A data-driven Bayesian Network for risk modeling and causal analysis of global maritime accidents

H. Y. Jiang; J. F. Zhang; C. P. Wan; M. Y. Zhang; C. Guedes Soares

doi:10.1201/9781003508762-36

A data-driven Bayesian Network for risk modeling and causal analysis of global maritime accidents

H. Y. Jiang, J. F. Zhang, C. P. Wan, M. Y. Zhang, C. Guedes Soares

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

Abstract

Multiple factors may cause maritime accidents. Investigating the impact of risk factors on maritime accidents is imperative. This paper employs a data-driven Bayesian network approach to explore the impact of risk factors on maritime safety using a large dataset of maritime accidents. The interdependencies among risk influencing factors are modeled using a Tree Augmented Network, followed by the sensitivity analysis and model validation. The results indicate that the key risk influencing factors influencing maritime accidents mainly include ship location, type, age, gross tonnage, and deadweight tonnage. This study contributes to the prevention of specific types of maritime accidents.

Original language	English
Title of host publication	Advances in Maritime Technology and Engineering
Editors	C. Guedes Soares, Tiago A. Santos
Publisher	CRC Press
Pages	287-295
Number of pages	9
Volume	1
ISBN (Electronic)	978-1-003-50876-2
ISBN (Print)	978-1-032-83099-5, 978-1-032-83310-1
DOIs	https://doi.org/10.1201/9781003508762-36
Publication status	Published - 2024
MoE publication type	A4 Conference publication
Event	International Conference on Maritime Technology and Engineering - Lisbon, Portugal Duration: 14 May 2023 → 16 May 2023 Conference number: 7

Publication series

Name	Proceedings in Marine Technology and Ocean Engineering
Volume	13
ISSN (Print)	2638-647X
ISSN (Electronic)	2638-6461

Conference

Conference	International Conference on Maritime Technology and Engineering
Abbreviated title	MARTECH
Country/Territory	Portugal
City	Lisbon
Period	14/05/2023 → 16/05/2023

Access to Document

10.1201/9781003508762-36

Cite this

Jiang, H. Y., Zhang, J. F., Wan, C. P., Zhang, M. Y., & Soares, C. G. (2024). A data-driven Bayesian Network for risk modeling and causal analysis of global maritime accidents. In C. G. Soares, & T. A. Santos (Eds.), Advances in Maritime Technology and Engineering (Vol. 1, pp. 287-295). (Proceedings in Marine Technology and Ocean Engineering; Vol. 13). CRC Press. https://doi.org/10.1201/9781003508762-36

@inproceedings{4d31e955e8a04da09b681d39ea34487e,

title = "A data-driven Bayesian Network for risk modeling and causal analysis of global maritime accidents",

abstract = "Multiple factors may cause maritime accidents. Investigating the impact of risk factors on maritime accidents is imperative. This paper employs a data-driven Bayesian network approach to explore the impact of risk factors on maritime safety using a large dataset of maritime accidents. The interdependencies among risk influencing factors are modeled using a Tree Augmented Network, followed by the sensitivity analysis and model validation. The results indicate that the key risk influencing factors influencing maritime accidents mainly include ship location, type, age, gross tonnage, and deadweight tonnage. This study contributes to the prevention of specific types of maritime accidents.",

author = "Jiang, {H. Y.} and Zhang, {J. F.} and Wan, {C. P.} and Zhang, {M. Y.} and Soares, {C. Guedes}",

note = "Publisher Copyright: {\textcopyright} 2024 The Author(s).; International Conference on Maritime Technology and Engineering, MARTECH ; Conference date: 14-05-2023 Through 16-05-2023",

year = "2024",

doi = "10.1201/9781003508762-36",

language = "English",

isbn = "978-1-032-83099-5",

volume = "1",

series = "Proceedings in Marine Technology and Ocean Engineering",

publisher = "CRC Press",

pages = "287--295",

editor = "Soares, {C. Guedes} and Santos, {Tiago A.}",

booktitle = "Advances in Maritime Technology and Engineering",

address = "United States",

}

Jiang, HY, Zhang, JF, Wan, CP, Zhang, MY & Soares, CG 2024, A data-driven Bayesian Network for risk modeling and causal analysis of global maritime accidents. in CG Soares & TA Santos (eds), Advances in Maritime Technology and Engineering. vol. 1, Proceedings in Marine Technology and Ocean Engineering, vol. 13, CRC Press, pp. 287-295, International Conference on Maritime Technology and Engineering, Lisbon, Portugal, 14/05/2023. https://doi.org/10.1201/9781003508762-36

A data-driven Bayesian Network for risk modeling and causal analysis of global maritime accidents. / Jiang, H. Y.; Zhang, J. F.; Wan, C. P. et al.
Advances in Maritime Technology and Engineering. ed. / C. Guedes Soares; Tiago A. Santos. Vol. 1 CRC Press, 2024. p. 287-295 (Proceedings in Marine Technology and Ocean Engineering; Vol. 13).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - A data-driven Bayesian Network for risk modeling and causal analysis of global maritime accidents

AU - Jiang, H. Y.

AU - Zhang, J. F.

AU - Wan, C. P.

AU - Zhang, M. Y.

AU - Soares, C. Guedes

N1 - Conference code: 7

PY - 2024

Y1 - 2024

N2 - Multiple factors may cause maritime accidents. Investigating the impact of risk factors on maritime accidents is imperative. This paper employs a data-driven Bayesian network approach to explore the impact of risk factors on maritime safety using a large dataset of maritime accidents. The interdependencies among risk influencing factors are modeled using a Tree Augmented Network, followed by the sensitivity analysis and model validation. The results indicate that the key risk influencing factors influencing maritime accidents mainly include ship location, type, age, gross tonnage, and deadweight tonnage. This study contributes to the prevention of specific types of maritime accidents.

AB - Multiple factors may cause maritime accidents. Investigating the impact of risk factors on maritime accidents is imperative. This paper employs a data-driven Bayesian network approach to explore the impact of risk factors on maritime safety using a large dataset of maritime accidents. The interdependencies among risk influencing factors are modeled using a Tree Augmented Network, followed by the sensitivity analysis and model validation. The results indicate that the key risk influencing factors influencing maritime accidents mainly include ship location, type, age, gross tonnage, and deadweight tonnage. This study contributes to the prevention of specific types of maritime accidents.

UR - http://www.scopus.com/inward/record.url?scp=85195144027&partnerID=8YFLogxK

U2 - 10.1201/9781003508762-36

DO - 10.1201/9781003508762-36

M3 - Conference article in proceedings

AN - SCOPUS:85195144027

SN - 978-1-032-83099-5

SN - 978-1-032-83310-1

VL - 1

T3 - Proceedings in Marine Technology and Ocean Engineering

SP - 287

EP - 295

BT - Advances in Maritime Technology and Engineering

A2 - Soares, C. Guedes

A2 - Santos, Tiago A.

PB - CRC Press

T2 - International Conference on Maritime Technology and Engineering

Y2 - 14 May 2023 through 16 May 2023

ER -

A data-driven Bayesian Network for risk modeling and causal analysis of global maritime accidents

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this