AI helps to track lobsters when 'no two shells are the same'

After nearly three weeks at sea, Joe Sayers docks a boat filled to the brim with treasure — it's red, thorny and alive.

"There is one in here, I know there's 220 millimetres just in the carapace … there's a couple of fish in here that are probably going to be three, four kilos, I'd say, somewhere there," he said. 

"A couple of monsters."

Every year, Tasmania's commercial fishers catch just over 1,000 tonnes of southern rock lobster, valued at about $90 million.

While things are now on the up, it's been a tough few years for the industry, brought on by trade restrictions and a domestic market flooded with cheap lobsters.

"Now we're up to getting a few dollars in the bank from better prices, but our costs are going up … all the time, like fuel and baits," Mr Sayers said.

"So, you outlay a lot of money before you go to sea, you can outlay say $50,000 before you even throw the lines off."

But for Mr Sayers, it's a way of life, and after more than 30 years at sea, he wants to hand over an industry in good shape to the next generation.

'No two shells the same'

Scientists from the University of Tasmania's Institute for Marine and Antarctic Studies (IMAS), in partnership with Fiordland Lobster Company and the South Australian Lobster Company, are trying to ensure just that, through newly developed artificial intelligence (AI) technology.

"It's just like a fingerprint or facial recognition technology," associate professor at IMAS Quinn Fitzgibbon said.

"We've used AI machine learning to look at the features on the shell of the lobster, and amazingly, we've been able to show that this technology can pick up those features and they're individual.

"There's no two shells the same."

It's as simple as a quick snap on an smartphone.

If the lobster has been photographed before, the AI recognises it, and if it hasn't, into the database it goes, joining thousands of others from across Australia and New Zealand.

"Now for the first time ever, to be able to trace a lobster from where it's captured … to where it might end up in a market or a restaurant in Sydney or China, it's actually a really big deal,"

Dr Fitzgibbon said.

The team has tested the AI under various scenarios, finding it recognises a lobster three years on, dressed up in barnacles and algae, or with a fresh exoskeleton.

It can even recognise it cooked.

In time, the idea is consumers themselves will be able to photograph their dinner and know exactly where it came from.

Tackling distrust around product misplacement

The technology could be transformative for exporters like Michael Blake, who processes up to 300,000 lobsters per year at his Bicheno facility.

"It's the most premium-priced lobster in the world," he said.

"When you eat this lobster sashimi, there's nothing else like it in the world you can compare it to, and it really does stand alone."

Scientists physically tag lobsters during population surveys, but that's not viable for the industry because tags can be removed or forged.

That means once fish leave the state, there's no way of proving where they came from, and money to be made from branding a foreign lobster as prized southern rock lobster.

"The lobsters are taken out of the boxes and placed in tanks with other lobsters from other countries, as well as from Australia," Mr Blake said.

"It's all mixed up and we have no idea if it's our lobsters, it's a New Zealand lobster, it's a South African lobster, the consumer really doesn't know."

He is hopeful AI could help break into new markets, like the European Union, and strengthen trust in existing ones.

"Giving some of those restaurateurs overseas the confidence that this is guaranteed to come from here, will put the lobster on plates that it's currently not on," Mr Blake said.

Improving fisheries management

The scientists are now working to advance the technology for the processing sector, training it to record information like sex, size, colour and defects, and eventually, vitality.

"Most of these lobsters are exported overseas to China, that's a long trip, if the lobster's not healthy and vital, it unfortunately might not make that journey,"

Dr Fitzgibbon said.

Down the track, the they also want to develop it for the fishery, so commercial and recreational fishers, and even citizen scientists, can contribute to the database.

Instead of piercing lobsters, the tags could become digital.

IMAS usually has only one or two observers out at a time, but there are almost 100 commercial boats, presenting potential for much more data to inform management decisions.

"It may not necessarily change the catch limits, but it will give us more assurance that our recommendations to government are accurate and the catch is sustainable,"

IMAS senior research fellow John Keane said.

The Wild Fisheries Program leader said data would also be close to real-time, allowing quicker responses, which is useful given productivity declines brought on by climate change and habitat loss from the migration of the long-spined sea urchin.

New horizons for southern rock lobsters

It's the kind of innovation that is making Mr Sayers optimistic about where things are headed.

"It's very good that at least people are interested and trying to do what's best for the industry, to look forward to the future of the industry," he said.

"It's came a long way over the years and it can probably go a long way again."