Maritime traffic has long been an area of interest for trade, tourism and governments alike. In recent years, the increase in capabilities to generate novel insights from large amounts of data has led to a larger interest in analysis in the maritime sector. One widely used data source is the Automatic Identification System (AIS), which requires extensive status reports to be sent by most ships at regular intervals. These reports are collected by data providers. In order to utilize this data, we introduce CAPTaiN, a real-time analytics and prediction approach for maritime navigation. Our approach provides continuous monitoring of maritime traffic solely based on AIS reports, meaning that ports, port calls and the traffic network are automatically identified using AIS messages. Historic AIS data is used to predict ship behaviour, including destination ports, routes taken and behavioural anomalies. We propose a novel iterative probability update method that predicts the destination correctly at 44.9% of a voyage when selecting from 854 possible ports. Furthermore, for predictions 48 steps ahead, the median distance between the actual position and the closest of the 25 highest-probability predicted positions, selected from more than 45,000 possible positions, is 49 km.     «

Maritime traffic has long been an area of interest for trade, tourism and governments alike. In recent years, the increase in capabilities to generate novel insights from large amounts of data has led to a larger interest in analysis in the maritime sector. One widely used data source is the Automatic Identification System (AIS), which requires extensive status reports to be sent by most ships at regular intervals. These reports are collected by data providers. In order to utilize this data, we...     »