Pub Date : 2025-01-24DOI: 10.1016/j.tre.2025.103980
Xingwei Lu, Xianhao Xu, Yi Sun
In the face of unprecedented global supply chain disruptions, enhancing supply chain resilience (SCR) has become a critical priority. This empirical study examines the crucial role of resource orchestration, encompassing internal reconfiguration and external integration, across the three dynamic capabilities of SCR: readiness, response, and recovery. Additionally, it investigates the moderating effect of AI assimilation on these relationships. Grounded in Resource Orchestration Theory (ROT), this research analyzes data from 388 supply chain executives in China. The findings demonstrate that resource orchestration significantly enhances SCR across most capabilities, with the notable exception of external integration’s effect on the recovery. Interestingly, AI assimilation emerges as a key moderator, strengthening the relationship between internal reconfiguration and the SCR capabilities of readiness and recovery, while exhibiting a negligible effect on the response. This study contributes to the academic discourse by illuminating the complex interactions among ROT, SCR, and AI assimilation, offering valuable guidance for developing effective SCR strategies and highlight the pivotal role of AI assimilation in navigating the complexities of modern global supply chain challenges.
{"title":"Enhancing resilience in supply chains through resource orchestration and AI assimilation: An empirical exploration","authors":"Xingwei Lu, Xianhao Xu, Yi Sun","doi":"10.1016/j.tre.2025.103980","DOIUrl":"https://doi.org/10.1016/j.tre.2025.103980","url":null,"abstract":"In the face of unprecedented global supply chain disruptions, enhancing supply chain resilience (SCR) has become a critical priority. This empirical study examines the crucial role of resource orchestration, encompassing internal reconfiguration and external integration, across the three dynamic capabilities of SCR: readiness, response, and recovery. Additionally, it investigates the moderating effect of AI assimilation on these relationships. Grounded in Resource Orchestration Theory (ROT), this research analyzes data from 388 supply chain executives in China. The findings demonstrate that resource orchestration significantly enhances SCR across most capabilities, with the notable exception of external integration’s effect on the recovery. Interestingly, AI assimilation emerges as a key moderator, strengthening the relationship between internal reconfiguration and the SCR capabilities of readiness and recovery, while exhibiting a negligible effect on the response. This study contributes to the academic discourse by illuminating the complex interactions among ROT, SCR, and AI assimilation, offering valuable guidance for developing effective SCR strategies and highlight the pivotal role of AI assimilation in navigating the complexities of modern global supply chain challenges.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"49 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143027372","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}
In emergency disaster response, the dynamic nature and uncertainty of resource transportation pose significant challenges for vehicle routing planning. We address a truck-drone collaborative routing problem in humanitarian logistics, where a set of truck-drone tandems collaboratively deliver relief resources from a distribution center to a set of affected areas which is dynamically updated as disaster changes. In the truck-drone collaborative mode, as each truck performs the delivery services and serves as a mobile depot for the drone associated with it, the drone launches from its associated truck at a node, delivers relief resources to one affected area, and returns to rendezvous with the truck at the node or another node along the truck route. We cast the problem as a Markov game model with an event-driven method, which can effectively capture the dynamic changes in the states and node information of trucks and drones during relief resources delivery. To solve the model, we develop a multi-agent deep reinforcement learning algorithm, which combines prioritized experience replay and invalid action masking to improve the sample efficiency and reduce the decision space. We conduct extensive numerical studies to validate the effectiveness of the proposed method by comparing it with existing solution methods and two well-known heuristic rules, and discuss the impacts of some model parameters on the solution performance. We also assess the advantages of the truck-drone collaborative mode over the truck/helicopter-only mode through a case study of the 2008 Wenchuan earthquake.
{"title":"Multi-agent deep reinforcement learning-based truck-drone collaborative routing with dynamic emergency response","authors":"Wenhao Peng, Dujuan Wang, Yunqiang Yin, T.C.E. Cheng","doi":"10.1016/j.tre.2025.103974","DOIUrl":"https://doi.org/10.1016/j.tre.2025.103974","url":null,"abstract":"In emergency disaster response, the dynamic nature and uncertainty of resource transportation pose significant challenges for vehicle routing planning. We address a truck-drone collaborative routing problem in humanitarian logistics, where a set of truck-drone tandems collaboratively deliver relief resources from a distribution center to a set of affected areas which is dynamically updated as disaster changes. In the truck-drone collaborative mode, as each truck performs the delivery services and serves as a mobile depot for the drone associated with it, the drone launches from its associated truck at a node, delivers relief resources to one affected area, and returns to rendezvous with the truck at the node or another node along the truck route. We cast the problem as a Markov game model with an event-driven method, which can effectively capture the dynamic changes in the states and node information of trucks and drones during relief resources delivery. To solve the model, we develop a multi-agent deep reinforcement learning algorithm, which combines prioritized experience replay and invalid action masking to improve the sample efficiency and reduce the decision space. We conduct extensive numerical studies to validate the effectiveness of the proposed method by comparing it with existing solution methods and two well-known heuristic rules, and discuss the impacts of some model parameters on the solution performance. We also assess the advantages of the truck-drone collaborative mode over the truck/helicopter-only mode through a case study of the 2008 Wenchuan earthquake.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"19 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143027370","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}
This study presents a comprehensive decision-making framework that employs eXplainable Artificial Intelligence (XAI)-based methods to improve proactive road transport safety management, which is critical for global supply chain networks. The framework offers explainable predictions as well as suggestions pertaining to the near-future digitization of safety tools and their usage, customized for road transport safety management. We employed four black-box machine learning-based models—artificial neural network (ANN), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost)—in this setting to enhance our comprehension of the crash-related risk factors that contribute to the severity of traffic accident injuries. Due to their opaqueness and complex inner workings, stakeholders often perceive these models as data-driven black-box approaches, making them incapable of providing an efficient decision-support tool. The recommended decision support incorporates agreement levels for predictions and interpretation across various XAI modeling paradigms. We deploy PFI (Permutation Feature Importance) and FIRM (Feature Importance Ranking Measures) tools to evaluate the extent of agreement in explainability between these various modeling approaches. The recommendations are based on PFI and FIRM values of highly performing models. We execute the framework as an illustration of the concept using a real crash dataset obtained from the NHTSA (National Highway Transportation Safety Administration of the United States) and report end-user feedback for use by transport policymakers.
{"title":"An interpretable machine learning framework for enhancing road transportation safety","authors":"Ismail Abdulrashid, Wen-Chyuan Chiang, Jiuh-Biing Sheu, Shamkhal Mammadov","doi":"10.1016/j.tre.2025.103969","DOIUrl":"https://doi.org/10.1016/j.tre.2025.103969","url":null,"abstract":"This study presents a comprehensive decision-making framework that employs eXplainable Artificial Intelligence (XAI)-based methods to improve proactive road transport safety management, which is critical for global supply chain networks. The framework offers explainable predictions as well as suggestions pertaining to the near-future digitization of safety tools and their usage, customized for road transport safety management. We employed four black-box machine learning-based models—artificial neural network (ANN), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost)—in this setting to enhance our comprehension of the crash-related risk factors that contribute to the severity of traffic accident injuries. Due to their opaqueness and complex inner workings, stakeholders often perceive these models as data-driven black-box approaches, making them incapable of providing an efficient decision-support tool. The recommended decision support incorporates agreement levels for predictions and interpretation across various XAI modeling paradigms. We deploy PFI (Permutation Feature Importance) and FIRM (Feature Importance Ranking Measures) tools to evaluate the extent of agreement in explainability between these various modeling approaches. The recommendations are based on PFI and FIRM values of highly performing models. We execute the framework as an illustration of the concept using a real crash dataset obtained from the NHTSA (National Highway Transportation Safety Administration of the United States) and report end-user feedback for use by transport policymakers.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"38 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143027375","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}
Pub Date : 2025-01-20DOI: 10.1016/j.tre.2024.103952
Xuanyi Shi, Daniel Prajogo, Di Fan, Adegoke Oke
In this increasingly highly turbulent environment, firms are facing demand changes, many of which are unpredictable. Furthermore, the magnitude of such uncertainties is unpredictable. Thus, firms have limited options as to how to prepare for such uncertainties. A viable strategy that firms may employ to cope with uncertainties effectively is operational flexibility. Firms’ operational flexibility is the ability of the operational system of a firm including processes and people, to cope with uncertainty without expending new resources or enlarging the range of operating costs. Studies have examined the role of operational flexibility as a mechanism for mitigating mundane supply chain risks; however, the effectiveness of operational flexibility in sustaining firms’ performance when facing a global and major disruptions to supply chains remains underexamined. This paper contributes to the supply chain resilience and risk management literature by examining the effectiveness of operational flexibility as a mitigation strategy for major supply chain disruptions. Against the backdrop of the COVID-19 pandemic, we found that U.S. manufacturing firms with higher operational flexibility exhibited higher abnormal inventory growth, fewer employment reductions, and higher operational efficiency during the global major supply chain disruptions caused by the COVID-19 pandemic. In addition, we found that smaller firms gain more from operational flexibility in inventory management, while those with strong adaptive capacity benefit more from retaining human resources to enhance operational efficiency during major disruptions. Our study contributes to the importance and effectiveness of operational flexibility in enabling manufacturing firms to thrive during major supply chain disruptions.
{"title":"Is operational flexibility a viable strategy during major supply chain disruptions? Evidence from the COVID-19 pandemic","authors":"Xuanyi Shi, Daniel Prajogo, Di Fan, Adegoke Oke","doi":"10.1016/j.tre.2024.103952","DOIUrl":"https://doi.org/10.1016/j.tre.2024.103952","url":null,"abstract":"In this increasingly highly turbulent environment, firms are facing demand changes, many of which are unpredictable. Furthermore, the magnitude of such uncertainties is unpredictable. Thus, firms have limited options as to how to prepare for such uncertainties. A viable strategy that firms may employ to cope with uncertainties effectively is operational flexibility. Firms’ operational flexibility is the ability of the operational system of a firm including processes and people, to cope with uncertainty without expending new resources or enlarging the range of operating costs. Studies have examined the role of operational flexibility as a mechanism for mitigating mundane supply chain risks; however, the effectiveness of operational flexibility in sustaining firms’ performance when facing a global and major disruptions to supply chains remains underexamined. This paper contributes to the supply chain resilience and risk management literature by examining the effectiveness of operational flexibility as a mitigation strategy for major supply chain disruptions. Against the backdrop of the COVID-19 pandemic, we found that U.S. manufacturing firms with higher operational flexibility exhibited higher abnormal inventory growth, fewer employment reductions, and higher operational efficiency during the global major supply chain disruptions caused by the COVID-19 pandemic. In addition, we found that smaller firms gain more from operational flexibility in inventory management, while those with strong adaptive capacity benefit more from retaining human resources to enhance operational efficiency during major disruptions. Our study contributes to the importance and effectiveness of operational flexibility in enabling manufacturing firms to thrive during major supply chain disruptions.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"18 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143027378","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}
Pub Date : 2025-01-20DOI: 10.1016/j.tre.2024.103949
Amirali Amirsahami, Farnaz Barzinpour, Mir Saman Pishvaee
The urgent need for rapid disaster response mechanisms, particularlyin the event ofearthquakes, is critical. In response to directives from the National Crisis Management Supreme Council, a plan has been initiated to establish distribution centers across all zones of Tehran, Iran,which signalsa significant shift towards decentralization. However, land scarcity and road blockages hinder thefull realization ofa decentralized structure in certain zones. To address these challenges, two strategies have been proposed: facility expansion and drone-aided delivery. The integration of these strategies has led to the development of a novel structure, the hybrid decentralized humanitarian relief chain with simultaneous utilization of trucks and drones (HDHRC-TD). Mathematical optimization techniques are employed to model the distribution of relief items during the pre-disaster preparedness stage, especially in the critical first hours following an earthquake. The system is treated as a two-echelon network. Additionally, to account for the negative impact of uncertainty in road network connectivity, truck travel time is modeled as an uncertain parameter. A novel simulation-based bi-objective fuzzy chance-constrained programming (SBFCCP) model is introduced to manage this uncertainty.To ensure the model can be solved within a reasonable time frame, a hybrid metaheuristic algorithm, the modified NSGA-II with adaptive VNS algorithm (M−NSGA−II−AVNS), is employed. The facility expansion strategy reduces establishment costs to 25% of those of a fully decentralized system, while achieving 77% of its response time reduction. The drone-aided delivery strategy further enhances disaster response by improving access to more roads, significantly reducing total waiting times. Moreover, validation of the proposed model confirms its accuracy in managing uncertainty, further supporting the cost-effectiveness and resiliency of the proposed structure for urban disaster response.
{"title":"A fuzzy programming model for decentralization and drone utilization in urban humanitarian relief chains","authors":"Amirali Amirsahami, Farnaz Barzinpour, Mir Saman Pishvaee","doi":"10.1016/j.tre.2024.103949","DOIUrl":"https://doi.org/10.1016/j.tre.2024.103949","url":null,"abstract":"The urgent need for rapid disaster response mechanisms, particularly<ce:hsp sp=\"0.25\"></ce:hsp>in the event of<ce:hsp sp=\"0.25\"></ce:hsp>earthquakes, is critical. In response to directives from the National Crisis Management Supreme Council, a plan has been initiated to establish distribution centers across all zones of Tehran, Iran,<ce:hsp sp=\"0.25\"></ce:hsp>which signals<ce:hsp sp=\"0.25\"></ce:hsp>a significant shift towards decentralization. However, land scarcity and road blockages hinder the<ce:hsp sp=\"0.25\"></ce:hsp>full realization of<ce:hsp sp=\"0.25\"></ce:hsp>a decentralized structure in certain zones. To address these challenges, two strategies have been proposed: facility expansion and drone-aided delivery. The integration of these strategies has led to the development of a novel structure, the hybrid decentralized humanitarian relief chain with simultaneous utilization of trucks and drones (HDHRC-TD). Mathematical optimization techniques are employed to model the distribution of relief items during the pre-disaster preparedness stage, especially in the critical first hours following an earthquake. The system is treated as a two-echelon network. Additionally, to account for the negative impact of uncertainty in road network connectivity, truck travel time is modeled as an uncertain parameter. A novel simulation-based bi-objective fuzzy chance-constrained programming (SBFCCP) model is introduced to manage this uncertainty.<ce:hsp sp=\"0.25\"></ce:hsp>To ensure the model can be solved within a reasonable time frame, a hybrid metaheuristic algorithm, the modified NSGA-II with adaptive VNS algorithm (M−NSGA−II−AVNS), is employed. The facility expansion strategy reduces establishment costs to 25% of those of a fully decentralized system, while achieving 77% of its response time reduction. The drone-aided delivery strategy further enhances disaster response by improving access to more roads, significantly reducing total waiting times. Moreover, validation of the proposed model confirms its accuracy in managing uncertainty, further supporting the cost-effectiveness and resiliency of the proposed structure for urban disaster response.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"120 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143027379","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}
Pub Date : 2025-01-20DOI: 10.1016/j.tre.2025.103965
Xiangdong Chen, Hao Guan, Qiang Meng
In the initial phase of implementing connected and automated vehicle (CAV) technology, the coexistence of human-driven vehicles (HVs) and CAVs is anticipated for the foreseeable future. While dedicated CAV lane is recognized as an effective solution to enhance traffic safety and efficiency in mixed traffic scenarios, it faces the challenges of road resource wastage, especially at low CAV penetration rates. Therefore, this study proposes a novel concept of a shared CAV lane for both connected and automated buses (CABs) and private CAVs, and develops a multi-green-wave control method for arterials to achieve space–time coordination in heterogeneous traffic. The two-dimensional traffic coordination aims to concurrently improve the service level of CABs and enhance overall traffic efficiency. A three-scale framework is established to integrate the control problems at the lane, intersection, and arterial levels. With the deployment of CAV lanes, lane-specified flow distribution control problem is investigated at the lane level, and a dedicated phase is designed to provide exclusive right-of-ways for CAVs, and jointed with an online conflict-free control strategy at the intersection level. Building upon this, a multiple green-wave design is developed for heterogeneous traffic at arterials, to take full exploit of the space–time resources of both CAV lanes and regular lanes and further improve traffic efficiency. To address the challenges of large-scale and complicated-structure optimization and enable real-time implementation, a hierarchical solution method is proposed. The original problem is decomposed into sub-problems, which can be efficiently solved with an approximation approach to relax the bounding constraints among them. Simulation experiments conducted on an arterial in Singapore validate the performance of the proposed methods. The results demonstrate that the proposed two-dimensional coordination strategy significantly improves traffic efficiency compared to other classic counterpart strategies, reducing the average travel delay for CABs, private CAVs, and HVs by at least 20.4%, 37.4%, and 21.4%, respectively.
{"title":"Shared use of dedicated lanes by connected and automated buses and private vehicles: A multi-green-wave signal control scheme","authors":"Xiangdong Chen, Hao Guan, Qiang Meng","doi":"10.1016/j.tre.2025.103965","DOIUrl":"https://doi.org/10.1016/j.tre.2025.103965","url":null,"abstract":"In the initial phase of implementing connected and automated vehicle (CAV) technology, the coexistence of human-driven vehicles (HVs) and CAVs is anticipated for the foreseeable future. While dedicated CAV lane is recognized as an effective solution to enhance traffic safety and efficiency in mixed traffic scenarios, it faces the challenges of road resource wastage, especially at low CAV penetration rates. Therefore, this study proposes a novel concept of a shared CAV lane for both connected and automated buses (CABs) and private CAVs, and develops a multi-green-wave control method for arterials to achieve space–time coordination in heterogeneous traffic. The two-dimensional traffic coordination aims to concurrently improve the service level of CABs and enhance overall traffic efficiency. A three-scale framework is established to integrate the control problems at the lane, intersection, and arterial levels. With the deployment of CAV lanes, lane-specified flow distribution control problem is investigated at the lane level, and a dedicated phase is designed to provide exclusive right-of-ways for CAVs, and jointed with an online conflict-free control strategy at the intersection level. Building upon this, a multiple green-wave design is developed for heterogeneous traffic at arterials, to take full exploit of the space–time resources of both CAV lanes and regular lanes and further improve traffic efficiency. To address the challenges of large-scale and complicated-structure optimization and enable real-time implementation, a hierarchical solution method is proposed. The original problem is decomposed into sub-problems, which can be efficiently solved with an approximation approach to relax the bounding constraints among them. Simulation experiments conducted on an arterial in Singapore validate the performance of the proposed methods. The results demonstrate that the proposed two-dimensional coordination strategy significantly improves traffic efficiency compared to other classic counterpart strategies, reducing the average travel delay for CABs, private CAVs, and HVs by at least 20.4%, 37.4%, and 21.4%, respectively.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"63 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143027377","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}
Pub Date : 2025-01-19DOI: 10.1016/j.tre.2024.103886
J. Gong, W.Y. Szeto, S. Sun
Transit frequency design is critical in determining the performance of public transit services. In the literature, single-period frequency design is often considered but ignores the demand variation over time of day. Moreover, in high-demand bus networks, the demand patterns are asymmetric in both directions of some bus routes. This study investigates a bus operation strategy to address these two issues. In this strategy, for each route, a class of buses serves both directions while the other class only serves one direction with high travel demand, leading to the two directions having different frequencies. A bilevel optimization problem is formulated for this strategy. The upper level problem is a multi-period asymmetric transit frequency design problem, which aims to determine the route frequencies of different classes of buses associated with each period to maximize the operating profit or social welfare. This upper level problem also considers deadhead trips between the bus depot and terminals or between terminals of different routes across periods. The lower level problem is a schedule-based user equilibrium transit assignment problem, taking elastic demand, the common line choice of passengers, and capacity constraints into account. A hybrid algorithm combining an enhanced artificial bee colony algorithm with the method of successive averages is proposed to tackle the bilevel optimization problem and then applied to the study of the Tin Shui Wai bus network to demonstrate the model properties. The effectiveness of the proposed algorithm is also examined. The results indicate that the proposed algorithm can produce better solutions compared with the modified hybrid genetic algorithm. Moreover, the proposed multi-period asymmetric design outperforms the existing design, which can achieve less passenger travel time and greater demand satisfaction, operating profit, and social welfare.
{"title":"A multi-period asymmetric transit frequency design problem","authors":"J. Gong, W.Y. Szeto, S. Sun","doi":"10.1016/j.tre.2024.103886","DOIUrl":"https://doi.org/10.1016/j.tre.2024.103886","url":null,"abstract":"Transit frequency design is critical in determining the performance of public transit services. In the literature, single-period frequency design is often considered but ignores the demand variation over time of day. Moreover, in high-demand bus networks, the demand patterns are asymmetric in both directions of some bus routes. This study investigates a bus operation strategy to address these two issues. In this strategy, for each route, a class of buses serves both directions while the other class only serves one direction with high travel demand, leading to the two directions having different frequencies. A bilevel optimization problem is formulated for this strategy. The upper level problem is a multi-period asymmetric transit frequency design problem, which aims to determine the route frequencies of different classes of buses associated with each period to maximize the operating profit or social welfare. This upper level problem also considers deadhead trips between the bus depot and terminals or between terminals of different routes across periods. The lower level problem is a schedule-based user equilibrium transit assignment problem, taking elastic demand, the common line choice of passengers, and capacity constraints into account. A hybrid algorithm combining an enhanced artificial bee colony algorithm with the method of successive averages is proposed to tackle the bilevel optimization problem and then applied to the study of the Tin Shui Wai bus network to demonstrate the model properties. The effectiveness of the proposed algorithm is also examined. The results indicate that the proposed algorithm can produce better solutions compared with the modified hybrid genetic algorithm. Moreover, the proposed multi-period asymmetric design outperforms the existing design, which can achieve less passenger travel time and greater demand satisfaction, operating profit, and social welfare.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"206 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143027380","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}
Pub Date : 2025-01-18DOI: 10.1016/j.tre.2025.103963
Chenliang Zhang, Zhongyi Jin, Kam K.H. Ng, Tie-Qiao Tang, Fangni Zhang, Wei Liu
With the increasing demand for air transport, numerous airports have exceeded their available capacity, resulting in more frequent congestion and disruptions. Therefore, airport gate assignment plans must prioritise robustness to alleviate congestion, absorb disruptions, and maintain high service levels. Given the uncertainties in airside operations, providing robust decisions is challenging. To address this issue, we employ two prescriptive analytics approaches to develop airport gate assignment plans. These approaches leverage historical data, auxiliary data, and machine learning (ML) methods to enhance decision effectiveness and robustness. Initially, we adopt a predict-then-optimise approach, utilising ML methods to predict aircraft arrival times. These predictions are then used as input for a deterministic model of the airport gate assignment problem (AGAP). Subsequently, we explore an estimate-then-optimise approach. In this approach, we first estimate the distribution of uncertain aircraft arrival times using ML methods. Then, we solve the two-stage stochastic programming model for the AGAP based on the estimated distribution. Given the complexity of the estimate-then-optimise approach, we develop an effective scenario selection strategy, the cluster-based scenario reduction (CSR) method, to maintain tractability while ensuring decision performance. Concurrently, we develop an efficient exact solution method, the Benders-based branch-and-cut (BBC) method, to effectively handle larger and more complex test instances. Numerical experiments using real-world data from Xiamen Gaoqi International Airport demonstrate the effectiveness of the CSR and BBC methods. The CSR method performs better with a smaller sample size, while the BBC method significantly enhances computational performance compared to commercial solvers. These proposed methods improve the tractability and scalability of the estimate-then-optimise approach. Notably, the estimate-then-optimise approach outperforms the predict-then-optimise approach driven by the same ML method. Furthermore, we find that estimate-then-optimise approaches, supported by well-performing ML methods and scenario selection strategies, provide superior performance compared to other optimisation approaches.
{"title":"Predictive and prescriptive analytics for robust airport gate assignment planning in airside operations under uncertainty","authors":"Chenliang Zhang, Zhongyi Jin, Kam K.H. Ng, Tie-Qiao Tang, Fangni Zhang, Wei Liu","doi":"10.1016/j.tre.2025.103963","DOIUrl":"https://doi.org/10.1016/j.tre.2025.103963","url":null,"abstract":"With the increasing demand for air transport, numerous airports have exceeded their available capacity, resulting in more frequent congestion and disruptions. Therefore, airport gate assignment plans must prioritise robustness to alleviate congestion, absorb disruptions, and maintain high service levels. Given the uncertainties in airside operations, providing robust decisions is challenging. To address this issue, we employ two prescriptive analytics approaches to develop airport gate assignment plans. These approaches leverage historical data, auxiliary data, and machine learning (ML) methods to enhance decision effectiveness and robustness. Initially, we adopt a predict-then-optimise approach, utilising ML methods to predict aircraft arrival times. These predictions are then used as input for a deterministic model of the airport gate assignment problem (AGAP). Subsequently, we explore an estimate-then-optimise approach. In this approach, we first estimate the distribution of uncertain aircraft arrival times using ML methods. Then, we solve the two-stage stochastic programming model for the AGAP based on the estimated distribution. Given the complexity of the estimate-then-optimise approach, we develop an effective scenario selection strategy, the cluster-based scenario reduction (CSR) method, to maintain tractability while ensuring decision performance. Concurrently, we develop an efficient exact solution method, the Benders-based branch-and-cut (BBC) method, to effectively handle larger and more complex test instances. Numerical experiments using real-world data from Xiamen Gaoqi International Airport demonstrate the effectiveness of the CSR and BBC methods. The CSR method performs better with a smaller sample size, while the BBC method significantly enhances computational performance compared to commercial solvers. These proposed methods improve the tractability and scalability of the estimate-then-optimise approach. Notably, the estimate-then-optimise approach outperforms the predict-then-optimise approach driven by the same ML method. Furthermore, we find that estimate-then-optimise approaches, supported by well-performing ML methods and scenario selection strategies, provide superior performance compared to other optimisation approaches.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"13 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143027384","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}
Pub Date : 2025-01-18DOI: 10.1016/j.tre.2025.103967
Siyavash Filom, Saiedeh Razavi
Synchromodal freight transport is characterized by its inherent dynamicity, necessitating the need for optimal decision-making in the presence of uncertainties in the real world. However, most prior research has overlooked the complexities of uncertainty modeling, often relying on assumed probability distributions that may not accurately reflect real-world conditions. This study presents a learning-based robust optimization framework for synchromodal freight transportation to derive data-driven explainable decisions. The study proposes a predict-then-optimize framework, using a combination of the Bayesian Neural Network with uncertainty quantification and dynamic robust optimization modules to solve the shipment matching problem under the synchromodality concept. The integration of prediction and optimization modules is achieved through scenario-based adjustable uncertainty sets. Rather than generating a single optimal solution, this framework produces an optimal policy based on various scenarios, enabling decision-makers to evaluate trade-offs and make informed decisions. The framework is implemented for the Great Lakes region containing nine intermodal terminals using real-world data and the performance is evaluated under various scenarios. In addition, a preprocessing heuristic-based feasible path generation algorithm is developed that helps the framework to maintain linear solution time. Numerical experiments performed on large demand instances (up to 700 shipment requests) demonstrate that the upstream prediction module significantly impacts the downstream optimization module. This effect is primarily due to variations in road travel times across scenarios, which impact transshipment operations, storage, and delay costs.
{"title":"A learning-based robust optimization framework for synchromodal freight transportation under uncertainty","authors":"Siyavash Filom, Saiedeh Razavi","doi":"10.1016/j.tre.2025.103967","DOIUrl":"https://doi.org/10.1016/j.tre.2025.103967","url":null,"abstract":"Synchromodal freight transport is characterized by its inherent dynamicity, necessitating the need for optimal decision-making in the presence of uncertainties in the real world. However, most prior research has overlooked the complexities of uncertainty modeling, often relying on assumed probability distributions that may not accurately reflect real-world conditions. This study presents a learning-based robust optimization framework for synchromodal freight transportation to derive data-driven explainable decisions. The study proposes a predict-then-optimize framework, using a combination of the Bayesian Neural Network with uncertainty quantification and dynamic robust optimization modules to solve the shipment matching problem under the synchromodality concept. The integration of prediction and optimization modules is achieved through scenario-based adjustable uncertainty sets. Rather than generating a single optimal solution, this framework produces an optimal policy based on various scenarios, enabling decision-makers to evaluate trade-offs and make informed decisions. The framework is implemented for the Great Lakes region containing nine intermodal terminals using real-world data and the performance is evaluated under various scenarios. In addition, a preprocessing heuristic-based feasible path generation algorithm is developed that helps the framework to maintain linear solution time. Numerical experiments performed on large demand instances (up to 700 shipment requests) demonstrate that the upstream prediction module significantly impacts the downstream optimization module. This effect is primarily due to variations in road travel times across scenarios, which impact transshipment operations, storage, and delay costs.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"76 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143027381","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}
Pub Date : 2025-01-17DOI: 10.1016/j.tre.2025.103971
Peng Peng, Xiaowei Xie, Christophe Claramunt, Feng Lu, Fuzhong Gong, Ran Yan
Maritime cybersecurity has emerged as a critical and rapidly evolving research field, necessitated by the increasing reliance on digital technologies and interconnectivity within the global maritime industry. In this paper, we adopt a bibliometric analysis method to review the existing academic publications pertaining to maritime cybersecurity, aiming to provide a comprehensive overview of the development status and research focus. The results show that: 1) Research on maritime cybersecurity is currently undergoing significant development; 2) Most articles on marine cybersecurity are published by researchers from North America and Europe, with most of them stem from the US, Norway, and UK; 3) Most international collaborations are limited at a regional level, and the major regions include North America and Europe; 4) Five closely related research keyword communities show that maritime cybersecurity research hotspots focus on transport-related cyber-attacks, autonomous vessel, AIS, maritime communication, and UAV. The above thorough examination of the current research on maritime cybersecurity also shows that there are some weaknesses in existing studies. For example, the research topic of maritime cybersecurity has not yet received adequate attention and the research hotspot is relatively concentrated. Based on the findings, we propose perspectives of the research on maritime cybersecurity from the aspects of the effectiveness of regulations, funding and investment opportunities, digitalization in the maritime industry and cybersecurity, advances in maritime communication systems, and unmanned aerial vehicles and maritime cybersecurity.
{"title":"Bibliometric analysis of maritime cybersecurity: Research status, focus, and perspectives","authors":"Peng Peng, Xiaowei Xie, Christophe Claramunt, Feng Lu, Fuzhong Gong, Ran Yan","doi":"10.1016/j.tre.2025.103971","DOIUrl":"https://doi.org/10.1016/j.tre.2025.103971","url":null,"abstract":"Maritime cybersecurity has emerged as a critical and rapidly evolving research field, necessitated by the increasing reliance on digital technologies and interconnectivity within the global maritime industry. In this paper, we adopt a bibliometric analysis method to review the existing academic publications pertaining to maritime cybersecurity, aiming to provide a comprehensive overview of the development status and research focus. The results show that: 1) Research on maritime cybersecurity is currently undergoing significant development; 2) Most articles on marine cybersecurity are published by researchers from North America and Europe, with most of them stem from the US, Norway, and UK; 3) Most international collaborations are limited at a regional level, and the major regions include North America and Europe; 4) Five closely related research keyword communities show that maritime cybersecurity research hotspots focus on transport-related cyber-attacks, autonomous vessel, AIS, maritime communication, and UAV. The above thorough examination of the current research on maritime cybersecurity also shows that there are some weaknesses in existing studies. For example, the research topic of maritime cybersecurity has not yet received adequate attention and the research hotspot is relatively concentrated. Based on the findings, we propose perspectives of the research on maritime cybersecurity from the aspects of the effectiveness of regulations, funding and investment opportunities, digitalization in the maritime industry and cybersecurity, advances in maritime communication systems, and unmanned aerial vehicles and maritime cybersecurity.","PeriodicalId":49418,"journal":{"name":"Transportation Research Part E-Logistics and Transportation Review","volume":"5 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142988503","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：