Sharks gather on California beach. Artificial intelligence tries to protect swimmers | CNN


CNN




On summer mornings, local kids like to gather at Padaro Beach in California to learn to surf on the calm waves. A few years ago, the beach also became a favorite spot for young great white sharks.



This led to the launch of SharkEye, an initiative of the Benioff Ocean Science Laboratory (BOSL) at the University of California, Santa Barbara, which uses drones to monitor what’s happening beneath the waves.




If a shark is spotted, SharkEye sends a text message to the 80 or so people who have signed up to receive alerts, including local lifeguards, surf shop owners and parents of children taking lessons.



In recent years, other initiatives have emerged From New York to Sydney, authorities and lifeguards are using drones to keep beachgoers safe, monitoring video streams from a camera. It requires the pilot to stay focused on a screen, battling choppy water and sun glare, to differentiate sharks from paddleboarders, seals and swaying strands of kelp. One study found that drones monitored by humans detect sharks only about 60 percent of the time.




SharkEye, a research program and community safety tool, uses the videos it collects to analyze shark behavior. It also feeds a computer vision machine learning model (a type of artificial intelligence (AI) technology that allows computers to glean information from images and videos) to train it to detect great white sharks near Padaro Beach, near the town of Santa Barbara.



“Automating shark detection… can (also) “This could really be useful for many communities outside of ours here in California,” BOSL project scientist Neil Nathan, who graduated from Stanford University with a master’s degree in environmental studies a few years ago, told CNN.




The growing popularity of drones and the proliferation of social media can make it seem like sharks are everywhere. Warming oceans are pushing sharks into new habitats, and young white sharks, which can grow to 8 to 10 feet long, like to hang out close to shore, making them more visible to swimmers.



Yet shark attacks are rare. In 2023, 69 people worldwide suffered unprovoked bites, which is in line with the average of 63 incidents per year between 2018 and 2022. Only 10 of those died, according to the Florida Museum of Natural History’s International Shark Attack File.



Although no fatal attacks have been recorded at Padaro Beach, some community members became concerned when sharks began prowling there.



That’s why SharkEye has been regularly conducting drone flights to monitor the coastline for about five years, once spotting 15 young great white sharks in a single day.



Early tests indicate the AI ​​technology is already working “incredibly well,” detecting most sharks a human could detect, and sometimes sharks a human missed, perhaps because they were swimming too deep to be easily spotted, Nathan said.



This summer, the project began field testing its SharkEye has developed a technology that pits drone pilots against AI. Its pilot surveys the area and counts the number of sharks it spots. SharkEye’s model then analyzes the video to see how many sharks it can find.


SharkEye drone pilot Samantha Mladjov in Padaro Beach, California.


Today, community alerts rely on human analysis. If all goes well, those reports could be AI-assisted — with manual oversight and checks — by the end of the season or early next summer, Nathan said. In the future, the process could even be fully automated, making it faster and potentially more accurate.


AI and wildlife



AI technologies are Tigers are being used in a variety 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 manage some of these dangerous creatures.



Ripper Corp and academics have developed what they say are the world’s first shark-identification algorithms, which were implemented on drones a few years ago. The latest version of the software is currently 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 in 50 locations. But a spokesperson told CNN that their drones do not currently use AI.



A group at an Australian university that has been working on AI-enhanced shark detection tools wrote in 2022 that the technology can struggle when it encounters conditions that weren’t present in the training data.



SharkEye plans to make its model free and accessible for researchers to modify or expand upon, and to create an AI-powered app that allows rescuers and drone enthusiasts to easily view their images. This could help keep people safe, but also allow humans to better understand and protect sharks.



Nathan said it remains to be seen how much SharkEye will need to refine to expand 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.



According to local media reports, Honolulu officials said this month they were considering launching a drone shark monitoring program. If SharkEye’s technology were to be used in places like Hawaii, where tiger sharks are the biggest concern and water colors vary, more training might be needed. But Nathan said SharkEye is open to working with other localities to help scale the model.



“Communities want to have that knowledge and awareness so it’s easier to share the water with these creatures safely,” Nathan said. “Sharks are an incredible species that we’re always learning new things about.”


Post a Comment

0 Comments