Surfing alongside sharks: How SharkEye is making California beaches safer
On summer mornings, children flock to Padaro Beach in California to learn to surf in the gentle whitewater waves. However, a few years ago, the beach also became a popular hangout for juvenile great white sharks, prompting the launch of SharkEye, an initiative by the University of California Santa Barbara’s Benioff Ocean Science Laboratory (BOSL).
Drone surveillance and real-time alerts
SharkEye uses drones to monitor the waters for sharks. If a shark is spotted, the program sends a text alert to around 80 people, including local lifeguards, surf shop owners, and parents of children taking lessons. “Automating shark detection … can (also) be really helpful for a lot of communities outside of ours here in California,” said Neil Nathan, a project scientist with BOSL.
AI and human cooperation
While drones are already used from New York to Sydney to monitor beach safety, SharkEye aims to improve detection accuracy with artificial intelligence (AI). Current studies suggest human-monitored drones only detect sharks about 60% of the time. SharkEye’s technology, which feeds video footage into a machine learning model, has shown promising results in early tests, often spotting sharks that humans miss.
The rise in drone popularity and social media has amplified the visibility of sharks, but shark attacks remain rare. In 2023, there were 69 unprovoked shark bites globally, with 10 fatalities, according to the Florida Museum of Natural History’s International Shark Attack File. Although Padaro Beach has not recorded any fatal attacks, community concerns arose when juvenile great whites began frequenting the area.
SharkEye has been conducting drone flights for about five years and has observed up to 15 juvenile great whites in a single day. This summer, the project began comparing human and AI shark detection capabilities, with the AI often matching or exceeding human accuracy.
Currently, alerts are based on human analysis, but Nathan hopes to integrate AI into this process by the end of the season or early next summer. Eventually, the process could become fully automated, enhancing both speed and accuracy. SharkEye plans to make its model free for researchers and create an AI-powered app for lifeguards and drone hobbyists, which could improve both human safety and shark conservation.
Expanding AI applications
AI technologies are increasingly used to mitigate human-wildlife conflicts. In India, AI-enabled cameras alert villagers to approaching tigers, while in Australia, technology manages dangerous wildlife. Despite these advances, AI is not yet widely used for shark detection. SharkEye’s adaptable model could be a game-changer, allowing communities worldwide to coexist more safely with sharks.
“Communities want to have that knowledge and that awareness so it’s easier to more safely share the water with these creatures,” said Nathan. “Sharks are an incredible species that we still are always learning new things about.”
