Comprehensive analysis of ship sinking accidents using Bayesian network

Sinking accidents can cause catastrophic losses in human, economic resources and environmental damage. Sinking accidents are one of the most common maritime accidents that occur in Indonesia. Therefore, this study aims to analyze the cause-and-effect probability of ship sinkings in Indonesian waters. Bayesian Network method and accident factor level are used to analyze the causal factors of ship sinking accidents. The results found that the Loss of Stability of the vessel is the most sensitive node. An additional take from the investigated sinking is that half of the accidents occurred on passenger vessels, and ships over 25 years old are prone to sinking due to corrosion and lack of proper maintenance. While 70.5% of accident caused by human error that is majorly triggered by unsafe acts. The real-case analysis also performed in this study reveals that eliminating Human Error and ship’s associated factors can reduce the probability of sinking by 17.2%.