Probabilistic ship domain with applications to ship collision risk assessment

Abstract

Ship domain plays a critical role in ship traffic risk assessment and safe navigation. Today, the widely available AIS data makes it possible to capture the diverse behaviors of navigators and navigational conditions by vessel trajectories in practice. We propose the novel concept of probabilistic ship domain, which depicts the ship domain boundary as the vague value rather than the crisp value with a forbidden boundary and a desired boundary. We also develop an effective big AIS data driven approach to determine the probabilistic ship domain. We further investigate how to use the probabilistic ship domain to assess ship collision risk. Finally, a few case studies from the Singapore Strait are conducted to show the merits of the probabilistic ship domain and the big AIS data driven approach.