Espy Oceans stalks the troubled waters of Australia.
The oceans are warming up. The reefs are dying. The fish are on the move.
As a result, sharks and illegal fishermen roam the Australian coast in search of an increasingly elusive catch, and that, says spy on the ocean founder Ian Dewey, is having an immense impact on everything from regional tourism to ocean ecologies.
Illegal fishers, like sharks, are elusive predators. Their survival depends on being quick, quiet, and unexpected. They threaten a $1.6 billion Australian regional industry.
Sharks don’t behave like they used to. They show up in unexpected places, at unexpected times, which can result in tragedy.
“Everyone says they use drones or airships to spot them,” Dewey says. “But everyone knows that when we’re on the beach in our thong bikinis and Speedos, the last thing we want is a drone above us.”
With shadowy fleets of illegal fishing boats disabling their tracking systems to cross international borders, time is running out to fix the problem, just like wayward sharks.
“Both are growing problems,” Dewey says. “I only know of the illegal fishing missions we’ve been on, but invariably there are people around the protected areas on a daily basis.”
Traditional spotter planes can’t cope, and using satellites to track ships is nothing new. What is new is multispectral imagery.
A regular camera captures an image in just three red, green and blue (RGB) channels – producing a crisp image of the visible spectrum if the weather is clear.
A multispectral image has up to 110 different frequencies, ranging from ultraviolet to microwave.
Read also: How to unite a supergroup of whales?
This imaging technology is not new. What’s new is the application of machine learning to identify what it “sees.”
“So it was about figuring out what we could do through the clouds in any weather, preferably at dawn,” says Dewey. “I’ve just started going through what frequencies can do what and – if we’re looking for a boat – what’s it going to look like?”
It’s a similar story for sharks – what multispectral signatures do different species give off, at what depth, under what conditions, when?
Dewey says the potential for extracting such detail from hyperspectral imagery is enormous.
He can identify what a boat is made of, what kind of paint has been used (and how old it is), and what equipment is on deck.
“All of these things mean your image is different from all the other boats in the ocean,” he says. “If we see you today, we can see you tomorrow, match those frequencies and say – we got you!”
ESPy demonstrated the technology’s potential for New South Wales fisheries over the past Easter long weekend. Appropriate satellites have been identified, access to their hyperspectral cameras has been secured, and patrol ships have been stationed at strategic locations awaiting a call to action.
“Our system is incredibly fast, which gives us the edge,” Dewey says. “Generally our system allows boats to be caught in the act. This makes things a lot easier when it comes to the courts.
The shark sighting challenge is a more recent project. ESPy is in initial discussions with NSW Fisheries and the University of South Australia’s Industrial AI Research Center to develop techniques to spot predators early in the morning and use established behavior patterns to predict where they could move during the day.
While intruding trawlers present a major problem, the deadliest culprit is often someone much closer to home. A single sweep can strip an ecosystem of everything from algae and small crustaceans to dolphins and turtles, leaving damage that can take years to recover.
“Our big problem in Australia is the little guy who throws a net once or twice,” Dewey says. “It’s usually local, or at least within 100 kilometers. But he has a high risk of being caught, so he just wants to get in and get as many as he can as quickly as possible.