AI can help authorities track ‘ghost’ fishing boats | Science

Spread the love

In February 2019, the 60-meter-long South Korean fishing vessel Oyang 77 slipped into Argentinian waters and deployed its trawls, bringing in over 140 tonnes of hake, rays and squid. The vessel did not have permission to fish in those waters, according to Argentine officials, and to avoid detection the crew turned off a beacon that sends a vessel’s precise position via satellite to maritime authorities. But the coast guard caught the Oyang 77confiscated the catch and destroyed his nets.

Now, researchers have used artificial intelligence to help authorities more easily decipher which ships like the Oyang 77 what they do when it is dark and if they are fishing illegally. The approach is already guiding some law enforcement agencies in planning their patrols.

Illegal fishing accounts for catches worth around $25 billion a year and includes endangered species such as sharks. Some ships were captured with enslaved crews. Although there is growing political awareness of the problem, governments have not taken enough action, says Rashid Sumaila, an oceans and fisheries economist at the University of British Columbia in Vancouver. “This document shows some of the possibilities we can achieve,” says Sumaila, who was not involved. “I think there is hope.”

To avoid collisions, international law requires many large boats to carry beacons that broadcast their position. These signals, called Automatic Identification System (AIS), are displayed in real time on websites as an aid to navigation.

For the researchers, recordings from these locations give telltale signs of activity: vessels move in one direction to deploy a long, drifting line of baited hooks, then turn back to bring in the catch. Vessels chasing tuna make loops by encircling a school of fish with a giant net. Researchers analyzing these patterns have created global maps of commercial fishing, showing that these vessels regularly fish in more than half of the world’s oceans.

But sometimes the beacons go silent, making ships invisible to other boats and searchers. This may be the result of poor satellite reception or technical issues with the devices. Other times, researchers suspect, captains disable devices to avoid detection.

Would it be possible to distinguish innocent problems from harmful activities? “It seemed like a really mature question,” says Heather Welch, a space ecologist at the University of California, Santa Cruz, “and a huge problem to solve.”

To do this, Welch and his colleagues turned to a kind of artificial intelligence called machine learning. These computer programs can make sense of large amounts of data, such as the billions of AIS locations stored in public databases.

First, the researchers identified case studies that clearly resembled deliberate beacon deactivation, such as when the signal suddenly ceased and then came back on at full strength. They also found examples where the problem appeared to be technical, such as a weakened and intermittent signal. These examples helped train machine learning programs to recognize signs of ships trying to evade detection.

The analysis detected more than 55,000 instances in which the crew appeared to deliberately turn off their AIS beacons between 2017 and 2019. A total of 5,269 vessels went missing for around 5 million hours while fishing.the team reports today in Scientists progress. Some disappear for days or even weeks.

“Some vessels come out and disappear, hiding from responsibility,” says study co-author Tyler Clavelle, data scientist at Global Fishing Watch, an environmental nonprofit. The new method “is a way to fill in the blind spots,” he adds. “Literally”.

Much of this activity was concentrated in areas known to have problems with illegal fishing, such as the northwest Pacific Ocean. Other hotspots include the rich fishing grounds off Argentina and West Africa, where foreign vessels fish without permission. The researchers also found that many fishing vessels deactivated their beacons when approaching refrigerated cargo ships, a way to sell illegal catches at sea to avoid being caught in ports.

Fisheries enforcement consultant Pramŏd Ganapathiraju calls the research “great work” as the analysis shows which country fleets are most likely to turn off their AIS beacons. Cases near an exclusive economic zone frequently involved Chinese and Spanish flagged vessels. Details of locations, times and vessels will help coastal states take action against suspected illegal activities, says Ganapathiraju, who was not involved in the research.

Not all escapes are criminal. Another hidden ship hotspot was in Alaskan waters, where US ships must also carry a beacon that cannot be turned off and is visible only to authorities. That means these trawlers can’t hide from law enforcement, so they’re probably not fishing illegally, Welch says. Instead, they’re likely turning off their AIS beacons so competitors can’t track them to good fishing spots, she notes. In other areas, such as off East Africa, ships may conceal their location from pirates.

Welch continues his work. It receives funding from the United States National Oceanographic and Atmospheric Administration’s Office of Law Enforcement to use AIS data to improve the protection of sharks from illegal tuna fishing. For 3 years, Global Fishing Watch has been sharing its AIS analyzes with the US Coast Guard to help them plan patrols in the North Pacific, which has increased violation detections. They are also developing an analytical tool to help port authorities prioritize fishing vessels for inspection. Knowing that a vessel had turned off its beacon while at sea is a clue that it might have been fishing illegally, Clavelle says.

Tracking fishing vessels via AIS can help reduce the cost of fisheries law enforcement, notes Sumaila. But it is easier for developed countries to enforce the law by sending patrol boats to catch violators, while poor countries continue to bear the burden of illegal fishing. The key, he says, is to make it unprofitable by increasing the risk of being apprehended and facing a significant penalty: in 2019, for example, the Indonesian Ministry of Fisheries blew up vessels caught fishing illegally.

Leave a Comment

Your email address will not be published.