ERC TRUST

1. A machine learning-based Bayesian model for predicting the duration of ship detention in PSC inspection

Transportation Research Part E: Logistics and Transportation Review, 2023

Port state control (PSC) inspections are deemed as an effective way to detect substandard vessels and ensure maritime safety around the world. Despite great efforts on PSC in recent years, one challenge that still exists in today’s PSC inspection practice is that there lack relevant scheme or academic research focusing on the duration of vessel detention, which is of great importance to the inspection system. To assist port authorities in estimating detention duration and minimizing the existence of substandard vessels, this paper aims to develop a novel data-driven machine learning based model based on the inspection records collected within the jurisdiction of Paris MoU from January 2015 to March 2022. The model is trained via the incorporation of an Improved Tree Augmented Naïve (ITAN) learning approach and a maximum a posteriori probability (MAP) of Expectation Maximization (EM) approach for the first time within the context of PSC research, which could be used as a prediction tool to determine rational durations for detained vessels. Thorough analysis of the proposed model enables the identification of risk variables and deficiency types having significant effects leading to long duration of detention. Further, the research findings could reveal managerial suggestions and insights for port authorities to reduce the occurrence of substandard vessels via the inspection system, i.e., identify specific risk level of vessels and ensure a more-efficient vessel selection process; design specific instructions and rules to regulate risk variables and deficiencies with huge effect on a long duration of detention. This research will provide insightful reference for effectively improving vessel quality, inspection efficiency, and maritime safety.

2. Quantification of CO2 emissions in transportation: An empirical analysis by modal shift from road to waterway transport in China

Transport Policy, 2024

In view of the huge contribution of transportation to global greenhouse gas emissions, it is imperative to embrace more carbon-efficient transportation modes to support our environmental goals. However, few studies offer empirical evidence to evaluate the potential of shifting transportation model for carbon emissions reduction. This paper, aiming at addressing this gap, conducts an empirical study to assess the CO2 emissions reduction through modal shift from road to waterway transport (MSRW). It utilizes primary data collected from more than 200 voyages of 92 enterprises through one national pilot project on CO2 emission reduction in the Quzhou region initiated by the Chinese central government. Specifically, it employs empirical analysis based on bottom-up methodologies to investigate the potential for CO2 emission reduction through MSRW. The results reveal that MSRW can aid to benefit 45,907 tons CO2 emission reduction from the modal shift within the study scope. When considering factors such as distance and voyage density, it provides new quantitative insights into the advantages of water transport over road transport in terms of CO2 emission reduction under different scenarios. Consequently, this study makes new contributions to the quantification of the benefits that an investigated region/city can derive from transport modal shift. It thereby lays the groundwork for effective cost-benefit analysis and policy implementation toward cleaner transportation.

3. Towards safe navigation environment: the imminent role of spatio-temporal pattern mining in maritime piracy incidents analysis

Reliability Engineering and System Safety, 2023

Since the new century, we have witnessed the fast evolution of pirate attack modes in terms of locations, time, used weapons, and targeted ships. It reveals that the current understanding of pirate attack spatio-temporal patterns is fading, requiring new technologies of big data analysis to master the hidden rules of piracy-related risk spatio-temporal patterns and rationalize the development of relevant anti-piracy measures and policies. This paper aims to develop a new framework of spatio-temporal pattern mining to realize the visualization and analysis of maritime piracy incidents from different standpoints using a new piracy incident database generated from three datasets. Time-based, space-based, and spatial-temporal pattern mining of piracy incidents are systematically investigated to dissect the influence of different risk factors and mine the characteristics of the incidents. Moreover, a novel Fast Adaptive Dynamic Time Warping (FADTW) method is proposed to uncover the hidden temporal and spatial-temporal patterns of piracy incidents. Furthermore, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) is applied to extract the spatial distribution patterns and discover the high-risk areas. Finally, risk factors-based classification exploration has uncovered different spatial patterns. The findings, showing the global and local features of piracy incidents, have made significant contributions to rationalizing anti-pirate measures for safe navigation.

4. Applications, evolutions and challenges of drones in maritime transport

Journal of Marine Science and Engineering, 2023

The widespread interest in using drones in maritime transport has rapidly grown alongside the development of unmanned ships and drones. To stimulate growth and address the associated technical challenges, this paper systematically reviews the relevant research progress, classification, applications, technical challenges, and possible solutions related to the use of drones in the maritime sector. The findings provide an overview of the state of the art of the applications of drones in the maritime industry over the past 20 years and identify the existing problems and bottlenecks in this field. A new classification scheme is established based on their flight characteristics to aid in distinguishing drones’ applications in maritime transport. Further, this paper discusses the specific use cases and technical aspects of drones in maritime rescue, safety, navigation, environment, communication, and other aspects, providing in-depth guidance on the future development of different mainstream applications. Lastly, the challenges facing drones in these applications are identified, and the corresponding solutions are proposed to address them. This research offers pivotal insights and pertinent knowledge beneficial to various entities such as maritime regulatory bodies, shipping firms, academic institutions, and enterprises engaged in drone production. This paper makes new contributions in terms of the comprehensive analysis and discussion of the application of drones in maritime transport and the provision of guidance and support for promoting their further development and integration with intelligent transport.

5. Ship trajectory prediction based on machine learning and deep learning: A systematic review and methods analysis

Engineering Applications of Artificial Intelligence, 2023

Ship trajectory prediction based on Automatic Identification System (AIS) data has attracted increasing interest as it helps prevent collision accidents and eliminate potential navigational conflicts. Therefore, it is necessary and urgent to conduct a systematic analysis of all the prediction methods to help reveal their advantages to ensure safety at sea in different scenarios. It is particularly important and significant within the context of unmanned ships forming a new hybrid maritime traffic together with manned ships in the future. This paper aims to conduct a comparative analysis of the up-to-date ship trajectory prediction algorithms based on machine learning and deep learning methods. To do so, five classical machine learning methods (i.e., Kalman Filter, Gaussian Process Regression, Support Vector Regression, Random Forest, and Back Propagation Network) and eight deep learning methods (i.e., Recurrent Neural Networks, Long Short-Term Memory, Bi-directional Long Short-Term Memory, Gate Recurrent Unit, Bi-directional Gate Recurrent Unit, Sequence to Sequence, Spatio-Temporal Graph Convolutional Network, and Transformer) are thoroughly analysed and compared from the algorithm essence and applications to excavate their features and adaptability for manned and unmanned ships. The findings reveal the characteristics of various prediction methods and provide valuable implications for different stakeholders to guide the best-fit choice of a particular method as the solution under a specific circumstance. It also makes contributions to the extraction of the research difficulties of ship trajectory prediction and the corresponding solutions that are put forward to guide the development of future research.

6. A hierarchical methodology for vessel traffic flow prediction using Bayesian tensor decomposition and similarity grouping

Ocean Engineering, 2023

Accurate vessel traffic flow (VTF) prediction can enhance navigation safety and economic efficiency. To address the challenge of the inherently complex and dynamic growth of the VTF time series, a new hierarchical methodology for VTF prediction is proposed. Firstly, the original VTF data is reconfigured as a three-dimensional tensor by a modified Bayesian Gaussian CANDECOMP/PARAFAC (BGCP) tensor decomposition model. Secondly, the VTF matrix (hour ✕ day) of each week is decomposed into high- and low-frequency matrices using a Bidimensional Empirical Mode Decomposition (BEMD) model to address the non-stationary signals affecting prediction results. Thirdly, the self-similarities between VTF matrices of each week within the high-frequency tensor are utilised to rearrange the matrices as different one-dimensional time series to solve the weak mathematical regularity in the high-frequency matrix. Then, a Dynamic Time Warping (DTW) model is employed to identify grouped segments with high similarities to generate more suitable high-frequency tensors. The experimental results verify that the proposed methodology outperforms the state-of-the-art VTF prediction methods using real Automatic Identification System (AIS) datasets collected from two areas. The methodology can potentially optimise relation operations and manage vessel traffic, benefiting stakeholders such as port authorities, ship operators, and freight forwarders.

7. Deep learning-powered vessel traffic flow prediction with spatial-temporal attributes and similarity grouping

Engineering Applications of Artificial Intelligence, 2023

Perceiving the future trend of Vessel Traffic Flow (VTF) in advance has great application values in the maritime industry. However, using such big data from the Automatic Identification System (AIS) for accurate VTF prediction remains challenging. Deep training networks can learn valuable features from extensive historical data. This paper proposes a new learning-based prediction network, improved Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) with similarity grouping, including three views. To effectively enable the training network to capture the temporal and periodic (i.e. a spatial attribute) change characteristics of VTF, the CNN and LSTM are employed to compose spatial and temporal views, respectively. Hence, the original one-dimensional data is transformed into a matrix (hour of the day ✕ day) to adapt the input of the proposed methodology. In practical applications, VTF of multiple adjacent target regions need to be predicted simultaneously, and the changes of VTF in different areas may influence each other. To explore their hidden relationships, the similarity grouping view aims to find the target area that exhibits the most similarity with the VTF change trend of the current research area. Furthermore, similar information is combined with the features generated from the other two views to obtain the prediction results. In summary, the new advantage lies in mining the spatiotemporal attributes of data and fusing the similarity information of adjacent regions. Comparative experiments with eleven other methods on realistic VTF datasets show that the proposed method demonstrates superior prediction accuracy and stability performance.

8. Multi-Scale collision risk estimation for maritime traffic in complex port waters

Reliability Engineering and System Safety, 2023

Ship collision risk estimation is an essential component of intelligent maritime surveillance systems. Traditional risk estimation approaches, which can only analyze traffic risk in one specific scale, reveal a significant challenge in quantifying the collision risk of a traffic scenario from different spatial scales. This is detrimental to understanding the traffic situations and supporting effective anti-collision decision-making, particularly as maritime traffic complexity grows and autonomous ships emerge. In this study, a systematic multi-scale collision risk estimation approach is newly developed to capture traffic conflict patterns under different spatial scales. It extends the application of the complex network theory and a node deletion method to quantify the interactions and dependencies among multiple ships within encounter scenarios, enabling collision risk to be evaluated at any spatial scale. Meanwhile, an advanced graph-based clustering framework is introduced to search for the optimal spatial scales for risk evaluation. Extensive numerical experiments based on AIS data in Ningbo_Zhoushan Port are implemented to evaluate the model performance. Experimental results reveal that the proposed approach can strengthen maritime situational awareness, identify high-risk areas and support strategic maritime safety management. This work therefore sheds light on improving the intelligent levels of maritime surveillance and promoting maritime traffic automation.

9. Graph-based ship traffic partitioning for intelligent maritime surveillance in complex port waters

Expert System with Applications, 2023

Maritime Situational Awareness (MSA) is a critical component of intelligent maritime traffic surveillance. However, it becomes increasingly challenging to gain MSA accurately given the growing complexity of ship traffic patterns due to multi-ship interactions possibly involving classical manned ships and emerging autonomous ships. This study proposes a new traffic partitioning methodology to realise the optimal maritime traffic partition in complex waters. The methodology combines conflict criticality and spatial distance to generate conflict-connected and spatially compact traffic clusters, thereby improving the interpretability of traffic patterns and supporting ship anti-collision risk management. First, a composite similarity measure is designed using a probabilistic conflict detection approach and a newly formulated maritime traffic route network learned through maritime knowledge mining. Then, an extended graph-based clustering framework is used to produce balanced traffic clusters with high intra-connections but low inter-connections. The proposed methodology is thoroughly demonstrated and tested using Automatic Identification System (AIS) trajectory data in the Ningbo-Zhoushan Port. The experimental results show that the proposed methodology 1) has effective performance in decomposing the traffic complexity, 2) can assist in identifying high-risk/density traffic clusters, and 3) is sufficiently generic to handle various traffic scenarios in complex geographical waters. Therefore, this study makes significant contributions to intelligent maritime surveillance and provides a theoretical foundation for promoting maritime anti-collision risk management for the future mixed traffic of both manned and autonomous ships.

10. Research in marine accidents: A bibliometric analysis, systematic review and future directions

Ocean Engineering, 2023

In order to analyse the research evolution and knowledge frontier in the research of marine accidents, 491 literatures on marine accidents in the Web of Science database from 2000 to 2022 are taken as data sources. Integrated with literature analysis of traditional method, CiteSpace and VOSviewer are then jointly used for the development of the knowledge network map and cluster analysis, and the knowledge of network map, research hotpots, research evolution and knowledge frontiers is obtained. It is found that there is a close cooperative relationship among journals, researchers, research institutions and countries or regions. According to the subjects and methods, the study of marine accidents can be divided into two parts: the analysis of the influential factors and accident consequences, as well as the methodology development of traditional and emerging technology. In this context, the analysis of human factors in remote-controlled ships, the prevention of accidents in Arctic waters have become research hotspots, while emerging accident analysis methods such as machine learning and big data mining also have shown powerful insights in the analysis of marine accidents. In terms of innovation, the bibliometric approach enhances the ability to handle large literature databases and conduct network analysis. Moreover, this study visualises collaborative networks, analyses evolution trends, reveals the research hotpots, and conducts a comparison and discussion of mainstream approaches in marine accident research. As a result, this study provides a theoretical basis and implementation direction for the development of maritime safety.

11. Accident data-driven human fatigue analysis in maritime transport using machine learning

Reliability Engineering & System Safety, 2024

In maritime transport, fatigue conditions can impair seafarer performance, pose a high risk of maritime incidents, and affect safety at sea. However, investigating human fatigue and its impact on maritime safety is challenging due to limited objective measures and little interaction with other risk influential factors (RIFs). This study aims to develop a novel model enabling accident data-driven fatigue investigation and RIF analysis using machine learning. It makes new methodological contributions, such as 1) the development of a human fatigue investigation model to identify significant RIFs leading to human fatigue based on historical accident and incident data; 2) the combination of least absolute shrinkage and selection operator (LASSO) and bayesian network (BN) to formulate a new machine learning model to rationalise the investigation of human fatigue in maritime accidents and incidents; 3) provision of insightful implications to guide the survey of fatigue's contribution to maritime accidents and incidents without the support of psychological data. The results show the importance of RIFs and their interdependencies for human fatigue in maritime accidents. It takes advantage of available knowledge and machine learning to open a new direction for fatigue management, which will benefit the maritime fatigue investigation and provide insights into other high-risk sectors suffering from human fatigue (e.g. nuclear and offshore).

12. Exploring seafarers’ emotional responses to emergencies: An empirical study using a shiphandling simulator

Ocean and Coastal Management, 2023

Seafarers are required to make quick decisions to avoid accidents in case of emergencies. However, officers with anxiety generally have a high probability of making wrong decisions that threaten safety and security during the voyage. With the help of a shiphandling simulator, this study aims to investigate the emotional changes of seafarers under simulated scenarios of emergencies. The State-Trait Anxiety Inventory (S-TAI) scale and electrocardiograph (ECG) signal are adopted to evaluate the emotions of the participant seafarers. To classify the anxiety state of the participants, a support vector machine-based method is applied to establish an anxiety recognition model. Classification results reveal that this proposed model can effectively identify different emotions of participants based on ECG features (cross-validation accuracy: 86.0%; test accuracy: 92.3%). The experimental results show that poor visibility could cause the greatest impact on the anxiety of seafarers. In addition, navigational officers and marine pilots react differently in case of emergencies. Seafarers tend to experience more anxiety when dealing with emergency situations, while marine pilots experience more anxiety during multi-ship encounter periods. Consequently, the findings of this study aid to effectively identify the scenarios that cause anxiety emotion of different professional seafarers, providing the corresponding reference for the training of seafarers. This could help prevent catastrophic accidents that pose a threat to oceans and coasts caused by human error.

13. Research in marine accidents: A bibliometric analysis, systematic review and future directions

Ocean Engineering, 2023

14. Incorporation of AIS data-based machine learning into unsupervised route planning for maritime autonomous surface ships

Transportation Research Part E: Logistics and Transportation Review, 2023

Maritime Autonomous Surface Ships (MASS) are deemed as the future of maritime transport. Although showing attractiveness in terms of the solutions to emerging challenges such as carbon emission and insufficient labor caused by black swan events such as COVID-19, the applications of MASS have revealed problems in practice, among which MASS navigation safety presents a prioritized concern. To ensure safety, rational route planning for MASS is evident as the most critical step to avoiding any relevant collision accidents. This paper aims to develop a holistic framework for the unsupervised route planning of MASS using machine learning methods based on Automatic Identification System (AIS) data, including the coherent steps of new feature measurement, pattern extraction, and route planning algorithms. Historical AIS data from manned ships are trained to extract and generate movement patterns. The route planning for MASS is derived from the movement patterns according to a dynamic optimization method and a feature extraction algorithm. Numerical experiments are constructed on real AIS data to demonstrate the effectiveness of the proposed method in solving the route planning for different types of MASS.

15. AIS data-driven ship trajectory prediction modelling and analysis based on machine learning and deep learning methods

Transportation Research Part E: Logistics and Transportation Review, 2023

Maritime transport faces new safety challenges in an increasingly complex traffic environment caused by large-scale and high-speed ships, particularly with the introduction of intelligent and autonomous ships. It is evident that Automatic Identification System (AIS) data-driven ship trajectory prediction can effectively aid in identifying abnormal ship behaviours and reducing maritime risks such as collision, stranding, and contact. Furthermore, trajectory prediction is widely recognised as one of the critical technologies for realising safe autonomous navigation. The prediction methods and their performance are the key factors for future safe and automatic shipping. Currently, ship trajectory prediction lacks the real performance measurement and analysis of different algorithms, including classical machine learning and emerging deep learning methods. This paper aims to systematically analyse the performance of ship trajectory prediction methods and pioneer experimental tests to reveal their advantages and disadvantages as well as fitness in different scenarios involving complicated systems. To do so, five machine learning methods (i.e., Kalman Filter (KF), Support Vector Progression (SVR), Back Propagation network (BP), Gaussian Process Regression (GPR), and Random Forest (RF)) and seven deep learning methods (i.e., Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gate Recurrent Unit (GRU), Bi-directional Long Short-Term Memory (Bi-LSTM), Sequence to Sequence (Seq2seq), Bi-directional Gate Recurrent Unit (Bi-GRU), and Transformer) are first extracted from the state-of-the-art literature review and then employed to implement the trajectory prediction and compare their prediction performance in the real world. Three AIS datasets are collected from the waters of representative traffic features, including a normal channel (i.e., the Chengshan Jiao Promontory), complex traffic (i.e., the Zhoushan Archipelago), and a port area (i.e., Caofeidian port). They are selected to test and analyse the performance of all twelve methods based on six evaluation indexes and explore the characteristics and effectiveness of the twelve trajectory prediction methods in detail. The experimental results provide a novel perspective, comparison, and benchmark for ship trajectory prediction research, which not only demonstrates the fitness of each method in different maritime traffic scenarios, but also makes significant contributions to maritime safety and autonomous shipping development.

16. Graph-based ship traffic partitioning for intelligent maritime surveillance in complex port waters

Expert Systems with Applications, 2023

17. Towards safe navigation environment: the imminent role of spatio-temporal pattern mining in maritime piracy incidents analysis

Reliability Engineering & System Safety, 2023

18. Adapting to the impacts posed by climate change: Applying Climate Change Risk Indicator (CCRI) framework in a multi-modal transport system

Sustainability, 2023

Climate change has threatened the infrastructure, operation, policymaking, and other pivotal aspects of transport systems with the accelerating pace of extreme weather events. While a considerable amount of research and best practices have been conducted for transport adaptation to climate change impacts, there is still a wide gap in the systematic assessment of climate risks on all-round transport modes (i.e., road, rail, sea, and air) with a comprehensive review and a quantitative scientific framework. This study aimed to critically review studies on how the transport sector has adapted to the impacts posed by climate change since the dawn of the 21st century. To support climate risk assessment in comprehensive transport systems, we developed a Climate Change Risk Indicator (CCRI) framework and applied it to the case of the British transport network. Focusing on a multi-modal transport system, this offers researchers and practitioners an invaluable overview of climate adaptation research with the latest tendency and empirical insights. Meanwhile, the developed CCRI framework elaborates a referable tool that enables decision-makers to employ objective data to realise quantitative risk analysis for rational transport adaptation planning.

19. Analysing seafarer competencies in a dynamic human-machine system

Ocean and Coastal Management, 2023

Human factors have been deemed to affect a variety of unsafe acts and hazardous conditions, with no exceptions in the maritime sector. With increasing applications of automation techniques in shipping, seafarers’ roles are changing, and their competencies require to be assessed and assured for safety at sea accordingly. The studies on seafarer competencies have therefore been tightly bound with a human-machine system which consists of the interaction of seafarers and ship operational systems and sub-systems. To evaluate the seafarer competencies that fit automation systems in shipping, this paper aims to develop a new dynamic human-machine model in shipping that can be used to analyse human factors in a closed-loop system. Based on Crew Resource Management and the International Convention on Standards of Training, Certification and Watchkeeping for Seafarers, it reflects the input, process, and output phases of the human system and its interactions with machine sub-systems. A new tool to analyse seafarer competencies is proposed to rationalise human factor evaluation in the maritime closed-loop system and reflect the dynamic human-machine cooperation process. Two case studies have been conducted to illustrate the feasibility of the new model and in the meantime to investigate seafarer competencies in the dynamic human-machine system. It produces a new human factor analysis tool to investigate maritime accidents. The results and policy implications help explore the adjustment of maritime training to support ship automation and provide guidance on risk management for traditional and autonomous ships.

20. Incorporation of seafarer psychological factors into maritime safety assessment

Ocean and Coastal Management, 2023

Psychological factors have been a critical cause of human errors in sectors such as health and aviation. However, there is little relevant research in the maritime industry, even though human errors significantly contribute to shipping accidents. It becomes even more worrisome given that seafarers are changing their roles onboard ships due to the growth of automation techniques in the sector. This research pioneers a conceptual framework for assessing seafarer psychological factors using neurophysiological analysis. It quantitatively enables the psychological factor assessment and hence can be used to test, verify, and train seafarers’ behaviours for ship safety at sea and along coasts. A case study on ship collision avoidance in coastal waters demonstrates its feasibility using ship bridge simulation. An experimental framework incorporating neurophysiological data can be utilised to effectively evaluate the contribution of psychological factors to human behaviours and operational risks. Hence, it opens a new paradigm for human reliability analysis in a maritime setting. This framework provides insights for reforming and evaluating operators’ behaviours on traditionally crewed ships and in remote-controlled centres within the context of autonomous ships. As a result, it will significantly improve maritime safety and prevention of catastrophic accidents that endanger oceans and coasts.

21. Analysis of factors affecting the severity of marine accidents using a data-driven Bayesian network

Ocean Engineering, 2023

A data-driven Bayesian network model (BN) is used to analyse the relationship between the severity of marine accidents and relevant Accident Influential Factors (AIFs). Firstly, based on the marine accident investigation reports involving 1,294 ships from 2000 to 2019, the severity grades of marine accidents are classified, and a database of factors affecting the severity of marine accidents is established. Secondly, a Tree Augmented Naive Bayesian algorithm (TAN) is used to establish a data-driven BN model, and the established database of AIFs is analysed by data training and machine learning to reveal the influence of related factors on the severity of the accident and the mechanism of action. Finally, the sensitivity analysis and verification of the model are conducted. Through the analysis of the Most Probable Explanation (MPE), it explains the possible configurations in different scenarios and identifies the related potential risks. This study finds that “accident type”, “engine power”, “gross tonnage”, “ship type” and “location” are the five most important AIFs of three accident severity grades. “Capsizing/sinking”, “hull/machinery damage” and “collision” that are most likely to lead to “very serious accidents”. Further, the possibility of fishing boats or other small ships leading to “very serious accidents” is also higher than that of other types of ships. The results of this study can help to analyse and predict marine accidents and ensure the safe navigation of ships and hence benefit such maritime stakeholders as safety authorities and ship owners.

22. Towards objective human performance measurement for maritime safety: A new psychophysiological data-driven machine learning method

Reliability Engineering and System Safety, 2023

Human errors significantly contribute to transport accidents. Human performance measurement (HPM) is crucial to ensure human reliability and reduce human errors. However, how to address and reduce the subjective bias introduced by assessors in HPM and seafarer certification remains a key research challenge. This paper aims to develop a new psychophysiological data-driven machine learning method to realize the effective HPM in the maritime sector. It conducts experiments using a functional Near-Infrared Spectroscopy (fNIRS) technology and compares the performance of two groups in a maritime case (i.e. experienced and inexperienced seafarers in terms of different qualifications by certificates), via an Artificial Neural Network (ANN) model. The results have generated insightful implications and new contributions, including (1) the introduction of an objective criterion for assessors to monitor, assess, and support seafarer training and certification for maritime authorities; (2) the quantification of human response under specific missions, which serves as an index for a shipping company to evaluate seafarer reliability; (3) a supportive tool to evaluate human performance in complex emerging systems (e.g. Maritime Autonomous Surface Ship (MASS)) design for ship manufactures and shipbuilders.

23. Collision avoidance for autonomous ship using deep reinforcement learning and prior-knowledge-based approximate representation

Frontier in Marine Science, 2023

Reinforcement learning (RL) has shown superior performance in solving sequential decision problems. In recent years, RL is gradually being used to solve unmanned driving collision avoidance decision-making problems in complex scenarios. However, ships encounter many scenarios, and the differences in scenarios will seriously hinder the application of RL in collision avoidance at sea. Moreover, the iterative speed of trial-and-error learning for RL in multi-ship encounter scenarios is slow. To solve this problem, this study develops a novel intelligent collision avoidance algorithm based on approximate representation reinforcement learning (AR-RL) to realize the collision avoidance of maritime autonomous surface ships (MASS) in a continuous state space environment involving interactive learning capability like a crew in navigation situation. The new algorithm uses an approximate representation model to deal with the optimization of collision avoidance strategies in a dynamic target encounter situation. The model is combined with prior knowledge and International Regulations for Preventing Collisions at Sea (COLREGs) for optimal performance. This is followed by a design of an online solution to a value function approximation model based on gradient descent. This approach can solve the problem of large-scale collision avoidance policy learning in static-dynamic obstacles mixed environment. Finally, algorithm tests were constructed though two scenarios (i.e., the coastal static obstacle environment and the static-dynamic obstacles mixed environment) using Tianjin Port as an example and compared with multiple groups of algorithms. The results show that the algorithm can improve the large-scale learning efficiency of continuous state space of dynamic obstacle environment by approximate representation. At the same time, the MASS can efficiently and safely avoid obstacles enroute to reaching its target destination. It therefore makes significant contributions to ensuring safety at sea in a mixed traffic involving both manned and MASS in near future.

24. A BN driven FMEA approach to assess maritime cybersecurity risks

Ocean and Coastal Management, 2023

Cybersecurity risks present a growing concern in the maritime industry, especially due to the fast development of digitalised technologies, also vis-à-vis autonomous shipping. Research on maritime cybersecurity is receiving increased attention. This paper aims to assess the cybersecurity risks in the maritime sector and improve safety at sea and in coastal areas. First, we identify all the concerned cyber threats in the sector based on literature review and expert opinion. A novel risk assessment framework of maritime cyber threats, which combines Failure Mode and Effects Analysis (FMEA) with a Rule-based Bayesian Network (RBN), is proposed and used to evaluate the risk levels of the identified threats and to better understand the threats that contribute the most to the overall maritime cybersecurity risk. The results can inform stakeholders about the most vulnerable parts in their cyber operations and stimulate the development of risk-based control measures. More specifically, the next step in managing cyber threats is to tackle the threats that are associated with unacceptable risk levels and identify cost-effective measures to manage them. To that extent, our findings provide a list of top threats – that is the areas where efforts should be focused on. As a result, this work can help the whole community to grow its resilience to cyber-attacks and improve the security of shipping operations.

25. Multi-stage and multi-topology analysis of ship traffic complexity for probabilistic collision detection

Expert Systems with Applications, 2023

Maritime traffic situational awareness plays a vital role in the development of intelligent transportation-support systems. The state-of-the-art study focuses on near-miss collision risk between/among ships but reveals challenges in estimating large-scale traffic situations associated with dynamic and uncertain ship motions at a regional level. This study develops a systematic methodology to evaluate ship traffic complexity to comprehend the traffic situation in complex waters. In the new methodology, the topological and evolutionary characteristics of ship traffic networks and the uncertainty in ship movements are considered simultaneously to realise probabilistic collision detection. The methodology, through the effective integration of probabilistic conflict estimation and traffic complexity modelling and assessment, enables the evaluation of traffic complexity in a fine-grained hierarchical manner. With the AIS-based trajectory data collected from the world’s largest port (i.e. Ningbo-Zhoushan Port), a thorough validation of the evaluation performance is conducted and demonstrated through scenario analysis and model robustness. Moreover, some critical research results are obtained in terms of traffic network heterogeneity analysis; statistics including occurrence frequency, temporal distribution, life cycle, and transition probability of traffic complexity patterns; and correlation examination between the number of ships and traffic complexity patterns. These findings offer new insights into improving maritime traffic awareness capabilities and promoting maritime traffic safety management.

26. Data-driven Bayesian network for risk analysis of global maritime accidents

Reliability Engineering and System Safety, 2023

Maritime risk research often suffers from insufficient data for accurate prediction and analysis. This paper aims to conduct a new risk analysis by incorporating the latest maritime accident data into a Bayesian network (BN) model to analyze the key risk influential factors (RIFs) in the maritime sector. It makes important contributions in terms of a novel maritime accident database, new RIFs, findings, and implications. More specifically, the latest maritime accident data from 2017 to 2021 is collected from both the Global Integrated Shipping Information System (GISIS) and Lloyd’s Register Fairplay (LRF) databases. Based on the new dataset, 23 RIFs are identified, involving both dynamic and static risk factors. With these developments, new findings and implications are revealed beyond the state-of-the-art of maritime risk analysis. For instance, the research results show ship type, ship operation, voyage segment, deadweight, length, and power are among the most influencing factors. The new BN-based risk model offers reliable and accurate risk prediction results, evident by its prediction performance and scenario analysis. It provides valuable insights into the development of rational accident prevention measures that could well fit the increasing demands of maritime safety in today’s complex shipping environment.

27. Maritime traffic clustering to capture high-risk multi-ship encounters in complex waters

Reliability Engineering and System Safety, 2023

Maritime traffic situational awareness is fundamental to the safety of maritime transportation. The state-of-the-art research primarily attaches importance to collision risk estimation and evaluation between/among ships but encounters the challenges of capturing the high-risk traffic clusters in complex waters. This paper develops a systematic traffic clustering approach to enhance traffic pattern interpretability and proactively discover high-risk multi-ship encounter scenarios, in which both the conflict connectivity and spatial compactness of encounter ships are considered. Specifically, a novel hybrid clustering approach that integrates a composite distance measure, a constrained Shared Nearest Neighbour clustering, and a fine-tuning strategy is developed to segment maritime traffic into multiple conflict-connected and spatially compact clusters. Meanwhile, a hierarchical bi-objective optimization algorithm is introduced to search for optimal clustering solutions. Through maritime traffic data obtained from the Ningbo-Zhoushan Port, a thorough methodology performance evaluation is carried out through application demonstration and validation. Experiment results reveal that the new approach: 1) can effectively capture the high-risk/density traffic clusters; 2) is robust with respect to various traffic scenarios; and 3) can be extended to assist in collision risk management. It therefore offers new insights into enhancing maritime traffic surveillance capabilities and eases the design of risk management strategy.

28. Risk assessment of maritime supply chains within the context of the Maritime Silk Road

Ocean and Coastal Management, 2023

This work aims to apply a novel approach to assess the risks of maritime supply chains (MSCs) within the context of the Maritime Silk Road (MSR) by employing fuzzy logic and evidential reasoning. Compared to traditional risk analysis methods, the novel approach has its superiorities in dealing with incomplete and vague data, synthesizing multiple data formats, and preventing the loss of important risk information. A case of the risk factors influencing MSCs along the MSR is analysed, and the assessment results reveal that the fuel price is the most significant risk factor. Sensitive analysis is applied to validate and illustrate the rationality and practicality of the proposed approach. The findings can provide the MSR stakeholders with important insights for the safety management of MSCs along MSR.

29. Risk evolution analysis of ship pilotage operation by an integrated model of FRAM and DBN

Reliability Engineering and System Safety, 2023

The risks involved in ship pilotage operations are characterized by random, uncertain and complex features. To reveal the spatiotemporal evolution of ship collision risks in the pilotage operations process, a risk evolution analysis model is developed in this paper by the combination of a Functional Resonance Analysis Method (FRAM) and Dynamic Bayesian Network (DBN). First, based on the analysis results of the functional resonance mechanism of a ship pilotage system, the relevant collision risk influencing factors (RIFs) and their coupling relationships are identified. Second, the DBN is quantified by the employment of various uncertainty treatment methods including the Dempster-Shafer evidence theory for the configuration of the prior probabilities and a Markov model for the dynamic factors’ transition probability calculation. Finally, using the temporal observation data, the temporal risk inference is conducted to reveal the risk evolution law in a ship pilotage operations process. The findings show that the evolution of collision risk in ship pilotage is significantly sensitive to regional locations, resulting in a “U” curve shaped by the action of functional resonance. “Inadequate human look-out” is among the most influential factors, and hence targeted risk control strategies should be formulated to ensure the safety of ship pilotage operations.

30. Maritime cybersecurity: Are onboard systems ready?

Maritime Policy & Management, 2022

Recent maritime cybersecurity accidents reveal that shipping is facing increased exposure to cyber threats, especially due to the fast-growing digitalisation of the sector, leaving vessels and their onboard systems vulnerable to cyberattacks. This research aims at evaluating the relationship among the critical dimensions influencing cybersecurity performance in the maritime industry. To achieve this, six critical dimensions related to cybersecurity preparedness are first identified through literature review, namely ‘regulations’, ‘company procedures’ from a managerial perspective and ‘shipboard systems readiness’, ‘training and awareness’, ‘human factor’ and ‘compliance monitoring’ at an operation level. A Likert-scale questionnaire is designed and used to collect empirical data from 133 seafarers and shore-based staff. Structural Equation Modelling (SEM) is applied to examine the causal relationships between the six dimensions and shipboard cybersecurity performance. The results show that ‘regulations’ positively influence shipping companies’ cybersecurity-related ‘procedures’, which in turn positively affects ‘shipboard systems readiness’, ‘training and awareness’, and ‘monitoring’. Further, ‘training and awareness’ positively influences the cybersecurity performance of ships. The results have profound implications for the shipping industry on how to strengthen their cyber practices in order to improve their cybersecurity performance. Recommendations for future academic research related to maritime cybersecurity are also provided.

31. Optimising the resilience of shipping networks to climate vulnerability

Maritime Policy & Management, 2022

Climate extremes are threatening transportation infrastructures and hence require new methods to address their vulnerability and improve their resilience. However, existing studies have yet to examine the climate impacts on transportation networks systematically rather than independently assessing the infrastructures at a component level. Therefore, it is crucial to configure alternative shipping routes from a systematic perspective to reduce climate vulnerabilities and optimise the resilience of the whole shipping network. This paper aims to assess the global shipping network focusing on climate resilience by a methodology that combines climate risk indicators, centrality analysis and ship routing optimisation. The methodology is designed for overviewing the climate vulnerability of the current and future scenarios for comparison. First, a multi-centrality assessment defines the global shipping hubs and network vulnerabilities. Secondly, a shipping model is built for finding the optimal shipping route between ports, considering the port disruption days caused by climate change (e.g. extreme weather) based on the climate vulnerability analysis result from the first step. It contributes to a new framework combining the global and local seaport climate vulnerabilities. Furthermore, it recommends changing shipping routes by a foreseeable increase in port disruptions caused by extreme weather for climate adaptation.

32. Safety and security co-analysis in transport systems: Current state and regulatory development

Transportation Research Part A: Policy and Practice, 2022

Transportation is sensitive to risk. Given the fast development of digitalisation and automation of transport systems in the past decade, new types of security risks (e.g. cyberattacks) emerge within the context of transport safety research. To enable the integrated analysis of emerging security and classical safety-related risks in a holistic manner, safety and security co-analysis (SSCA) is highly demanded for accident prevention. SSCA in transport systems will benefit the risk analysis of complex cyber physical transport systems facing challenges from both hazards and threats. However, the nature of hazard and threat-based risks is fundamentally different, which leads to the various difficulties of analysing them on the same plane. They include the use of different risk parameters, the uncertainty levels of the risk input and the methodologies of risk inference. To address such concerns, this study firstly reviews the literature on SSCA and compares the employed methodologies and their applications within the context of transport systems. Taking into account the advantages of both security-driven and safety-oriented methods, a conceptual framework is proposed to imply the insights on SSCA for transportation through both top-down and bottom-up perspectives, followed by a quantitative illustrative case study. Then, the regulatory development and evolution of SSCA in transport in practice is analysed across different transport modes, which configures initiatives’ interrelations for a cross-fertilisation purpose. As a result, the findings reveal new research directions for the safety of digitalised and/or autonomous transport vehicles and aid in the formation of future transport safety study agendas.

33. Shipping accident analysis in restricted waters: Lesson from the Suez Canal blockage in 2021

Ocean Engineering, 2022

Global shipping flows through strategically important restricted waters such as Panama and Suez Canals, and hence accidents occurring in the Canals will cause serious disruptions to global supply chains. In this paper, a new data-driven Bayesian network (BN) based risk model is developed to investigate how risk factors jointly generate impact on different types of maritime accidents within restricted waters. A new risk database involving 25 factors has been developed by manual analysis of all the recorded accidents from 2005 to 2021 that occurred in the world’s important restricted waters including key maritime canals, channels and straits. A data-driven BN model is constructed to analyse the key risk influential factors (RIFs) contributing to such accidents. The model is verified by sensitivity analysis and real accident cases. Further, it is tested by the already known information of the 2021 Suez Canal blockage case to generate useful insights and draw the lessons to learn. In a retrospective analysis using the currently available limited information on the Suez Canal case, the implication of the case study shows a plausible explanation for the observed findings by scenario analysis. The findings can be applied to backward risk cause diagnosis for accident investigation and forward risk prediction for accident prevention in restricted waters to avoid the reoccurrence of similar accident to the Suze Canal blockage.

34. The impact of marine engine noise exposure on seafarer fatigue: A China case

Ocean Engineering, 2022

Previous relevant studies have revealed that noise and poor sleep quality are two important risk factors causing seafarer fatigue. However, the relationship between marine engine noise and objective sleep parameters has rarely been studied. Using primary data collected from a 28-day on-board experiment and 1 questionnaire survey during both voyage and berthing periods, this study takes a pioneering step to address this crucial relationship. Energy indicators related to the engine noise for 28 days were estimated and 6 objective sleep parameters were used to measure the degree of seafarer fatigue. The findings reveal that as seafarers want to sleep longer to relieve their anxiety and irritability caused by the increased engine noise, the time in bed (TB) and the total sleep time (TST) increased when the engine noise level increased. Meanwhile, with the growing engine noise levels and the higher number of engine noise events, the total wake time after sleep onset (WASO) and the time for sleep onset latency (SOL) increased, and the sleep efficiency (SE) decreased. Energy indicators were significantly associated with objective sleep parameters. Finally, strengthening the content of psychological adjustment in the seafarer training link and cultivating the seafarers’ character strength to improve the ability to face harsh environments are recommended. In maritime management, managers should play the role of social work intervention to adjust seafarers’ sleep quality and ease fatigue. In the construction of ships, builders should emphatically consider the use of sound insulation materials to reduce noise effect on living areas.

35. Incorporation of deep kernel convolution into density clustering for shipping AIS data denoising and reconstruction

Journal of Marine Science and Engineering, 2022

Automatic Identification System (AIS) equipment can aid in identifying ships, reducing ship collision risks and ensuring maritime safety. However, the explosion of massive AIS data has caused increasing data processing challenges affecting their practical applications. Specifically, mistakes, noise, and missing data are presented during AIS data transmission and encoding, resulting in poor data quality and inaccurate data sources that negatively impact maritime safety research. To address this issue, a robust AIS data denoising and reconstruction methodology was proposed to realise the data preprocessing for different applications in maritime transportation. It includes two parts: Density-Based Spatial Clustering of Applications with Noise based on Deep Kernel Convolution (DBSCANDKC) and the reconstruction method, which can extract high-quality AIS data to guarantee the accuracy of the related maritime research. Firstly, the kinematics feature was employed to remove apparent noise from the AIS data. The square deep kernel convolution was then incorporated into density clustering to find and remove possibly anomalous data. Finally, a piecewise cubic spline interpolation approach was applied to construct the missing denoised trajectory data. The experiments were implemented in the Arctic Ocean and Strait of Dover to demonstrate the effectiveness and performance of the proposed methodology in different shipping environments. This methodology makes significant contributions to future maritime situational awareness, collision avoidance, and robust trajectory development for safety at sea.

36. Risk analysis of cargo theft from freight supply chains using a data-driven Bayesian network

Reliability Engineering and System Safety, 2022

Cargo theft has been among the most concerning risks influencing global freight supply chains, which causes serious supply chain disruptions, injuries/deaths, economic loss, and environmental damage. However, there are very few studies on the risk analysis of cargo theft, particularly in a quantitative manner, and fewer on the relevant risk factors affecting theft-related accidents in the current literature. This paper aims to analyse the risk influential factors (RIFs) of cargo theft and predict the occurrence likelihood of different types of cargo theft accidents. The historical data of 9316 cargo theft accidents that happened in the UK from 2009 to 2021 were first collected from the TAPA IIS database, and then purified and trained to construct a Bayesian network (BN) based cargo theft risk analysis model. The data-driven BN interprets the interdependency of RIFs and their combined effects on the occurrence of different types of cargo theft accidents. Compared with the previous studies, this paper makes new contributions, including that (1) The cargo theft RIFs are identified from the literature and accident records. (2) A data-driven BN is proposed to construct the model with uncertainty to realise cargo theft risk prediction and diagnosis. (3) The critical RIFs contributing to cargo theft are evaluated and prioritised to predict the occurrence of possible cargo theft accidents. (4) The real accidents are investigated to verify the model and draw useful insights for cargo theft prevention. The findings show that the most influential RIFs for the occurrence of cargo theft accidents are product category, year, location type, modus operandi (MO), and region. The findings also reveal the combined risk contributions of the RIFs, hence providing useful insights for cost-effective theft risk control in practice.

37. A trustable architecture over blockchain to facilitate maritime administration for MASS systems

Reliability Engineering & System Safety, 2022

Maritime Autonomous Surface Ship (MASS) is widely deemed as the future of global shipping. The cyber vulnerability has however been identified as an emerging problem and a potential barrier influencing MASS development. This paper, through the investigation of the fundamental trust problem with regards to the cyber security of MASS systems, aims to develop a blockchain-based scheme for the trust management of MASS. The innovative idea of using blockchain within the MASS context is that the mobile entities in the MASS operational environment constitute a decentralized opportunity network, which makes blockchain an appealing tool to provide a solution to evaluating and maximizing the trust over the dynamics of the entities. This paper elaborates the mechanism by which the MASS entities participate in keeping the main chain. Firstly, the paper illustrates how the Belief of Trust (BoT) among the entities is encoded and assembled into the chain, to allow MASS entities to have an initial judgement towards another entity before they get acquainted. Secondly, at the consensus layer of blockchain technique, it addresses how the witness, who has a temporary right of producing a block and append it to the chain, can be elected among the nodes and how to incent the nodes to maintain the blockchain from a proof-of-stake perspective. Finally, this paper describes how the MASS entities can use the certificate dependence information to evaluate the trust transition in the MASS operating environment. Typical scenarios are delineated to show the procedure of certificate inquiry, handover of controls between maritime supervision centers and shore-side remote control centers in case of the occurrence of unexpected events. The findings provide any entity in an MASS network with an effective solution to evaluating the degree of trust he can have for any targeted node/participant. They can therefore help choose better (more trustable) nodes to maintain the MASS network’s knowledge of evidence to judge the trust on an unknown member.

38. Numerical Analysis and Staircase Layout Optimization for a Ro-Ro Passenger Ship during Emergency Evacuation

Reliability Engineering and System Safety, 2022

In this research, the effects of the passenger population composition and ship familiarity in an emergency evacuation are analysed. The results identified that the effects of different population compositions on the Ro-Ro evacuation process vary significantly. It is therefore recommended that a targeted survey of the population on a specific ship should be conducted before the evacuation analysis to improve the analysis accuracy of the evacuation process. It is not always the case that a higher familiarity with the ship staircase layout necessarily results in less time to complete the evacuation, and the issue of balanced exits has to be considered due to its significant impact. The results obtained in this research can be used to aid the ship’s staircase layout optimisation to facilitate the evacuation process. Given the type of Ro-Ro vessel in this analysis, it is suggested that adding a staircase towards the bow of the ship can reduce the evacuation time by 13.6%, when considering 95% of the passengers to complete an evacuation. Similarly, adding one staircase at the stern can reduce the time by approximately 10% for all passengers to complete the evacuation. It is not recommended that the size of staircases towards the middle of the ship should be adjusted.

39. Evaluating recovery strategies for the disruptions in liner shipping networks: a resilience approach

The International Journal of Logistics Management, 2022

Since the start of the current century, the world at large has experienced uncertainties as a result of climate change, terrorism threats and increasing economic upheaval. These uncertainties create non-classical risks for global seaborne container trade and liner shipping networks (LSNs). The purpose of this paper is to establish a novel risk-based resilience framework to measure the effectiveness of different recovery strategies for the disruptions in LSNs in a quantitative manner.

40. Decarbonisation of shipping: A state of the art survey for 2000–2020

Ocean & Coastal Management, 2021

In the global effort to reduce Green House Gases and carbon emissions, there is great importance for the shipping industry to decarbonise and move forward into a greener future. However, there is a lack of academic commentary on how attempts at various decarbonisation methods reported in research articles have developed over the 21st century, particularly in line with the relevant policy and regulatory developments. This paper analyses how the shipping industry has decarbonised by utilising 294 papers from 2000 to 2020. By analysing 20 years’ worth of research, this paper delivers a comprehensive review of shipping decarbonisation research and analyses the evolution of its themes as a function of time. It therefore aids to develop a greater understanding and comparison of governmental, economic and academic perspectives (and their potential alignment) for the industry to decarbonise. For 2017–20 the key shipping decarbonisation technologies were summarised and their advantages, disadvantages and current academic literature applications are revealed. Furthermore, the analysis of the evolution of shipping decarbonisation research themes reveals clear research gaps in the current literature and guides the development of a future research agenda with the prediction of future opportunities and potential for shipping decarbonisation research developments for the shipping industry.

41. Climate change risk indicators (CCRI) for seaports in the United Kingdom

Ocean & Coastal Management, 2021

Climate change is the most threating environmental issue and the biggest challenge that humanity has ever faced. While acting as the key nodes of globalisation and international business, seaports are exposed to the vulnerability of climate impacts, mainly because of their locations, including low-lying areas, coastal zones, and deltas. The paper is to develop a Climate Change Risk Indicator (CCRI) framework for climate risk assessment of seaports, enabling research-informed policymaking on such a demanding topic. Due to the increasing number of extreme weather events (EWEs), climate change adaptation is becoming an essential and necessary issue to be addressed by seaport stakeholders. Climate risk analysis aids rational adaptation planning. Many climate assessments have been done for measuring climate vulnerabilities, and various climate adaptation measures have been proposed for reducing climate risks. However, few of them used quantitative approaches for climate risk evaluations in seaports and fewer on the provisions of CCRIs for comparing climate risks of different locations and timeframes to guide rational policy making. Furthermore, climate change is a dynamic issue, requiring big objective data to support the analysis (e.g. monthly climate data on CCRIs) of climate threats and vulnerabilities. In this paper, Evidence Reasoning (ER) is employed to evaluate the climate risks in seaports by tackling the incomplete data. The findings reveal the quantitative measures of climate change risks in different locations and in different months. Furthermore, the risk levels of seaports in the future are assessed for observing the changes and informing policy making. The main contributions of this study include the visualisation of the comprehensive climate risk levels and provision of a new climate risk analysis framework through the comparison of climate change risks with respect to different locations and timeframes. Suitable climate adaptation measures can be chosen to implement, and seaports can cooperate on climate resilience issues (e.g. seaport network service and pre-disaster relief logistics).

42. A probabilistic risk approach for the collision detection of multi-ships under spatiotemporal movement uncertainty

Reliability Engineering and System Safety, 2021

It is vital to analyse ship collision risk for preventing collisions and improving safety at sea. The state-of-the-art of ship collision risk analysis focuses on encountering conflict between ship pairs, subject to a strong assumption of the ships having no/little spatiotemporal motion uncertainty. This paper proposes a probabilistic conflict detection approach to estimate potential collision risk of various multi-vessel encounters, in which the spatiotemporal-dependent patterns of ship motions are newly taken into account through quantifying the trajectory uncertainty distributions using AIS data. The estimation accuracy and efficiency are assured by employing a two-stage Monte Carlo simulation algorithm, which provides the quantitative bounds on the approximation accuracy and allows for a fast estimation of conflict criticality. Several real experiments are conducted using the AIS-based trajectory data in Ningbo-Zhoushan Port to demonstrate the feasibility and superiority of the proposed new approach. The results show that it enables the effective detection of collision risk timely and reliably in a complicated dynamic situation. They therefore provide valuable insights on ship collision risk prediction as well as the formulation of risk mitigation measures.

43. Optimal scheduling of emergency resources for major maritime oil spills considering time-varying demand and transportation networks

European Journal of Operational Research, 2021

During an emergency response to a major oil spill accident, the features of the motion of the oil films affect the response decisions. A highly dynamic optimal solution is needed to tackle the continuous changes in the demand for emergency resources and transportation networks for logistics deliveries that must occur. To effectively balance the responsiveness and the total response cost in emergency operations, this paper proposes a dynamic multi-objective location-routing model to address new challenges, such as the time-varying conditions in the response to oil spills and the interrelationship between the decision-making environment and emergency operations. Since the problem is NP-hard, to efficiently obtain Pareto solutions, a novel implementation of a heuristic framework based on particle swarm optimization is developed to conduct numerical experiments. Additionally, to handle the multi-objective model, an alternative solution based on the cost performance method is adopted to help decision makers select the ideal options for Pareto solutions. A case study of a major oil spill accident that occurred in the Bohai Bay is conducted to demonstrate the application of the proposed model and approaches and the real-world implications.

44. Dynamic optimization of emergency resource scheduling in a large-scale maritime oil spill accident

Computers and Industrial Engineering, 2021

Current maritime emergency logistics studies on oil spills are largely conducted based on static analysis to optimize resource scheduling. This does not suitably address the practical industrial demand, where the oil spill risk in nature dynamically depends on the motion of oil films. To better simulate the reality, this paper aims to conduct a study on a novel dynamic multi-objective location-routing model with split delivery considering practical characteristics, such as the time-varying demands of contaminated areas, uncertainty in the state of associated transportation networks and interrelationship between the changes in spilled oil films and emergency operations, which all result from the dynamic motion of oil films at sea. To address model complexity, we propose a two-stage optimization model, whereby a hybrid heuristic algorithm is developed to obtain Pareto solutions. To demonstrate the proposed model and approaches, a case study involving a series of sensitivity analyses is presented to highlight the importance of the proposed model and determines its implications.

45. Geometrical risk evaluation of the collisions between ships and offshore installations using rule-based Bayesian reasoning

Reliability Engineering and System Safety, 2021

Increasing human installations and vessel traffic in offshore waters render a collision risk between ships and offshore installations (SOI). Past decades have witnessed many accidents occurred in the offshore waters involving complex traffic networks. To safeguard offshore installations and improve water-bound transport safety, this paper proposes a novel Bayesian-based model to assess the SOI collision risk involving passing ships. It first identifies the relevant risk factors with the aid of a geometrical analysis concerning SOI collisions. The causal relationships between the risk factors are numerically defined by causal rules with a degree of belief structure, while a Bayesian network (BN) is constructed to aggregate the evaluated value of each risk factor and to assess the collision risks involving different navigational environments. To illustrate the new model, a real case on SOI collision risk in the Liverpool Burbo Bank offshore wind farm is investigated. The results provide empirical evidence for SOI collision risk analysis under complex water conditions and uncertain navigational environments and hence useful insights on SOI collision avoidance.

46. Risk assessment of the operations of maritime autonomous surface ships

Reliability Engineering and System Safety, 2021

Maritime Autonomous Surface Ships (MASS) are attracting increasing attention in the maritime industry. Despite the expected benefits in reducing human error and significantly increasing the overall safety level, the development of autonomous ships would undoubtedly introduce new risks. The overall goal of this work is to develop an approach to evaluate the risk level of major hazards associated with MASS. To that extent, a Failure Modes and Effects Analysis (FMEA) method is used in conjunction with Evidential Reasoning (ER) and Rule-based Bayesian Network (RBN) to quantify the risk levels of the identified hazards. The results show that ‘interaction with manned vessels and detection of objects’ contributes the most to the overall risk of MASS operations, followed by ‘cyber-attacks’, ‘human error’ and ‘equipment failure’. The findings provide useful insights on the major hazards and can aid the overall safety assurance of MASS.

47. Incorporation of deficiency data into the analysis of the dependency and interdependency among the risk factors influencing port state control inspection

Reliability Engineering and System Safety, 2021

Port State Control (PSC) inspection aids to control substandard ships and ensure safety at sea. Current risk-based PSC research and practice fail to incorporate ship deficiency records into detention probability analysis, because of the difficulty introduced by the involved big deficiency data. In this paper, a new Bayesian Network (BN) based PSC risk probabilistic model is developed to analyze the dependency and interdependency among the risk factors influencing PSC inspections based on big data derived from the inspection database of Tokyo MoU for the period between 2014 and 2017. The results reveal that ship’s safety condition related deficiencies as well as technical features of the inspected vessel itself are among the most influential factors concerning PSC inspections and ship detention. New Bayesian learning methods are used to improve the model efficiency in ship detention prediction. As a result, the newly developed model has shown a reliable performance on dynamic prediction and cause-effect diagnosis of ship detention probabilities by pioneering the incorporation of ship deficiency records in the analysis. The findings provide important insights on how to facilitate risk-based PSC inspections for both ship owners and port states. They provide support for port state authorities to implement rational inspection policies.

48. Climate change research on transportation systems: Climate risks, adaptation and planning

Transportation Research Part D: Transport and Environment, 2020

With the occurrence of more frequent and intense climate change events, transportation systems, including their infrastructure and operations become increasingly vulnerable. However, the existing research related to climate risks, adaptation and planning in the transport sector is still at an embryonic stage. Understanding such, this paper presents a critical review on climate risks, adaptation strategies and planning in the context of road and rail transportation systems. It aims to conduct a rigorous survey, to highlight any significant research gaps not addressed in past studies and to analyse current emerging topics to guide future directions. It critically dissects the selected papers by categorising them into several dimensions to reveal the status quo and potential challenges, including climate risk assessment, transport asset management, climate planning and policy, and adaptation of transport infrastructure to climate change. It will provide valuable references for future research and constructive insights and empirical guidance on climate adaptation, risk analysis, transport planning and other important relevant topics.