How A.I. is helping to protect the endangered whale sharks of the Galapagos

This post was originally published on this site

https://content.fortune.com/wp-content/uploads/2022/11/GettyImages-110050253.jpg

Within the Galápagos Marine Reserve, one of the world’s largest and most biologically diverse marine protected areas, more than 2,900 species survive off the interconnectedness of healthy ecosystems. Globally, humans also live off the many benefits of a thriving ocean.

Technology underwater is increasing to safeguard the environments needed for the ocean to release the earth’s oxygen, sequester carbon, provide sustenance, and so much more. And data is essential to track the development of the ecosystems as threats, such as illegal fishing and climate change, fluctuate. Collecting and analyzing ocean data at a large scale—including that of rare and endangered species—gives researchers useful insight to help conserve the vital diversity that makes up such a valued part of the earth.

“Wildlife research has, until the past few years, been a world of ‘small data,’” says Jason Holmberg, executive director at Wildbook Image Analysis (WBIA), a tech company that builds open software and A.I. solutions for conservationists. “Observations of rare or endangered species, whether via collars, camera traps, DNA samples, or photos, have been expensive to obtain and often required research teams to go directly into the field for short durations to obtain even small volumes of data.”

But with the use of A.I., the data and capabilities are expanding.

Observing whale sharks through passive tracking

In 2016, the International Union for Conservation of Nature (IUCN) downgraded whale sharks from vulnerable to endangered because of the many anthropogenic impacts they face, including industrial fisheries (both targeted and bycatch), vessel strikes, marine pollution, and climate change.

Whale sharks, which can grow up to 60 feet long, provide significant ecological importance, according to Sofia Green, marine biologist and research scientist at the Galápagos Whale Shark Project, who studies the behavior, ecology, and migration patterns of the species. As predators on the top of the food chain, whale sharks feed off the weak and sick. By doing so, they keep the food chain in order. They also serve as carbon sequesters and nutrient-dense fertilizers by bringing nutrients (via defecation) to unhealthy ecosystems.

“If you protect sharks, you protect the ocean. And if you protect the ocean, you have a healthy planet,” she explains, while emphasizing the incredible importance of preserving the existence of all sharks. “And you cannot save a species if you don’t understand how they behave.” 

In the northernmost point of the Galápagos, near the island of Darwin, Green and her team tag, video, photograph, do ultrasounds and blood draws, and take tissue samples to track the health and whereabouts of whale sharks that migrate through the Galápagos reserve. Observations like this are extremely valuable. But when made from limited studies, such as these, they may provide information at a small scale.

This is where technology like “passive tracking”—via photo identification and A.I.—broadens the data set. Whale sharks have unique spots, like human thumbprints, that can be referenced as identification. The Galápagos Whale Shark Project uses sharkbook.ai, a system run by WBIA that taps into A.I. to aggregate images of individual whale sharks uploaded by the likes of Green as well as images and videos posted on social media platforms around the world.

“Consider how whale sharks, the world’s biggest fish, were once rarely observed and even less frequently photographed,” Holmberg says. With the advent of cell phones, numerous sightings show up on YouTube and Instagram. “With this new wealth of data emerging from more cost-effective technology and public observations of wildlife, there is now an overwhelming amount of wildlife data available.”

A.I. helps sort and curate images and videos. Then sharkbook.ai classifies each whale shark based on the spot patterns and uses the photos for “capture/recapture.” For Green, this information shows where sharks appear elsewhere on the planet, when the individual returns to Galápagos, or if one has ended up on land or in an area it typically wouldn’t go (usually a result of being illegally fished).

“Modified growth algorithms like this are used by NASA to track stars,” Green explains. “It’s now being used to track the underwater constellations found on the bodies of these whale sharks.” Before this technology, researchers would obtain identification only from sharks seen on their expeditions. Through new, more expansive data collection, they now track almost 700 identified whale sharks that have migrated through the Galápagos.

When a photo is inputted for the first time, it goes into a newly created profile page. There, a summary of its sightings will build over time based on contributions. “All of this is aimed at a single goal,” Holmberg says: “Identifying the best ways to prevent extinction.”

A.I. to resolve the Galápagos “longline dilemma”

A threat to whale sharks and other species within the Galápagos Marine Reserve is the illegal longline fishing of tuna, which was banned in 2000 as a precautionary measure to prevent unintentional bycatch of endangered, threatened, and protected (ETP) species. However, it is still a common practice. Over the past two decades, people in the Galápagos have debated longline as the biggest threat to biodiversity. As a result, management authorities and environmental organizations hope to maintain the ban. On the other hand, local fishers argue that longline fishing should be authorized because it is the most cost-efficient way to catch tuna.

According to a study done by marine biologist Mauricio Castrejón, Ph.D., as the local population (approximately 30,000 people spread across three habitable islands) grows, so does tuna consumption. Between 1997 and 2017, yellowfin tuna landings increased from 41.1 tons to 196.8 tons per year. Castrejón, who has led small-scale fisheries research and development projects in the Galápagos and the Eastern Tropical Pacific region (Costa Rica, Panama, Colombia, and Ecuador) for more than 18 years, dubs this fishing debate the “longline dilemma.”

This technique of fishing trails a long line with numerous hooks behind a boat. If not properly monitored, it can result in the unintended bycatch of ETP species. Many believe the rate of bycatch isn’t as high as reported or believed. And as of now, Galápagos doesn’t have proper data collection to track and survey the true rate of bycatch. Through science, technology, and innovation, Castrejón is hoping to build better monitoring and practices, and end the debate.

One such pathway is installing video cameras created by Shellcatch onto fishing vessels, an initiative that began in 2021 after being chosen by the Charles Darwin Foundation and WildAid. The cameras capture high-resolution information of fishing activities (technique, bycatch rate, and more) to hold fishers accountable for how and what they are catching, which creates market incentives, like selling their catch at a premium.

Shellcatch uses an A.I. algorithm through its electronic monitoring sensor to quickly detect bycatch of nontarget species. “A.I. is critical in validating sustainable fishing practices and connecting supply and demand in a cost-effective way,” says Alfredo Sfeir, founder and president of Shellcatch. He also cofounded Frescapesca, a seafood marketplace that also uses A.I. With Shellcatch, fishers input data into their logbooks (per usual practice), and scientists/A.I. use the video and accumulated data to validate the information. This proves to consumers that their product is fresh, legal, sustainable, and has a low incidental catch of protected species. Hence, earning a premium market price.

Sfeir believes these technologies, including Frescapesca, will be a game changer. “With A.I., the online seafood market platform can convert a growing number of fishing events into data that optimizes logistics and creates higher margin transactions,” he says. “The end result is a growing number of fishermen and women supplying seafood and buyers ready to purchase when vessels arrive with product anywhere along the shoreline.”

Furthermore, this new data can be integrated into science-based evidence and advice to better validate the best technique, risk-averse gear, and solutions to protect other species and keep tuna fishing sustainable for the people of Galápagos and beyond.