、以人为本的、基于信任的政策方法，而不仅仅是技术进步。该研究提出了一个综合框架，强调法律和监管准备，透明可靠的人机界面，以及有针对性的公共教育。这些见解为政策制定者、汽车制造商和技术开发人员提供了有价值的指导，以促进社会对自动驾驶技术的接受和可持续部署。

引用次数: 0

Breaking barriers to shared micro-mobility: Understanding non-adoption through an explanatory sequential mixed-method 打破共享微流动性的障碍：通过解释性顺序混合方法理解非采用

IF 7.7 1区工程技术 Q1 ENVIRONMENTAL STUDIES

Transportation Research Part D-transport and Environment

Pub Date : 2025-12-19 DOI: 10.1016/j.trd.2025.105171

Jasmijn van der Craats , Xiaodong Guan , Dea van Lierop , Dick Ettema

Shared micro-mobility (SMM) services such as shared bikes, e-bikes, and e-scooters are increasingly promoted as sustainable transport solutions, yet barriers to adoption remain poorly understood, particularly among non-users. This study employs an explanatory sequential mixed-methods design, guided by the Social-Ecological Model (SEM), to analyse barriers to SMM use in three European cities. In phase one, an online survey conducted in Malmö (Sweden), Manchester (United Kingdom), and Utrecht (Netherlands) identified the prevalence and distribution of barriers across socio-demographic groups. In phase two, go-along interviews conducted in Utrecht built directly on these findings to explore how users and non-users experience barriers in everyday mobility. Findings highlight affordability, safety concerns, and service availability as persistent obstacles of non-users, while users emphasize flexibility and convenience. By integrating breadth and depth across SEM’s micro, meso, and macro levels, this study advances understanding of SMM non-adoption and provides guidance for more inclusive and equitable SMM policies.

共享微型交通（SMM）服务，如共享自行车、电动自行车和电动滑板车，越来越多地被推广为可持续的交通解决方案，但采用的障碍仍然知之甚少，特别是在非用户中。本研究采用解释性顺序混合方法设计，在社会生态模型（SEM）的指导下，分析了三个欧洲城市使用SMM的障碍。在第一阶段，在Malmö（瑞典）、曼彻斯特（英国）和乌得勒支（荷兰）进行了一项在线调查，确定了障碍在社会人口群体中的普遍程度和分布。在第二阶段，在乌得勒支进行的访谈直接建立在这些发现的基础上，以探索用户和非用户如何在日常移动中遇到障碍。调查结果强调了可负担性、安全性和服务可用性是非用户的持续障碍，而用户则强调灵活性和便利性。通过整合SEM微观、中观和宏观层面的广度和深度，本研究促进了对不采用SMM的理解，并为更具包容性和公平性的SMM政策提供了指导。

{"title":"Breaking barriers to shared micro-mobility: Understanding non-adoption through an explanatory sequential mixed-method","authors":"Jasmijn van der Craats , Xiaodong Guan , Dea van Lierop , Dick Ettema","doi":"10.1016/j.trd.2025.105171","DOIUrl":"10.1016/j.trd.2025.105171","url":null,"abstract":"<div><div>Shared micro-mobility (SMM) services such as shared bikes, e-bikes, and e-scooters are increasingly promoted as sustainable transport solutions, yet barriers to adoption remain poorly understood, particularly among non-users. This study employs an explanatory sequential mixed-methods design, guided by the Social-Ecological Model (SEM), to analyse barriers to SMM use in three European cities. In phase one, an online survey conducted in Malmö (Sweden), Manchester (United Kingdom), and Utrecht (Netherlands) identified the prevalence and distribution of barriers across socio-demographic groups. In phase two, go-along interviews conducted in Utrecht built directly on these findings to explore how users and non-users experience barriers in everyday mobility. Findings highlight affordability, safety concerns, and service availability as persistent obstacles of non-users, while users emphasize flexibility and convenience. By integrating breadth and depth across SEM’s micro, meso, and macro levels, this study advances understanding of SMM non-adoption and provides guidance for more inclusive and equitable SMM policies.</div></div>","PeriodicalId":23277,"journal":{"name":"Transportation Research Part D-transport and Environment","volume":"152 ","pages":"Article 105171"},"PeriodicalIF":7.7,"publicationDate":"2025-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145786100","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}

引用次数: 0

Modelling sustainability of passenger fleet transition: Assessment of policy and environmental outcomes 客运机队转型的可持续性建模：政策和环境结果评估

IF 7.7 1区工程技术 Q1 ENVIRONMENTAL STUDIES

Transportation Research Part D-transport and Environment

Pub Date : 2025-12-18 DOI: 10.1016/j.trd.2025.105152

Michael M. Aba , Vinicius Picanco Rodrigues , T.C. Wong , Ildo Luís Sauer , Paulo Gonçalves

Being at the forefront of the global electric vehicle (EV) revolution with an amazing 96% of new electric car sales in 2024, it remains questionable if Norway can sustain this momentum over the long term. This study uses a system dynamics model to examine the key drivers of Norway’s transition to a zero-emission fleet, focusing on consumer behaviour, policy impacts, and energy-environmental outcomes. A key innovation is the integration of Hofstede’s cultural dimensions into the modeling of consumer behavior—an aspect overlooked in previous studies. Findings highlight the importance of vehicle range, affordability, and charging infrastructure. Sensitivity analysis emphasises the role of policy timing, infrastructure, and social influence in market dynamics. Scenario analysis predicts 97% EV sales by 2025 under current policies, with emissions declining by 59% by 2050. The study underscores the need for sustained incentives in the short term, infrastructure expansion, and technological innovation, offering insights for policymakers.

作为全球电动汽车（EV）革命的前沿，挪威在2024年的新电动汽车销量中占据了惊人的96%，但挪威能否长期保持这种势头仍是个问题。本研究使用系统动力学模型来研究挪威向零排放车队过渡的关键驱动因素，重点关注消费者行为、政策影响和能源环境结果。一个关键的创新是将Hofstede的文化维度整合到消费者行为模型中，这是以前的研究忽视的一个方面。调查结果强调了车辆续航里程、可负担性和充电基础设施的重要性。敏感性分析强调政策时机、基础设施和社会影响在市场动态中的作用。情景分析预测，在现行政策下，到2025年电动汽车销量将达到97%，到2050年排放量将下降59%。该研究强调了短期内持续激励、基础设施扩建和技术创新的必要性，为政策制定者提供了见解。

{"title":"Modelling sustainability of passenger fleet transition: Assessment of policy and environmental outcomes","authors":"Michael M. Aba , Vinicius Picanco Rodrigues , T.C. Wong , Ildo Luís Sauer , Paulo Gonçalves","doi":"10.1016/j.trd.2025.105152","DOIUrl":"10.1016/j.trd.2025.105152","url":null,"abstract":"<div><div>Being at the forefront of the global electric vehicle (EV) revolution with an amazing 96% of new electric car sales in 2024, it remains questionable if Norway can sustain this momentum over the long term. This study uses a system dynamics model to examine the key drivers of Norway’s transition to a zero-emission fleet, focusing on consumer behaviour, policy impacts, and energy-environmental outcomes. A key innovation is the integration of Hofstede’s cultural dimensions into the modeling of consumer behavior—an aspect overlooked in previous studies. Findings highlight the importance of vehicle range, affordability, and charging infrastructure. Sensitivity analysis emphasises the role of policy timing, infrastructure, and social influence in market dynamics. Scenario analysis predicts 97% EV sales by 2025 under current policies, with emissions declining by 59% by 2050. The study underscores the need for sustained incentives in the short term, infrastructure expansion, and technological innovation, offering insights for policymakers.</div></div>","PeriodicalId":23277,"journal":{"name":"Transportation Research Part D-transport and Environment","volume":"152 ","pages":"Article 105152"},"PeriodicalIF":7.7,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145771987","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}

引用次数: 0

Technical performance evolution of BEVs: range, consumption and weight projections to 2050 纯电动汽车的技术性能演变：到2050年的范围、消耗和重量预测

IF 7.7 1区工程技术 Q1 ENVIRONMENTAL STUDIES

Transportation Research Part D-transport and Environment

Pub Date : 2025-12-18 DOI: 10.1016/j.trd.2025.105172

Abdullah Isilti, James E. Tate

Battery Electric Vehicles (BEVs) are assuming a pivotal role in the road electrification, with continuous advancements in technology. This UK-focused study analyses the evolution of the technical parameters of BEVs between 2011 and 2024 and forecasts their development to 2050 for a range of scenarios (pessimistic, realistic and optimistic) focusing on range, energy consumption and vehicle weight. The research is underpinned by a data set of the technical specifications of 575 BEV models. The relationships between the parameters were revealed by machine learning (Random Forest and SHAP), with the forecast performed using the Prophet. The driving range of a typical C segment Sports Utility Vehicle (SUV) is forecast to increase by between 60 % and 180 %, vehicle weight and energy consumption varied between 1051–2000 kg and 267–286 Wh/mile, respectively, depending on the scenarios and underlying assumptions. The findings provide evidence-based insights for automotive technology planning and weight-based fiscal policy responses.

随着技术的不断进步，纯电动汽车（BEVs）在道路电气化中扮演着举足轻重的角色。这项以英国为重点的研究分析了2011年至2024年间纯电动汽车技术参数的演变，并对其到2050年的发展进行了一系列情景（悲观、现实和乐观）的预测，重点是续航里程、能耗和车辆重量。这项研究以575款纯电动汽车的技术规格数据集为基础。通过机器学习（随机森林和SHAP）揭示参数之间的关系，并使用Prophet进行预测。典型的C级运动型多功能车（SUV）的行驶里程预计将增加60%至180%，车辆重量和能耗分别在1051-2000公斤和267-286 Wh/mile之间变化，具体取决于不同的场景和潜在的假设。研究结果为汽车技术规划和基于权重的财政政策响应提供了基于证据的见解。

引用次数: 0

A generative physics-informed reinforcement learning-based approach for construction of representative drive cycle 一种基于生成物理的强化学习方法构建具有代表性的驾驶循环

IF 7.7 1区工程技术 Q1 ENVIRONMENTAL STUDIES

Transportation Research Part D-transport and Environment

Pub Date : 2025-12-17 DOI: 10.1016/j.trd.2025.105150

Amirreza Yasami, Mohamadali Tofigh, Mahdi Shahbakhti, Charles Robert Koch

Accurate driving cycle construction is crucial for vehicle design, fuel economy analysis, and environmental impact assessments. A generative Physics Informed Expected (State Action Reward State Action) SARSA-Monte Carlo (PIESMC) approach that constructs representative driving cycles by capturing transient dynamics, acceleration, deceleration, idling, and road grade transitions while ensuring model fidelity is introduced. Leveraging a physics-informed reinforcement learning framework with Monte Carlo sampling, PIESMC delivers efficient cycle construction with reduced computational cost. Experimental evaluations on two real-world datasets demonstrate that PIESMC replicates key kinematic and energy metrics, achieving up to an 83.9 % reduction in cumulative kinematic fragment errors compared to the Micro-trip-based (MTB) method and a 61.9 % reduction relative to the Markov-chain-based (MCB) method. Moreover, it is over an order of magnitude faster than conventional techniques, delivering more than a 30 ×  decrease in computational time. Analyses of vehicle-specific power distributions and wavelet-transformed frequency content further confirm its ability to reproduce experimental central tendencies and variability.

准确的行驶循环构建对于车辆设计、燃油经济性分析和环境影响评价至关重要。一种生成物理告知预期（状态动作奖励状态动作）SARSA-Monte Carlo （PIESMC）方法，通过捕获瞬态动力学、加速、减速、空转和道路坡度转换来构建具有代表性的驾驶循环，同时确保模型保真度。PIESMC利用具有蒙特卡罗采样的物理信息强化学习框架，以降低计算成本的方式提供高效的循环构建。在两个真实数据集上的实验评估表明，PIESMC复制了关键的运动学和能量指标，与基于微行程（MTB）的方法相比，累计运动学碎片误差减少了83.9%，与基于马尔可夫链（MCB）的方法相比，减少了61.9%。此外，它比传统技术快一个数量级以上，计算时间减少了30 × 以上。对车辆特定功率分布和小波变换频率内容的分析进一步证实了其再现实验中心趋势和可变性的能力。

{"title":"A generative physics-informed reinforcement learning-based approach for construction of representative drive cycle","authors":"Amirreza Yasami, Mohamadali Tofigh, Mahdi Shahbakhti, Charles Robert Koch","doi":"10.1016/j.trd.2025.105150","DOIUrl":"10.1016/j.trd.2025.105150","url":null,"abstract":"<div><div>Accurate driving cycle construction is crucial for vehicle design, fuel economy analysis, and environmental impact assessments. A generative Physics Informed Expected (State Action Reward State Action) SARSA-Monte Carlo (PIESMC) approach that constructs representative driving cycles by capturing transient dynamics, acceleration, deceleration, idling, and road grade transitions while ensuring model fidelity is introduced. Leveraging a physics-informed reinforcement learning framework with Monte Carlo sampling, PIESMC delivers efficient cycle construction with reduced computational cost. Experimental evaluations on two real-world datasets demonstrate that PIESMC replicates key kinematic and energy metrics, achieving up to an 83.9 % reduction in cumulative kinematic fragment errors compared to the Micro-trip-based (MTB) method and a 61.9 % reduction relative to the Markov-chain-based (MCB) method. Moreover, it is over an order of magnitude faster than conventional techniques, delivering more than a 30 ×  decrease in computational time. Analyses of vehicle-specific power distributions and wavelet-transformed frequency content further confirm its ability to reproduce experimental central tendencies and variability.</div></div>","PeriodicalId":23277,"journal":{"name":"Transportation Research Part D-transport and Environment","volume":"151 ","pages":"Article 105150"},"PeriodicalIF":7.7,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145785151","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}

引用次数: 0

Deep learning driven spatiotemporal prediction of global carbon emissions from container shipping 深度学习驱动的全球集装箱运输碳排放时空预测

IF 7.7 1区工程技术 Q1 ENVIRONMENTAL STUDIES

Transportation Research Part D-transport and Environment

Pub Date : 2025-12-17 DOI: 10.1016/j.trd.2025.105169

Hongchu Yu , Chenxi Jiang , Qinglong Fang , Tianming Wei , Lei Xu

Container shipping is a significant source of global CO₂ emissions, making accurate predictions essential for meeting international environmental targets. This study proposes ConvLSTM-CBAMNet, a deep learning model integrating channel and spatial attention mechanisms to capture complex spatiotemporal emission trends. The model significantly outperforms four deep learning baselines, including Transformer, ConvGRU, CNN-LSTM, and the traditional ConvLSTM. Compared to the strongest baseline, ConvLSTM, it demonstrates marked improvements, reducing the Root Mean Square Error (RMSE) by 19.4% to 0.0914 and the Mean Absolute Error (MAE) by 16.8% to 0.0432, while increasing the Structural Similarity Index (SSIM) by 5.8% to 0.9035. These predictions can inform targeted environmental policies, dynamically adjust Emission Control Areas (ECAs), optimize port scheduling to mitigate pollution peaks, and develop environmental early-warning systems, thereby supporting the shipping industry’s transition toward sustainability.

集装箱运输是全球二氧化碳排放的重要来源，准确的预测对于实现国际环境目标至关重要。本研究提出了一种融合通道和空间注意机制的深度学习模型ConvLSTM-CBAMNet，以捕捉复杂的时空发射趋势。该模型显著优于四个深度学习基线，包括Transformer、ConvGRU、CNN-LSTM和传统ConvLSTM。与最强基线ConvLSTM相比，它表现出明显的改善，将均方根误差（RMSE）降低19.4%至0.0914，平均绝对误差（MAE）降低16.8%至0.0432，而将结构相似指数（SSIM）提高5.8%至0.9035。这些预测可以为有针对性的环境政策提供信息，动态调整排放控制区（eca），优化港口调度以减轻污染高峰，并开发环境预警系统，从而支持航运业向可持续发展过渡。

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Transportation Research Part D-transport and Environment

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀