Skip to content
Join our Newsletter

Bringing AI to commercial fishing

Vancouver startup wins prize for technology that uses AI to calculate bycatch
alaska-fishers-2-watershedwatchskeenawild
What's in that net? Using machine learning, new technology could identify fish species and numbers in commercial fishing nets. | WastershedWatch-SkeenaWild

A startup spun out of the University of BC has won $10,000 to help it advance a monitoring system that uses video and artificial intelligence to better calculate catch and bycatch for commercial fishing boats.

OnDeck Fisheries AI was one of four Canadian startups developing oceans technology that recently won $10,000 prizes in a competition run by the Ocean Startup Project.

Another startup, PhyCo., made up of a team from Burnaby and Prince Edward Island, also won $10,000 for a biodegradable bioplastic made from seaweed.

OnDeck Fisheries AI, which was admitted to UBC’s Venture Founder CORE program earlier this year, also recently won a US$25,000 prize through Dempsey Startup Competition hosted by the University of Washington’s Foster School Buerk Center for Entrepreneurship.

The problem of under reporting bycatch in commercial fisheries is something Daniel Pauly, a renowned fisheries biologist at the University of BC, has studied.

Pauly and his team at the Sea Around Us institute at UBC have estimated that the global commercial catch could be 30% higher than reported, with unreported bycatch being a significant part of the under reporting.

Pauly is one of the advisers for OnDeck Fisheries AI, which has developed a video monitoring and scanning system that uses machine learning and “computer vision” to analyze all the fish in a net to give quick, accurate estimates of the types and number of fish caught in a net. This could make for more accurate reporting of both catch and bycatch.

“The Idea Challenge was invaluable in helping us validate our business idea and understand its potential through the lens of prospective customers,” said OnDeck Fisheries AI CEO and co-founder Alexander Dungate.

[email protected]

nbennett_biv