Big data for Maritime Domain Awareness: An AIS case study

Waldo Kleynhans
2018 Zenodo  
The world's oceans is of critical importance to humanity as it is key to fisheries, shipping as well as the environment. From an economic perspective, it is estimated that 90% of all global goods and energy transportation are done by sea with millions of people being dependent on maritime related activities for their livelihood. As maritime activities increase globally, there exist a greater dependency on technology in the monitoring, control and surveillance of vessel activities. One of the
more » ... t prominent systems for monitoring vessel activity is Automatic Identification System (AIS). AIS operates in the VHF band and transmits messages from vessels which can be received by other vessels, terrestrial shore stations as well as satellites. When dealing with AIS data, two pertinent factors to consider are: 1. AIS data fidelity: Due to the fact that AIS is broadcast in a non-secure channel, information could be manipulated / corrupted (such as malicious or inadvertently introduced false GPS positions and errors in vessel parameters). In addition, AIS receivers are not controlled in the same manner as AIS transmitters, which could introduce additional errors at the receiver side . 2. Significant volume increase of AIS messages: Due to the global increase in vessels fitted with AIS transmitters as well as the proliferation of satellite and terrestrial receiving stations there has been a significant increase in AIS messages received globally (estimated at over a 40% increase over the last four years [1]). While this increase in AIS data volumes is beneficial as this enriches the information available to maritime authorities, processing and storage of these large data volumes can become problematic especially when performing analytics based on historic vessel temporal and positional data. By using advanced filtering and analytics, IMIS Global Limited has been able to process the AIS data stream to eliminate a large portion of the faulty data (as described in point 1) and is also focusing on the efficien [...]
doi:10.5281/zenodo.2274078 fatcat:5bgkw7kt3rdilkuvi3kaur3ami