Accenture, Intel and the Philippines-based Sulubaaï Environmental Foundation have developed a new solution powered by artificial intelligence (AI) to monitor, characterize and analyze coral reef resiliency. The solution — the work product of Project: CORaiL, an initiative the three organizations created in 2019 — has been deployed in a reef in the Philippines since last year.
Coral reefs are some of the world’s most diverse ecosystems, with more than eight hundred species of corals building and providing habitats and shelter for approximately 25% of global marine life. The reefs also benefit humans — protecting coastlines from tropical storms, providing food and income for 1 billion people, and generating US$9.6 billion in tourism and recreation annually. But reefs are being endangered and rapidly degraded by overfishing, bottom trawling, warming temperatures and unsustainable coastal development.
“Project: CORaiL is an incredible example of how AI and edge computing can be used to help researchers monitor and restore the coral reef. We are very proud to partner with Accenture and the Sulubaaï Environmental Foundation on this important effort to protect our planet,” said Rose Schooler, corporate vice president in Intel’s sales and marketing group.
A critical element of Project: CORaiL was to identify the number and variety of fish around a reef, which serve as an important indicator of overall reef health. Traditional coral reef monitoring efforts involve human divers manually capturing video footage and photos of the reef. In addition to being dangerous and time-intensive, this approach can disrupt marine life, as divers might inadvertently frighten fish into hiding.
Engineers from Accenture, Intel and Sulubaaï implemented an artificial, concrete reef — called a Sulu-Reef Prosthesis (SRP) — to provide support for unstable coral fragments underwater. The SRP was designed by Sulubaaï and placed in the reef surrounding the Pangatalan Island in the Philippines. Fragments of living coral were planted on it and will grow and expand, providing a hybrid habitat for fish and marine life.
The engineers then strategically placed intelligent underwater video cameras, equipped with the Accenture Applied Intelligence Video Analytics Services Platform (VASP), to detect and photograph fish as they pass by. VASP uses AI, powered by Intel Xeon, Intel FPGA Programmable Acceleration Cards and Intel Movidius VPU, to count and classify the marine life. The data is then sent to a surface dashboard, providing analytics and trends to researchers on the ground in real-time, enabling them to make data-driven decisions that will help the reef progress.
“The value of your data depends on how quickly you can glean insights to make decisions from it,” said Athina Kanioura, Accenture’s chief analytics officer and Accenture Applied Intelligence lead. “With the ability to do real-time analysis on streaming video, VASP enables us to tap into a rich data source — in effect doing ‘hands on’ monitoring without disrupting the underwater environment.”
Since being deployed in May 2019, the solution has collected roughly 40,000 images, which researchers have used to gauge reef health in real-time.
“Artificial intelligence provides unprecedented opportunities to solve some of society’s most vexing problems,” said Jason Mitchell, a managing director in Accenture’s Communications, Media & Technology practice and the company’s client lead for Intel. “Our ecosystem of corporate and social partners for this ‘AI for social good’ project proves that strength in numbers can make a positive environmental impact.”
Engineers from Accenture and Intel are already at work on the next-gen Project: CORaiL prototype, which will include an optimized convolutional neural network and a backup power supply. They are also looking into infra-red cameras which will enable videos at night to create a complete picture of the coral ecosystem. Additional uses could include studying the migration rate of tropical fish to colder countries and monitoring intrusion in protected or restricted underwater areas.