UVic Researchers Uncover Unique Fish Sounds Using AI Technology

University of Victoria (UVic) biologists have made a significant discovery, revealing that closely related fish species produce unique and distinctive sounds. This breakthrough allows researchers to identify fish based solely on their acoustic signatures, opening new avenues for marine conservation efforts.

Utilizing passive acoustic monitoring techniques, the researchers identified specific sounds from eight different fish species commonly found on Vancouver Island. Their innovative approach led to the development of a machine learning model capable of predicting fish species based on sound with an impressive accuracy of up to 88 percent. This advancement could enhance scientists’ ability to monitor specific fish populations through sound, according to Darienne Lancaster, a PhD candidate in biology who spearheaded the project.

“We knew previously that many fish were making sounds in the wild, but we didn’t know which sounds belonged to which species, or if it was possible to tell these sounds apart,” Lancaster explained. “Now, just as we use bird song to identify specific bird species in the wild, we can also listen to fish sounds to identify specific fish species.”

Identifying Fish Sounds in Their Natural Habitats

The research, published in the Journal of Fish Biology, is part of a broader initiative led by the Juanes Lab at UVic. While researchers have previously identified fish sounds, these studies often occurred in laboratory settings and did not assess whether distinct species produced unique sounds. Lancaster and her team focused on eight fish species prevalent along the coast of British Columbia: the Black Rockfish, Quillback Rockfish, Copper Rockfish, Lingcod, Canary Rockfish, Vermillion Rockfish, Kelp Greenling, and Pile Perch. Notably, this research represents the first identification of sounds for both the Canary and Vermillion Rockfish, whether in the lab or the field.

“It’s been exciting to see how many different species of fish make sounds and the behaviors that go along with these calls,” Lancaster noted. “Some fish, like the Quillback Rockfish, emit rapid grunting noises when being chased, likely as a defensive mechanism. Others, like the Copper Rockfish, produce knocking sounds while hunting prey on the ocean floor.”

The Black Rockfish generates a growling sound reminiscent of a frog croak, while the Quillback Rockfish creates a series of short knocks and grunts.

The Role of Passive Acoustics in Conservation

To differentiate the fish sounds, Lancaster employed passive acoustic monitoring, collecting underwater audio and video with a sound localization array developed by Xavier Mouy, a former UVic PhD student. The research team analyzed sound characteristics, focusing on 47 different sound features, including duration and frequency, to distinguish between species calls. The machine learning model grouped species calls by identifying subtle differences in their acoustic signatures.

“The ability of passive acoustics to identify specific fish by sound could be an important new tool for conservationists and fisheries managers,” said Francis Juanes, a UVic biology professor and project principal investigator. “Passive acoustics could allow us to estimate population size, monitor activity, and assess the overall health of a fish population in a minimally invasive manner.”

The techniques developed by Lancaster and her team can be adapted by scientists globally to decipher fish calls, promoting enhanced understanding of marine ecosystems.

The research is part of the wider Fish Sounds project, which includes several components: FishSounds.net, an online database of global peer-reviewed fish sounds research; The Codcast, a podcast exploring the Arctic cod grunt; and Fish Sounds Educate, a free educational program designed to inspire future conservation leaders and improve ocean literacy across Canada.

Funding for this research was provided by the Natural Sciences and Engineering Research Council of Canada and Fisheries and Oceans Canada. The project aligns with the United Nations Sustainable Development Goals 14, which focuses on life below water, highlighting the importance of sustainable marine ecosystems.

Through these groundbreaking findings, UVic’s research team not only enhances our understanding of fish communication but also provides vital tools for marine conservation strategies moving forward.