An Advanced Method for Detecting Exceptional Vessel Encounters in Open Waters from High Resolution AIS Data

This paper proposes a model to estimate the frequency of close encounters between ships which can be an indication of collision risk. The model utilizes a ship domain approach to find potential exceptional encounters, which is well established in the navigational risk research community. From this set of encounters rate of turn is estimated before and after the closest point of approach (CPA) to identify exceptional encounters where the rate of turn indicates a CPA that is too close. This is a new approach to quantify the presences of risk in an encounter between two vessels. It is based on the rules of the sea (COLREGs) where a vessel required to give way must do so early and clearly from the other vessel's point of view. The model was applied to an area of Vestfjorden in Norway, and a four-year period from 2013 to 2016. The model found 707 ship pairs where one or both vessels had their ship domain violated. Using a threshold of 70 deg/min for rate of turn, 381 encounters were classified as exceptional. Normalizing encounters for distance and trips show that certain ship types are over-represented. It is concluded that the hybrid solution for estimating frequency of exceptional encounters where traditional ship domain theory and evasive manoeuvre detection combined have potential to become a solid risk assessment tool with further development.