A novel framework for regional collision risk identification based on AIS data

Abstract

Identification of regional collision risk in water area is of significance for the safety of navigation. However, traditional risk identification models are subject to the limitations in accuracy, short-term identification and traffic characteristics. Herein, a framework was put forward to identify regional collision risk instantaneously based on AIS data. The vessels were clustered by using the spatial clustering method. Afterwards, the framework was divided into two steps. Firstly, collision risk of each cluster was obtained by collision risk and contribution of the vessels within the cluster. An analytical method was adopted to identify collision risk of each vessel from the perspective of vessel pairs. Contribution of each vessel was determined by using improved Shapley value method in game theory. Secondly, regional collision risk was obtained by collision risk and contribution of each cluster. Case studies were carried out based on the AIS data of Northern Yellow Sea in China to validate the validity of the proposed framework. The results show that the proposed framework can effectively identify collision risk in water area, presenting the potential for collision risk monitoring and collision risk analysis of water area.