Linking causal factors and the human element in maritime accidents using K-means clustering

It is widely accepted that a shipping accident is a result of many factors. The human element onboard is usually involved as it has the overall control of the vessel. The aim of this paper is to investigate how a series of different factors are coexisting in shipping accidents and to contribute to the better understanding of these factors so that more targeted staff training, manning and shipping maintenance measures can be taken to prevent future events. Our methodology involves the systematic review and analysis of comprehensive reports from 355 shipping accidents which are publicly available from the European Maritime Safety Agency (EMSA). We generated a dataset based on the reports and analysed the data using the K-means clustering method with a selection of 15 a priori defined clusters. In our findings, fishing vessels demonstrated the highest representation regarding the total number of clusters, followed by general cargo and containerships. Collision and grounding were the type of casualty involved in most accidents with human-related causes being present in the majority of the cases. Overall, our results indicate that human factors often coexist with parameters related to the condition of the ship and other external factors (i.e., bad weather).