New Technology Can Classify Mollusc Crushing Sounds

Source Domain: www.deeperblue.com

Researchers at Florida Atlantic University have developed an innovative machine learning framework to remotely detect and classify the sounds of shell-crushing predators.

These feeding events produce distinct acoustic signatures that were previously difficult to isolate from underwater background noise. However, by training models on experimental tank data, the team successfully developed a system that reliably identifies these events in both controlled and natural environments.

This new technology provides a scalable, non-invasive method for evaluating and counting predator-prey interactions at ecosystem scales. This information can offer vital insights into mollusk population dynamics and predator behavior. As a result, the information can be invaluable for improving coastal conservation management efforts.

Discussing the findings, Laurent Chérubin, corresponding author and a research professor at FAU’s Harbor Branch Oceanographic Institute, stated:

“Shell-crushing sounds contain a surprising amount of ecological information about predator-prey interactions and feeding behavior. This work shows how passive acoustic monitoring can be used not only to detect these events, but also to better understand how marine predators interact with their environment in places that are otherwise difficult to observe.”

While Matt Ajemian, senior author, an associate research professor and director of the Fisheries Ecology and Conservation Lab (FEC) at FAU Harbor Branch, added:

“From an ecological perspective, this technology opens the door to quantifying predator impacts in a way we’ve never been able to do before. Being able to remotely detect and classify feeding events means we can begin measuring predation pressure on mollusk populations at ecosystem scales, not just in isolated observations. That represents a major step forward for coastal ecology and conservation.

“Beyond simple detection, our approach also provides insight into predator behavior itself….

Source