Modeling Vessel Behaviours by Clustering AIS Data Using Optimized DBSCAN

Abstract

Today, maritime transportation represents a substantial portion of international trade. Sustainable development of marine transportation requires systematic modeling and surveillance for maritime situational awareness. In this paper, we present an enhanced density-based spatial clustering of applications with noise (DBSCAN) method to model vessel behaviours based on trajectory point data. The proposed methodology enhances the DBSCAN clustering performance by integrating the Mahalanobis distance metric, which considers the correlation between the points representing vessel locations. This research proposes applying the clustering method to historical Automatic Identification System (AIS) data using an algorithm to generate a clustering model of the vessels’ trajectories and a model for detecting vessel trajectory anomalies, such as unexpected stops, deviations from regulated routes, or inconsistent speed. Further, an automatic and data-driven approach is proposed to select the initial parameters for the enhanced DBSCAN approach. Results are presented from two case studies using an openly available Gulf of Mexico AIS dataset as well as a Saint Lawrence Seaway and Great Lakes AIS licensed dataset acquired from ORBCOMM (a maritime AIS data provider). These research findings demonstrate the applicability and scalability of the proposed method for modeling more water regions, contributing to situational awareness, vessel collision prevention, safe navigation, route planning, and detection of vessel behaviour anomalies for auto-vessel development towards the sustainability of marine transportation.

A Review on Motion Prediction for Intelligent Ship Navigation

“…This approach trains on ship AIS trajectory data using the TensorFlow framework and reduces the time required for ship anomaly identification. Han et al introduced a density-based spatial clustering method called DBSCAN (Density-Based Spatial Clustering of Applications with Noise) [64]. They adjusted clustering-algorithm parameters using a data-driven approach to model ship behavior based on ship AIS trajectory points, identifying abnormal ship behaviors.…”

A close contact identification algorithm using kernel density estimation for the ship passenger health

“…Ref. Han et al (2021) provides an optimized DBSCAN algorithm to model ship behavior. However, one of its limitations is that it does not calculate the probability density of each data point.…”

Development of Priority Index for Intelligent Vessel Traffic Monitoring System in Vessel Traffic Service Areas

“…A method aimed at clustering the AIS coordinate data to explore the latitude and longitude lattice and spot areas of the cluster range was recently proposed [21]. In addition, a model for analyzing ship route patterns and predicting dangerous situations using DBSCAN was introduced [22], and the ship trajectory anomaly detection models such as unexpected stop, deviation from the prescribed route, or inconsistent speed, were proposed [23]. The DBSCAN algorithm was also used in another case as a method to reconstruct the damaged or missing AIS coordinate data [24].…”