(ORDO NEWS) — The ocean swims in sounds, and a new AI tool could help scientists sift through all that noise to track and study marine mammals.
This tool is called Deep Squeak, not because it measures the calls of dolphins. in the underworld of the ocean, but because it is based on a deep learning algorithm that was first used to classify various ultrasonic mouse squeals.
The researchers are now applying the technology to vast marine bioacoustics datasets.
Given that much of the ocean is out of our physical reach, underwater sound can help us understand where marine mammals swim, their density and abundance, and how they interact with each other.
Recordings of whale songs have already helped to identify an unknown population of blue whales in the Indian Ocean and a previously unknown species of beaked whales.
But listening to recordings of the ocean and trying to identify animal noise from hours of waves, wind, and boat engines is slow and painstaking work.
This is where DeepSqueak comes in. This technology was recently presented at the 182nd meeting of the American Acoustic Society and is designed to classify underwater acoustic signals faster and more accurately than any other method to date.
Deep Squeak looks at sound data in the ocean and creates a kind of heat map based on where and at what frequency certain acoustic signals are heard.
These signals are then transmitted to a specific animal.
“While we used Deep Squeak to detect underwater sounds, this handy open source tool would be useful for a variety of terrestrial species,” says Elizabeth Ferguson, CEO and founder of Ocean Science Analytics, presented the study.
“Call detection capabilities extend to frequencies below ultrasonic sounds, for which it was originally intended. Thanks to this and the ability of Deep Squeak to detect variable types of calls, the development of neural networks is possible. for many species of interest.”
Marine acoustic noise has never been easier to collect, but as databases around the world accumulate hours of ocean soundscapes, scientists need to figure out how to use this information most effectively. .
Deep Squeak could be a possible alternative to the human ear, allowing researchers to classify and study sounds from around the world with incredible efficiency.
Fully automated tool constantly for detecting special calls. marine mammals such as humpback whales, dolphins and fin whales during testing.
It can also distinguish between the calls of these animals in background noise, which is important given that man-made sound amplifies the volume into the ocean.
Deep Squeak was first introduced in 2019 as a way to analyze the rich repertoire of ultrasonic vocalizations used by rats and mice.
Looking through a series of squeaky recordings, the instrument was able to identify a wide range of syllabic sounds, and these short mouse calls appear to be arranged differently depending on the context in which they are used.
The results could help scientists study how certain syllables and syntax can convey unique information in the mouse world. For example, the sounds a mouse makes in certain situations can be used to convey fear, anxiety, or depression.
By reliably associating contextual information with specific vocal cues, Deep Squeak could enable scientists to better understand the nuances between vocalizations and animal behavior even in remote ocean underworlds where some of the planet’s most elusive animals swim.
Contact us: [email protected]