Ship AIS Trajectory Clustering: An HDBSCAN-Based Approach

Lianhui Wang,Pengfei Chen,Linying Chen,Junmin Mou

doi:10.3390/jmse9060566

Abstract

The Automatic Identification System (AIS) of ships provides massive data for maritime transportation management and related researches. Trajectory clustering has been widely used in recent years as a fundamental method of maritime traffic analysis to provide insightful knowledge for traffic management and operation optimization, etc. This paper proposes a ship AIS trajectory clustering method based on Hausdorff distance and Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN), which can adaptively cluster ship trajectories with their shape characteristics and has good clustering scalability. On this basis, a re-clustering method is proposed and comprehensive clustering performance metrics are introduced to optimize the clustering results. The AIS data of the estuary waters of the Yangtze River in China has been utilized to conduct a case study and compare the results with three popular clustering methods. Experimental results prove that this method has good clustering results on ship trajectories in complex waters.

Highlights

With the development of the marine industry and the rise of Automatic Identification System (AIS) data mining, more and more researchers use AIS to analyze maritime traffic problems [1,2,3]
The HDBSCAN method is applied to cluster the trajectory data and clustering performance metrics are proposed to test the performance of the method
In the previous section, a series of case studies are conducted to illustrate the process of the HDBSCAN algorithm on trajectory clustering in the area of ship complex confluence

Summary

Introduction

With the development of the marine industry and the rise of AIS data mining, more and more researchers use AIS to analyze maritime traffic problems [1,2,3]. Cluster analysis is to group or cluster data according to the inherent similarity and characteristics between data to achieve the purpose of data mining [4]. The clustering results may show the usual route and traffic volume distribution and regularity of marine environmental change [5,6,7]. As a commonly used data mining method, ship trajectory clustering integrates the trajectory data of different ships into different categories or clusters. It’s beneficial for the maritime traffic management stakeholders, such as Maritime Safety Administration (MSA), to obtain insights on the operation status and characteristics of the regional traffic. Ship trajectory clustering is one of the fundamental methods for trajectory prediction, anomaly detection, and avoiding ship collision [8,9], which draws much attention from academia

Objectives

Methods

Findings

Discussion

Conclusion