On summer mornings, local children like to gather at Padaro Beach in California to learn to surf in gentle, whitewater waves. A few years ago, the beach also became a popular hangout for young white sharks.
That led to the launch of SharkEye, an initiative from the University of California, Santa Barbara's Benioff Ocean Science Laboratory (BOSL) that uses drones to monitor what's happening beneath the waves.
When a shark is spotted, SharkEye sends a message to the 80 or so people who have signed up for alerts, including local lifeguards, surf shop owners and parents of children taking lessons.
In recent years, other initiatives have seen government officials and lifeguards from New York to Sydney use drones to keep beachgoers safe, monitoring video streamed from a camera. That requires a pilot to stay focused on a screen, battling choppy waters and sun glare to distinguish sharks from paddleboarders, seals and billowing strands of kelp. One study found that drones monitored by humans detected sharks only 60 percent of the time.
SharkEye — part research program, part community safety tool — uses the video it collects to analyze shark behavior. It also feeds its footage into a computer vision machine learning model — a type of artificial intelligence (AI) technology that allows computers to extract information from images and video — training it to detect great white sharks off Padaro Beach, near the city of Santa Barbara.
“Automating shark detection … could (also) be very useful for many communities beyond ours here in California,” Neil Nathan, a project scientist at BOSL who graduated from Stanford University a few years ago with a master's degree in environmental studies, told CNN.
Human vs AI Shark Detection
The rise in popularity of drones and the proliferation of social media can make it seem like sharks are everywhere. It doesn’t help that warming ocean temperatures are driving sharks into new habitats, and young white sharks, which can grow to be about eight to ten feet long, like to hang out near shore, making them more visible to beachgoers.
Still, shark attacks are rare. In 2023, 69 people worldwide were bitten by unprovoked bites, which compares to an average of 63 annual incidents between 2018 and 2022. Only 10 of them died, according to the Florida Museum of Natural History’s International Shark Attack File.
Although no fatal attack has been recorded at Padaro Beach, some community members were concerned when sharks were spotted floating around.
That's why SharkEye has been conducting regular drone flights to monitor the coastline for about five years now. Once, fifteen young white sharks were spotted in one day.
Early tests show the AI technology is already performing “incredibly well,” detecting most sharks that a human can detect, and sometimes sharks that a human has missed, perhaps because they were swimming too deep to see them easily, Nathan said.
This summer, the project began testing the technology by pitting drone pilots against AI. The pilot surveys the area and counts the number of sharks they spot. Then, SharkEye’s model analyzes the video to see how many sharks it can find.
Today, community reports are based on human analysis. If all goes well, those reports could be AI-enhanced by the end of the season or early next summer, with manual monitoring and checks, Nathan said. In the future, the process could even be fully automated, making it faster and potentially more accurate.
AI and wild animals
AI technologies are being used in a myriad of ways to mitigate human-wildlife conflict. In India, AI-powered cameras alert villagers when tigers approach their livestock, and in Australia, the technology is being used to control some of their dangerous creatures.
Ripper Corp and academics pioneered what they call the world’s first shark identification algorithms, which were used in drones a few years ago. The latest version of the software is being tested in the Australian state of Queensland, Mexico and the Caribbean to detect sharks and crocodiles.
However, AI is not yet widely used for shark detection. Surf Life Saving New South Wales, which protects dozens of beaches along the state’s coast, including Sydney’s iconic Bondi Beach, uses drones at 50 locations. But a spokesperson told CNN its drones do not currently use AI.
A group at an Australian university working on AI-enhanced shark-spotting tools wrote in 2022 that the technology can struggle in conditions not present in the training data.
SharkEye plans to make its model free and available for researchers to modify or build upon, and to create an AI-powered app that makes it easy for people like lifeguards and drone enthusiasts to review their footage. That could help keep people safe, but also empower people to better understand and protect sharks.
Nathan said it remains to be seen how much retraining will be needed to expand SharkEye to other locations. He hopes that if drone pilots fly at the same speed and altitude, they won’t have too many problems elsewhere in California, where the coastline is similar.
Officials in Honolulu said this month that they are considering launching a drone shark-monitoring program, local media reported. If SharkEye’s technology were to be used in places like Hawaii, where tiger sharks are the biggest concern and the color of the water varies, more retraining might be needed. But Nathan said SharkEye is open to working with other locations to adapt the model.
“Communities want to have that knowledge and awareness so that it’s easier to share the waters with these creatures more safely,” Nathan said. “Sharks are an incredible species that we’re still learning new things about.”
For more CNN news and newsletters, create an account at CNN.com
