UH uses AI to save Hawaiʻi’s coral reef colonies

HONOLULU (KHON2) — New technology may be the key to saving Hawaiʻi’s precious and threatened coral reef colonies.

On Sunday, May 21, the University of Hawaiʻi at Mānoa announced an innovation in marine conservation.

According to UH, their researchers have developed a new coral reef conservation tool. In doing so, researchers decided to use cutting-edge artificial intelligence (AI) technology.

The team developed unique deep learning algorithms that allowed coral ecologists at the School of Ocean and Earth Science and Technology (SOEST) to be able to identify and measure reef halos from space.

“Reef halos may be important indicators of the health and vitality of coral reefs, but until now, their measurement and tracking has been a challenging and time-consuming process,” said Simone Franceschini, lead author of the study and postdoctoral research fellow in the Madin Lab at the Hawai‘i Institute of Marine Biology (HIMB) in SOEST.

Also known as grazing halos or sand halos, reef halos have been identified to consist of ring-like patterns of bare sand that occur around coral patch reefs. The best thing about these halos is that they’re readily visible from satellite images.

“With this new method, we can accurately identify and measure reef halos on a global scale in a tiny fraction of the time it would take a human being to accomplish the same task,” added Franceschini.

As an ecosystem, coral reefs are one of the most diverse on the planet; and it is upon these delicate systems that many millions of people globally depend.

Over the last couple of centuries, human innovation has put coral reefs under threat, according to research. From overfishing to climate change and many other factors, the trend toward irreparable damage to reef ecosystems continues.

“We’re aiming to develop a freely available remote sensing tool to monitor ecological processes over large scales to improve the understanding and management of coral reef ecosystems,” said Elizabeth Madin, the study’s senior author and associate research professor at HIMB.

Researchers said that coral reef ecosystems, particularly the impact of fisheries and marine reserves, are notoriously difficult to monitor at large scales and over time.

“Our current research shows that reef halos may represent an emerging opportunity to monitor reef ecosystems’ function at large scales, including in remote and otherwise inaccessible areas, added Madin. 

According to UH, something known as computer vision techniques has been increasingly used to recognize patterns in medical and biological studies in recent years. This led researchers to think outside the box.

“This work stems from our team’s understanding of the current state of AI technology and its potential applications for conservation research in coral reef ecosystems,” Madin added.

The identification of halos is a challenge that required combining different deep learning algorithms since each colony is a complex, ecological pattern with much variation.

“Reef halos are sometimes very clear in satellite imagery, with distinct edges and high contrast with background vegetation, but sometimes they are quite faint and hard to distinguish—even by a highly trained observer,” Franceschini said.

He went on to explain further.

“In the end, our team was able to develop a set of algorithms capable of taking into account the diversity of these patterns globally and identify and measure halos with surprising accuracy. It is hugely satisfying for us to now have built something that can accurately identify more than 90% of halos in some parts of the world,” added Franceschini.

Researchers on this project said they hope that in the near future they will be able to develop a free web app that can allow conservation practitioners, scientists and resource managers to remotely, quickly and inexpensively monitor aspects of reef health using satellite or drone imagery.

“This breakthrough is a key step in scaling up—in both space and time—our ability to monitor and quantify aspects of coral reef ecosystem health,” Madin said.

Hence, this is a more efficient and effective way of measuring coral reefs and their surrounding halos.

“[It] paves the way for the development of a global-scale reef conservation and monitoring tool based on the phenomenon of reef halos, concluded Madin.

The study was published recently in Remote Sensing of Environment.