AI and Shark Photos Power Global Ocean Conservation

Bridging the Critical Data Gap in Shark Conservation

With one-third of all shark species currently facing the threat of extinction, scientists are in a race against time. A significant hurdle in this effort is the lack of fundamental data regarding their populations, habitats, and trends. To address this, a collaborative team of researchers from Virginia Tech, Stanford University, and other institutions is pioneering a groundbreaking solution called sharkPulse.

This project aims to build the world's most extensive open database of shark sightings, not by waiting for submissions, but by actively seeking them out. As lead author Francesco Ferretti notes, “We can’t protect what we don’t know.”

From Online Photos to Scientific Insight

SharkPulse represents a paradigm shift in citizen science. Instead of relying on voluntary contributions, the platform leverages artificial intelligence to automatically scan online sources for photos of sharks. The AI extracts crucial metadata like location, timestamps, and even preliminary species identification. This automated approach transforms everyday digital activities into a powerful stream of conservation data.

“This shifts citizen science from voluntary submissions to intelligent autonomous discovery,” explains Ferretti, an assistant professor in the Department of Fish and Wildlife Conservation. The collected images are then validated by both the public and experts before being added to a searchable database, allowing for unprecedented mapping and tracking of shark populations.

Jeremy Jenrette, a Ph.D. candidate on the project, adds, “With cameras in nearly everyone’s hands, our encounters with the ocean are being recorded more than ever. SharkPulse taps into this unprecedented global stream of images and videos, using AI and data science to passively monitor shark populations at a scale never before possible.”

A New Wave of Conservation Research

This initiative builds upon a strong foundation of marine conservation research at Virginia Tech. Related projects highlight a multi-faceted approach to protecting marine life:

• White Shark Chase: This project used eDNA and baited cameras to track critically endangered white sharks in the Mediterranean, supporting the launch of a dedicated monitoring program.
• Mako Shark Tagging: Researchers tagged the first juvenile shortfin mako shark in the Mediterranean, revealing it traveled over 750 miles in 54 days and highlighting the need for broad conservation planning.
• MegaMove Contribution: Virginia Tech was part of a global effort to map the habitats of over 100 large marine species, discovering that 60 percent of their critical habitats are outside protected areas.

Tracking Global Trends and Identifying Hotspots

The impact of sharkPulse is already significant. To date, the platform has validated over 91,000 records covering 285 different shark species—which is nearly 53 percent of all known species. This wealth of data has helped identify new shark hotspots, such as previously unknown white shark congregations in the Mediterranean. Furthermore, the platform's ability to generate dynamic distribution maps makes it a vital tool for supporting assessments by The International Union for Conservation of Nature’s Red List of Threatened Species. The full scope of the research was detailed in the journal Fish and Fisheries.

Local Impact Across the Mid-Atlantic

The platform's utility extends from global patterns to local ecosystems. For instance, while bull sharks are known to visit Virginia's Chesapeake Bay in the summer, little is understood about their movements. When a fisherman caught and photographed a bull shark in 2018, it became a valuable data point.

“sharkPulse is built around this kind of records. The platform gives us a way to collect and organize fugitive local information and transform them into scientific knowledge,” Ferretti says. “It strengthens our understanding of marine ecosystems close to home — not just globally.”

The Waters Ahead

The team has ambitious plans for the future. They aim to scale sharkPulse by incorporating multilingual data mining and forging international partnerships to cover more geographic areas. A key goal is to make the data more accessible and actionable for policymakers, fishery managers, and conservation organizations.

“This is about creating an always-on pulse monitor for the ocean,” Ferretti states. “The more we see, the more we can do to protect.”

The technology's flexible framework also serves as a blueprint that could be adapted to monitor other species, from sea turtles to bats, creating a new frontier in tech-driven wildlife conservation.