Maritime accident risk estimation for sea lanes based on a dynamic Bayesian network

Meizhi Jiang and Jing Lu

Maritime Policy & Management, 2020, vol. 47, issue 5, 649-664

Abstract: The safety of maritime transportation has become increasingly important with the development of international economics and trade. This paper introduces a dynamic Bayesian network (DBN) model to facilitate the estimation of the dynamic emergency risk in sea lanes. The DBN model is a novel model that can efficiently represent and infer complex stochastic knowledge. To construct this model, available data, which were collected from emergency investigation reports by the International Maritime Organization (IMO), are employed in conjunction with expert knowledge to develop and demonstrate a BN; an evidence theory approach is applied to calculate the prior probability with the help of historical data; the conditional probability is learned by the expectation maximization (EM) algorithm; and the transition probability is obtained by a Markov model. Finally, the Viterbi algorithm is adopted to estimate emergency risk. The emergencies that occurred in the Indian Ocean from 2009 to 2018 were used as a case study for risk estimation. Sensitivity analysis was conducted to identify significant influential factors. The results show that the sea lane risk in the Indian Ocean fluctuates within a small range, presenting an overall downward trend over time. These findings provide a reference for maritime stakeholders to make proper decisions.

Date: 2020
References: Add references at CitEc
Citations: View citations in EconPapers (7)

Downloads: (external link)
http://hdl.handle.net/10.1080/03088839.2020.1730995 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:marpmg:v:47:y:2020:i:5:p:649-664

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/TMPM20

DOI: 10.1080/03088839.2020.1730995

Access Statistics for this article

Maritime Policy & Management is currently edited by Dr Kevin Li and Heather Leggate McLaughlin

More articles in Maritime Policy & Management from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().