• Jacob Bourne

Researchers Deploy Machine Listening to Decode Melting Arctic Ice Mysteries

There are many ways that scientists are ramping up efforts to track climate change, like launching methane-detecting satellites into space, flying aircraft to sample the stratosphere, gathering data from ocean buoys, taking samples out in the field, etc. Yet, a novel approach is listening to the climate, which apparently has a lot to tell us.



Arctic sea ice, polar bears
Credit: FloridaStock/Shutterstock

A collaboration between the Korea Polar Research Institute (KOPRI) and Cochl — a leader in machine listening, which applies signal processing and deep learning techniques to deepen the understanding of environmental sounds — is underway to use sound AI to analyze data related to climate change, biodiversity and other ecological changes.

The modern adage, “what happens in the Arctic doesn’t stay in the Arctic," becomes more apparent every year as warming polar temperatures and melting ice trigger wild weather patterns elsewhere on the planet. This means that the state of Arctic sea ice is a crucial indicator of climate change. The idea behind the collaboration is that the underwater acoustics in the Arctic Ocean could yield critical insights about both marine species and the climate.

"We hope our sound AI technology could help bring a paradigm shift in the underwater acoustics studies, and we are excited for this unique opportunity to contribute to sophisticated studies of acoustic habitats and climate change," says Yoonchang Han, Co-founder & CEO of Cochl.

Using AI allows researchers to automate some of the repetitive tasks associated with listening to the ocean and derive insights from AI-based quantification of time-series audio data. It represents the next chapter of work done by KOPRI to collect ecological data from the Arctic. Recent studies include validating the effects of sea ice conditions on ambient noise level, in which KOPRI analyzed data collected from underwater microphones placed off the East Siberian Shelf.


[Like what you read in The Carbonic? Help support climate journalism]

However, KOPRI’s research is formidable as it deals with terabytes of acoustic data, which is too much for a human to digest and glean insights about marine wildlife vocalizations or sea ice movement. Unique geological features in the Arctic Ocean also add complexity and make it more challenging to use traditional acoustic monitoring methods, which generally involve biologists manually sifting through sounds.

To date, Cochl’s advances in acoustic AI technology have been applied to applications like smart cities, manufacturing, the automotive industry and entertainment; however, its collaboration with KOPRI represents a new frontier for using machine listening to decipher underwater acoustics to help better understand climate change.


 

Drop a line to contact@thecarbonic.com for newsletter subscriptions, tips, questions or comments.