Research Area:  Machine Learning

Abstract:

Maritime Situational Awareness (MSA) is a critical component of intelligent maritime traffic surveillance. However, it becomes increasingly challenging to gain MSA accurately given the growing complexity of ship traffic patterns due to multi-ship interactions possibly involving classical manned ships and emerging autonomous ships. This study proposes a new traffic partitioning methodology to realise the optimal maritime traffic partition in complex waters. The methodology combines conflict criticality and spatial distance to generate conflict-connected and spatially compact traffic clusters, thereby improving the interpretability of traffic patterns and supporting ship anti-collision risk management. First, a composite similarity measure is designed using a probabilistic conflict detection approach and a newly formulated maritime traffic route network learned through maritime knowledge mining. Then, an extended graph-based clustering framework is used to produce balanced traffic clusters with high intra-connections but low inter-connections. The proposed methodology is thoroughly demonstrated and tested using Automatic Identification System (AIS) trajectory data in the Ningbo-Zhoushan Port. The experimental results show that the proposed methodology 1) has effective performance in decomposing the traffic complexity, 2) can assist in identifying high-risk/density traffic clusters, and 3) is sufficiently generic to handle various traffic scenarios in complex geographical waters. Therefore, this study makes significant contributions to intelligent maritime surveillance and provides a theoretical foundation for promoting maritime anti-collision risk management for the future mixed traffic of both manned and autonomous ships.

Keywords:  

Author(s) Name:  Xuri Xin, Kezhong Liu, Sean Loughney, Jin Wang, Huanhuan Li, Zaili Yang

Publisher name:  ScienceDirect

DOI:  10.1016/j.eswa.2023.120825

Volume Information:  Volume 231,(2023)

Paper Link:   https://www.sciencedirect.com/science/article/pii/S0957417423013271