Artificial intelligence trained to study coral reef ‘song’

An artificial intelligence has been programmed by researchers from Exeter University to monitor the health of coral reefs by studying their sounds.

  • New research shows that artificial intelligence (AI) can track the health of coral reefs by analyzing the sounds and noises emitted by its constituent parts.
  • Exeter University used the technology to monitor the progress of coral restoration.
  • The series of recordings successfully determined the health status of the reef 92 percent of the time.

What sound does a coral reef make?? The University of Exeter, in the UK, decided to find out for scientific purposes. A team of researchers created an artificial intelligence program that can determine the health of coral reefs by listening to the sounds as they do. These living organisms, consisting of colonies of polyps and found on the bottom of seas and oceans, produce complex sounds and noise resulting from the passage of fish and other animals. By analyzing these special songs through artificial intelligence, researchers can obtain data useful in measuring coral health and initiating restoration projects when necessary.

A researcher places a hydrophone among the corals © Ben Williams – Exeter

Koraller’s favorite songs

In it study led by Professor Ben Williamsan algorithm was trained using a large database of sounds from both healthy and degraded coral reefs, so the machine can learn the difference. The artificial intelligence was then used to analyze new recordings and was able to determine the health of the coral reefs 92 percent of the time. “Coral reefs face several threats including climate changeso monitoring their health and the success of conservation projects is critical,” Williams said.

Until now, one of the biggest difficulties has come from the fact that visual and acoustic analyzes of coral reefs were based on very labor-intensive methods that only specially trained researchers could participate in. “Visual surveys are also limited by the fact that many reef creatures hide or are active at nightwhile the complexity of reef sounds has made it difficult to identify reef health using individual recordings,” Williams explained. The Exeter team took a technological approach inspired by machine learning to create a program that could recognize the song of a healthy coral reef. “Our results show that a computer can pick up patterns that are undetectable to the human ear. It can tell us faster and more accurately how the reef is doing.”

coral reefs, degradation
A coral reef that has suffered extensive degradation © The Ocean Agency

The role of coral reefs and how to avoid degradation

The recordings used in the study were made in Indonesia, where some of the local reefs are seriously damaged. The study’s authors state that the AI ​​method offers great opportunities to improve the monitoring of these important organisms. “It is a really exciting development. Audio recorders and artificial intelligence could be used all over the world to monitor the reefs’ health and discover whether efforts to protect and restore them are working,” said Dr. Tim Lamont, co-author of the study. “In many cases it is easier and cheaper to insert an underwater hydrophone on a reef and leave it there, rather than having expert divers visit the reef repeatedly to survey it – especially in remote locations.”

Around the rain 25-50 percent of the world’s coral reefs have been destroyedand a further 60 percent are threatened, according to the UN Environment Programme. These ecosystems are vital sources of food and protect the coasts of island nations. 850 million people live within 100 km of a coral reef and get economic benefits from the nearest reef. In the future, Williams is confident that the use of artificial intelligence can be expanded to other locations around the world to help with restoration projects. “We will now send recorders around the world: to the Maldives, to the Great Barrier Reef, to Mexico, to lots of different places where we have partners that can collect similar data.”

Translated by

License Creative Commons
This work is distributed under a license Creative Commons Attribution – Non-Commercial – No Derivatives 4.0 International.

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button