Grid-Based Vessel Deviation from Route Identification with Unsupervised Learning

Abstract

The application of anomaly-monitoring and surveillance systems is crucial for improving maritime situational awareness. These systems must work on the fly in order to provide the operator with information on potentially dangerous or illegal situations as they are occurring. We present a system for identifying vessels deviating from their normal course of travel, from unlabelled AIS data. Our approach attempts to solve problems with scalability and on-line learning of other grid-based systems available in the literature, by applying a dynamic grid size, adjustable per vessel characteristics, combined with a binary-search tree method for data discretization and vessel grid search. The results of this study have been validated during the Portuguese Maritime Trial in April 2022, conducted by the Portuguese navy along the southern coast of Portugal.