Artificial intelligence shows unprecedented detail in global fishing activities
Using only vessel movements, software able to identify more than 70,000 commercial fishing vessels
Researchers are learning more than ever before about the effects humans are having on global fish stocks.
It's all thanks to a website — funded in part by actor Leonardo DiCaprio's foundation — that tracks ships and uses a type of artificial intelligence to figure out incredible detail in worldwide fishing patterns.
Kristina Boerder, a PhD student in marine biology at Dalhousie University, is one of the researchers working with Global Fishing Watch and a co-author on a study published this week in the journal Science.
She said humans have been fishing for 42,000 years but we've been "rather in the dark" about where and how much fishing activity is happening.
"This is really a problem because this is a resource that is not infinite," Boerder told the CBC's Mainstreet. "We need a better picture of what is going on globally on the oceans in order to … understand what's happening."
Launched in 2016, the website allows users to view a world map with tens of thousands of fishing vessels moving in "near real time," which is 72 hours from the present time. The data are so detailed that individual vessels can be tracked hourly.
Using only vessel movements, the website's machine learning algorithm — a type of artificial intelligence — was able to identify more than 70,000 commercial fishing vessels.
Machine learning is a branch of computer science in which software uses a training set of data to teach itself to interpret large amounts of data — for example, how Google is able to tell with some degree of accuracy what is spam and what is email you want to receive.
Software can figure out type of fishing
Global Fishing Watch's sophisticated software, also called a neural network, can extrapolate the type of fishing the vessels are engaged in, when and where they are fishing and even the size of the engine powering the vessel.
For example, Boerder said the algorithm can distinguish purse seiners — which drive in a loop with their nets around schools of fish — from other types of fishing.
"So we see these loopy patterns in the data and others would be more straight lines, for example longliners. They set long lines with hooks and then wait until the fish bite and collect these lines so we see a back and forth pattern that sometimes can look like a Christmas tree on the map," she said.
The software can also identify potentially illegal fishing activity.
"The transponder can be switched off or it can be manipulated," said Boerder.
The study found that 55 per cent of the ocean is fished, though that number is likely higher, since some areas of the world have poor satellite coverage or vessels that do not have on-board tracking equipment.
The website observed more than 37 million hours of fishing in 2016 and vessels travelled more than 460 million kilometres — a distance three times that from the Earth to the sun.
Goal is to help protect oceans
One of the goals of the project, said Boerder, is to help enact proper legislation when it comes to fishing.
"The oceans are facing a multitude of threats and problems, one being overfishing, and in order to manage the fisheries appropriately, of course we need to see it and we need to understand it," she said.
"And this is just the first step, of course. Then we need to take the appropriate actions, a multitude of conservation actions, of course — one being marine protected areas."
Marine protected areas are a hot topic in Canada at the moment. The government has committed to an international target of protecting 10 per cent of marine and coastal areas by 2020.
"There's a lot happening in that field. I think just a year ago Canada had one per cent of the ocean protected, now we have roughly seven per cent," said Boerder.
Global Fishing Watch is a joint project between Google, digital mapping non-profit SkyTruth and ocean conservation group Oceana. It's funded by the Leonardo DiCaprio Foundation.
With files from CBC's Mainstreet