A new artificial intelligence tool could help scientists track and study marine mammals in the ocean.
The tool is called DeepSqueak, not because it measures dolphin calls in the ocean, but because it is based on a deep learning algorithm that was first used to categorize the different sounds of mice.
Researchers are applying the technology to large quantities of marine bioacoustics.
Underwater sound could help us understand where marine mammals swim, their density and abundance, and how they interact with one another, because much of the ocean is out of our reach.
A population of blue whales in the Indian Ocean and a never-before-heard species of beaked whale have been identified by recordings of whale songs.
Listening to recordings of the ocean and trying to pick out animal noise from hours of waves, wind, and boat engines is difficult.
DeepSqueak comes in. The technology was recently presented at the 182nd Meeting of the Acoustical Society of America, and is designed to classify underwater acoustic signals faster and more accurately than any other method to date.
DeepSqueak combs through sound data in the ocean and creates heat maps based on where acoustic signals are heard and at what frequencies.
Those signals are used to find a specific animal.
Although we used DeepSqueak to detect underwater sounds, this user-friendly, open source tool would be useful for a variety of species.
The capabilities of call detection extend to frequencies below the sounds they were intended for. Neural networks can be developed for many species due to the ability of DeepSqueak to detect variable call types.
As hours of ocean soundscapes pile up in databases around the world, scientists need to figure out how to use that information most effectively.
DeepSqueak could be an alternative to the human ear, allowing researchers to classify sounds and study them right around the world.
During tests, the fully automated tool has been able to detect the calls of specific marine mammals.
It can pick out the calls of animals in the background, which is important since sound is turning up the volume in the ocean.
DeepSqueak is a way to analyze the vocalizations used by rats and mice.
The tool was able to identify a wide range of sounds through a series of recordings, and these short mouse calls appear to be arranged in different ways depending on the context in which they are used.
Scientists could use the results to study how the sounds a mouse makes in certain situations can be used to convey fear, anxiety, or depression.
By linking contextual information to certain vocal signals, DeepSqueak could allow scientists to better study the nuances between animal vocalizations and behavior.
The research will be presented at a meeting.
All Rights Reserved © 2024
