Abstract
In this work we propose a novel spatial knowledge discovery pipeline capable of automatically unravelling the “roads of the sea” and maritime traffic patterns by analysing voluminous vessel tracking data, as collected through the Automatic Identification System (AIS). We present a computationally efficient and highly accurate solution, based on a MapReduce approach and unsupervised learning methods, capable of identifying the spatiotemporal dynamics of ship routes and most crucially their characteristics, thus deriving maritime “patterns of life” at a global scale, without the reliance on any additional information sources or a priori expert knowledge. Experimental results confirm high accuracy of results and superior performance in comparison to other methods, with the entire processing duration completing in less than 3 hours for more than a terabyte of non-uniform spatial data. Finally, to clearly demonstrate the applicability and impact of our proposed method, we evaluate its ability to detect real world “anomalies”, such as maritime incidents reported in the European Marine Casualty Information Platform. Numerical results show the advantages of our scheme in terms of accuracy, with an achieved anomaly detection accuracy of higher than 93%, by detecting 313 out of 335 relevant maritime incidents.
Highlights
With more than 80% of the global trade today being carried by sea, shipping routes or ‘‘sea roads’’ are vital to the global economy [1]
The hypothesis here is that, the majority of vessel positions future to the cut-off date used for the route definitions should fall within the convex hulls of that sea road
We evaluate ROTA’s ability to detect true ‘‘anomalies’’, such as maritime incidents reported in the European Marine Casualty Information Platform
Summary
With more than 80% of the global trade today being carried by sea, shipping routes or ‘‘sea roads’’ are vital to the global economy [1]. Sea roads though are not paved in concrete, as the location of the connector, its width and its content, can vary significantly over space and time, under the influence of various trade and carrier patterns, and due to large infrastructure investments (e.g., canal expansions), climate changes (e.g., global warming), traffic restrictions (e.g., Emission Control Areas), political events and other international incidents (e.g., increase of piracy in specific regions) Modelling this network and the spatiotemporal characteristics of ship traffic patterns is vital for improving maritime decision making and for applications such as navigation, traffic optimisation, policy making, environmental impact assessment and many more.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have