Artificial intelligence (AI) can track coral reef health by learning the “song of the reef,” new research shows.
In the new study, scientists at the University of Exeter trained a computer algorithm using multiple recordings of healthy and degraded reefs, which allowed the machine to learn the difference.
The computer then analyzed a large number of new recordings and successfully identified the reef’s health 92% of the time.
The team used this to track the progress of reef restoration projects.
“Coral reefs face multiple threats, including: climate changeso monitoring their health and the success of conservation projects is vital,” said lead author Ben Williams.
“A major difficulty is that visual and acoustic surveys of reefs usually rely on labour-intensive methods.
“Visual examination is also limited by the fact that many reef animals are hiding or active at night, while the complexity of reef sounds has made it difficult to identify reef health using individual recordings.
“Our approach to that problem was to use machine learning– to see if a computer could learn the reef’s song.
“Our findings show that a computer can pick up patterns that are imperceptible to the human ear. It can tell us more quickly and accurately how the reef is doing.”
The fish and other creatures that live on Coral reef create a wide variety of sounds.
The meaning of many of these calls remains unknown, but the new AI method can distinguish between the common sounds of healthy and unhealthy reefs.
The images used in the study were taken at the Mars Coral Reef Restoration Project, which is restoring heavily damaged reefs in Indonesia.
Co-author Dr. Tim Lamont, of Lancaster University, said the AI method creates great opportunities to improve monitoring of coral reefs.
“This is a really exciting development. Sound recorders and AI could be used around the world to monitor the health of reefs and find out if efforts to protect and restore them are working,” said Dr. Lamont.
“In many cases it is easier and cheaper to place an underwater hydrophone on a reef and leave it there than to have experienced divers visit the reef. reef repeatedly to investigate it, especially in remote locations.”
The article was published in the magazine Ecological indicators†
Ben Williams et al, Improving automated analysis of marine soundscapes using eco-acoustic indices and machine learning, Ecological indicators (2022). DOI: 10.1016/j.ecolind.2022.108986
University of Exeter
Quote: AI learns coral reef ‘song’ (2022, May 27) retrieved May 27, 2022 from https://phys.org/news/2022-05-ai-coral-reef-song.html
This document is copyrighted. Other than fair dealing for personal study or research, nothing may be reproduced without written permission. The content is provided for informational purposes only.
#learns #coral #reef #song