Port of Antwerp-Bruges is the second largest European sea port, handling over 9000 container vessels and over 71 million tonnes of liquid bulk. The port at Antwerp is also a very complex port as it is situated inland along the river Scheld and has a complex layout with many locks and terminals.
Monitoring the activity at the port is complex and detecting anomalous and suspicious vessel movements is difficult.
In this project, xyzt.ai helped Port of Antwerp-Bruges to use a data-driven approach to detect anomalous vessel movements. Using years of historic vessel movement data (IVEF data which is a fusion of radar and AIS data), fused with Port of Antwerp-Bruge's APICS port database data, we trained machine learning models that are then used to detect vessel movements out of the ordinary. The machine learning models are based on auto-encoders and k-nearest neighbor algorithms working on feature vectors defined from the vessel movements and important vessel data.
From the first meeting with xyzt.ai, we were very impressed with their visual analytics platform. It’s a fantastic toolbox that generates insights from large volumes of location data with incredible speed and efficiency. They also have a great team of experts with the right mindset and work ethic. Working with xyzt.ai helped Port of Antwerp-Bruges accelerate the transition towards a smart and safe port. Pieter Van Bouwel, Lead Data Scientist, Port of Antwerp-Bruges
In this project we developed novel AI machine learning models for Port of Antwerp-Bruges to detect anomalous vessel movements. The algorithms were most successful in detecting suspicious nightly activity and in detecting illegal events such as degassing activities of tanker vessels in the port and on journey to the Netherlands.
