Arctic waters are becoming increasingly passable as global warming advances. Increased maritime traffic is therefore expected in the region in the future. But not all ships will come with good intentions, notes Poul Bondo, Deputy Director of Gatehouse Maritime:
“Illegal shipping traffic will also make an appearance. These are ships involved in trading illegal weapons and sanctioned goods, or especially illegal fishing, which is a widespread problem in the Arctic according to the World Wildlife Fund.”
In addition to the illegal activities, several nations are also showing increasing interest in extracting resources in the Arctic region, which may lead to violations of Danish territorial waters. To prevent these undesirable activities, it is becoming increasingly necessary to monitor the sea in the Arctic. Given the enormous size of this region, it makes sense to use satellite monitoring. But what is a ship and what is an iceberg on a satellite image? And where has the ship gone in the meantime, after the satellite images have been received and the ship distinguished from the icebergs?
A new technology aims to address these issues. It will be developed jointly by DTU Space and Gatehouse Maritime, which have together received DKK 9 million from the Danish Armed Forces for the three-year project, called Dark Ships. The solution being developed will combine DTU’s many years of experience identifying icebergs from satellite data with Gatehouse Maritime’s experience collecting data from ships and predicting their future positions.
Data on shipping traffic
Gatehouse is a data and analysis company based in North Jutland. Its maritime department specializes in collecting and reselling data on shipping traffic around the world. Data is collected via the ships’ Automatic Identification System (AIS) transponders, which provide information on the ship’s cargo, route, next port of call, etc. The customers in Gatehouse Maritime’s portfolio are typically civil authorities, port authorities or military commands, seeking knowledge of the movements of ships.
Ship AIS data often does not correspond to reality, notes Henning Heiselberg, Head of Security DTU, and DTU’s anchor person on the Dark Ships project.
“Sometimes ships forget to update the information, so their AIS data does not show the correct route or time of arrival at a port. At the more serious end of the spectrum, there are the ships that turn off the transponder when they enter our waters, to hide their position and route. This can mean that they are engaged in illegal activities, and that the ship should be found and stopped,” says Henning Heiselberg.
When Gatehouse Maritime and DTU Space compare satellite data with AIS data, it will be possible to identify those objects in the Arctic Ocean that are not icebergs, but ships. If there is no AIS data for one of these ships, a ‘dark’ (illegal) ship has been identified.
Artificial intelligence used
In order to handle the large volume of data (AIS data and data from a range of European satellites), the project will develop algorithms as part of a machine learning solution, so that computer power is used to identify the illegal shipping traffic.
“With such large amounts of data, it is necessary to automate the process using machine learning and artificial intelligence. It would take too long for humans to sit and analyse them,” explains Henning Heiselberg.
The project partners will also develop the solution to be able to predict the positions of ships in time and space, notes Poul Bondo from Gatehouse:
“Once a dark ship has been identified, it will already have moved. Based on our knowledge of which routes ships usually follow and where they typically sail with a given cargo, we can start predicting where they are going to be if an authority needs to make contact, for example by flying out,” says Poul Bondo.
“The very first step towards stopping illegal shipping is to know that it is taking place, and where.”
Once the technology has been developed, it can be used in other regions of the world.