Integrating Bayesian Network and Cloud Model to Probabilistic Risk Assessment of Maritime Collision Accidents in China’s Coastal Port Waters DOI Creative Commons
Zhuang Li,

Xiaoming Zhu,

Shiguan Liao

et al.

Journal of Marine Science and Engineering, Journal Year: 2024, Volume and Issue: 12(12), P. 2113 - 2113

Published: Nov. 21, 2024

Ship collision accidents have a greatly adverse impact on the development of shipping industry. Due to uncertainty relating these accidents, maritime risk is often difficult accurately quantify. This study innovatively proposes comprehensive method combining qualitative and quantitative methods predict ship accidents. First, in view uncertain factors, Bayesian network analysis was used characterize correlations between accident assessment model established. Secondly, information about subjective data quantification based cloud adopted, reasoning determined multi-source fusion. The proposed applied spatiotemporal China’s coastal port waters. results show that there higher Guangzhou Port Ningbo China, potential for southern China greater, occurrence most affected by environment operations operators. Combining integrating conduct an assessment, this innovative has significance improving prevention response risks navigation ports.

Language: Английский

Prediction of the severity of marine accidents using improved machine learning DOI Creative Commons
Yinwei Feng, Xinjian Wang, Qilei Chen

et al.

Transportation Research Part E Logistics and Transportation Review, Journal Year: 2024, Volume and Issue: 188, P. 103647 - 103647

Published: July 2, 2024

Although many studies have focused on the occurrence likelihood of marine accidents, few analysis severity consequences, and even fewer prediction severity. To this end, a new research framework is proposed in study to accurately predict accidents. First, novel two-stage feature selection (FS) method was developed select rank Risk Influential Factors (RIFs) improve accuracy Machine Learning (ML) model interpretability FS. Second, comprehensive evaluation measure performance FS methods based stability, predictive improvement, statistical tests. Third, six well-established ML models were used compared different predictors. The Light Gradient Boosting (LightGBM) found best for accidents treated as benchmark model. Finally, LightGBM accident RIFs selected by method, effect risk control measures counterfactually analysed from quantitative perspective. This innovative use improved approaches can effectively analyse providing methodology triggering direction using Artificial Intelligence (AI) technologies safety assessment prevention studies. source code publicly available at: https://github.com/FengYinLeo/PGI-SDMI.

Language: Английский

Citations

29
Spatial-Temporal Evolution of Maritime Accident Hot Spots in the East China Sea: A Space-Time Cube Representation DOI Creative Commons
Yanqing Feng, Daozheng Huang, Hong Xuan

et al.

Journal of Marine Science and Engineering, Journal Year: 2025, Volume and Issue: 13(2), P. 233 - 233

Published: Jan. 26, 2025

As public concern for maritime safety grows, there is a pressing need to delve deeper into the root causes of accidents and develop effective preventive strategies. Spatial-temporal analysis stands out as powerful approach pinpointing accident hot spots. While previous research has shed light on spatial aspects these incidents, comprehensive understanding their temporal dimensions remains elusive. This paper bridges this gap by leveraging Space-Time Cube tool in conjunction with traditional Kernel Density chart spatial-temporal dynamics Focusing East China Sea, region notorious its high incidence home numerous world-class ports, we present case study that offers fresh insights. Data spanning from 1994 2020, sourced Lloyd’s List Intelligence (LLI) database, reveal evolving landscape area. Notably, since 2005, Yangtze River Delta Region emerged persistent spot accidents, underscoring significance discourse. Furthermore, our 2010s detects new expanding towards southwest Kaohsiung Port, China, signaling burgeoning area safety. Fujian coast seen share it not qualified zone. The proves be an indispensable unraveling progression findings indicate certain areas may merely random occurrences but exhibit intricate patterns.

Language: Английский

Citations

5
Investigation of the risk influential factors of maritime accidents: A novel topology and robustness analytical framework DOI Creative Commons
Yuhao Cao, Iulia Manole, Arnab Majumdar

et al.

Reliability Engineering & System Safety, Journal Year: 2024, Volume and Issue: 254, P. 110636 - 110636

Published: Nov. 6, 2024

Language: Английский

Citations

16
A novel method for ship carbon emissions prediction under the influence of emergency events DOI Creative Commons
Yinwei Feng, Xinjian Wang,

Jianlin Luan

et al.

Transportation Research Part C Emerging Technologies, Journal Year: 2024, Volume and Issue: 165, P. 104749 - 104749

Published: July 13, 2024

Accurate prediction of ship emissions aids to ensure maritime sustainability but encounters challenges, such as the absence high-precision and high-resolution databases, complex nonlinear relationships, vulnerability emergency events. This study addresses these issues by developing novel solutions: a Spatiotemporal Trajectory Search Algorithm (STSA) based on Automatic Identification System (AIS) data; rolling structure-based Seasonal-Trend decomposition Loess technique (STL); modular deep learning model Structured Components, stacked-Long short-term memory, Convolutional neural networks Comprehensive forecasting module (SCLCC). Based solutions, case using pre post-COVID-19 AIS data demonstrates reliability pandemic's impact emissions. Numerical experiments reveal that STSA algorithm significantly outperforms conventional identification standard in terms accuracy navigation state identification; SCLCC exhibits greater resistance against events excels comprehensively capturing global information, thus yielding higher accurate results. sheds light changing dynamics transport its impacts carbon

Language: Английский

Citations

14
Enabling autonomous navigation: adaptive multi-source risk quantification in maritime transportation DOI Creative Commons
Lichao Yang, Jingxian Liu, Quanlin Zhou

et al.

Reliability Engineering & System Safety, Journal Year: 2025, Volume and Issue: unknown, P. 111118 - 111118

Published: April 1, 2025

Citations

1
Decoding dependencies among the risk factors influencing maritime cybersecurity: Lessons learned from historical incidents in the past two decades DOI Creative Commons
Massoud Mohsendokht, Huanhuan Li, Christos A. Kontovas

et al.

Ocean Engineering, Journal Year: 2024, Volume and Issue: 312, P. 119078 - 119078

Published: Aug. 29, 2024

The distinctive features of maritime infrastructures present significant challenges in terms security.Disruptions to the normal functioning any part transportation can have wide-ranging consequences at both national and international levels, making it an attractive target for malicious attacks.Within this context, integration digitalization technological advancements seaports, vessels other elements exposes them cyber threats.In response critical challenge, paper aims formulate a novel cybersecurity risk analysis method ensuring security.This approach is based on data-driven Bayesian network, utilizing recorded incidents spanning past two decades.The findings contribute identification highly contributing factors, meticulous examination their nature, revelation interdependencies, estimation probabilities occurrence.Rigorous validation developed model ensures its robustness diagnostic prognostic purposes.The implications drawn from study offer valuable insights stakeholders governmental bodies, enhancing understanding how address threats affecting industry.This knowledge aids implementation necessary preventive measures.

Language: Английский

Citations

9
Enhancing maritime transportation security: A data‐driven Bayesian network analysis of terrorist attack risks DOI Creative Commons
Massoud Mohsendokht, Huanhuan Li, Christos A. Kontovas

et al.

Risk Analysis, Journal Year: 2024, Volume and Issue: 45(2), P. 283 - 306

Published: July 21, 2024

Maritime terrorist accidents have a significant low-frequency-high-consequence feature and, thus, require new research to address the associated inherent uncertainty and scarce literature in field. This article aims develop novel method for maritime security risk analysis. It employs real accident data from attacks over past two decades train data-driven Bayesian network (DDBN) model. The findings help pinpoint key contributing factors, scrutinize their interdependencies, ascertain probability of different scenarios, describe impact on manifestations terrorism. established DDBN model undergoes thorough verification validation process employing various techniques, such as sensitivity, metrics, comparative analyses. Additionally, it is tested against recent real-world cases demonstrate its effectiveness both retrospective prospective propagation, encompassing diagnostic predictive capabilities. These provide valuable insights stakeholders, including companies government bodies, fostering comprehension terrorism potentially fortifying preventive measures emergency management.

Language: Английский

Citations

8
A methodology to quantify risk evolution in typhoon-induced maritime accidents based on directed-weighted CN and improved RM DOI
Laihao Ma, Xiaoxue Ma,

Liguang Chen

et al.

Ocean Engineering, Journal Year: 2025, Volume and Issue: 319, P. 120303 - 120303

Published: Jan. 6, 2025

Language: Английский

Citations

1
Wave energy forecasting: A state-of-the-art survey and a comprehensive evaluation DOI
Ruobin Gao, Xiaocai Zhang, Maohan Liang

et al.

Applied Soft Computing, Journal Year: 2025, Volume and Issue: 170, P. 112652 - 112652

Published: Jan. 8, 2025

Language: Английский

Citations

1
Seafarer competency analysis: Data-driven model in restricted waters using Bayesian networks DOI Creative Commons
Kun� Shi, Shiqi Fan, Jinxian Weng

et al.

Ocean Engineering, Journal Year: 2024, Volume and Issue: 311, P. 119001 - 119001

Published: Aug. 15, 2024

Despite the efforts of maritime authorities to enhance seafarer competencies through International Convention on Standards Training, Certification and Watchkeeping for Seafarers (STCW), human error remains a leading cause accidents. To thoroughly investigate impact various errors among seafarers accidents, this paper aims examine relationships between accidents using data-driven approach from perspective bridge resource management (BRM). Through analysis historical accident reports, dataset associated with is established. The least absolute shrinkage selection operator (LASSO) method employed identify critical prevention. Then, Bayesian Network (BN) model, based Tree Augmented Naive Bayes (TAN) method, constructed reveal relationship types, which are validated by sensitivity case study. results indicate that key all 'Maneuvers', 'Amend/maintain ship course', 'Decision making', 'Cognitive capacity', 'Information', 'Procedure operations', 'Situational awareness' 'Communication'. Moreover, study underscores importance leveraging lessons learned past mitigate risks ensure safe operations. findings contribute deeper understanding dynamics unveiling joint different This offers valuable insights in strengthening safety regulations.

Language: Английский

Citations

4