Scientists are collecting massive amounts of images and video to study marine life and assess ocean health. Artificial intelligence (AI) can help researchers analyze this deluge of visual data more efficiently. However, before AI can be used for ocean exploration, machine learning models need to be trained to identify ocean animals.
MBARI is working to address this challenge with a new mobile game called FathomVerse that enlists ocean enthusiasts around the world to help review and label images so AI can accurately recognize ocean animals.
Created with our education and conservation partner, the Monterey Bay Aquarium, and our collaborators in the FathomNet Program, FathomVerse allows anyone with a smartphone or tablet to participate in ocean exploration and discovery. Players interact with real underwater images to improve the artificial intelligence that helps researchers study ocean life. Available for download on the App Store and Google Play, the game combines immersive imagery, compelling gameplay, and cutting-edge science to inspire a new wave of ocean explorers.
FathomVerse aims to solve a bottleneck in analyzing visual data about the ocean.
Cameras on MBARI’s advanced underwater robots have helped our scientists discover remarkable new species, observe unique deep-sea environments, and monitor ocean health. MBARI has amassed an enormous archive of deep-sea video. To analyze the video, researchers in our Video Lab comb through thousands of hours of footage to identify and label animals and objects. This treasure trove of visual data includes more than 10 million observations of animals, behaviors, interactions, geological features, marine debris, and more.
Manually processing the enormous amounts of visual data that researchers have collected and will continue to collect is a daunting task, requiring a significant investment of time and resources. Keeping up with the deluge of data poses a serious challenge to the ocean exploration community. AI can help researchers analyze data more efficiently and scale with the ever-growing amount of visual data, but first must be trained to recognize and identify marine organisms correctly.
MBARI is lending our expertise and resources to support much-needed efforts to develop AI tools that can accelerate analysis of ocean visual data.
Inspired by other community science apps like iNaturalist and eBird, the FathomVerse team wanted to design ways to tap into widespread enthusiasm for ocean animals while at the same time inviting a broader community of people to participate in ocean exploration and discovery. Games can spark creative and unexpected solutions to real-world problems. More than 3 billion people play video games globally, presenting a large audience the FathomVerse team could engage in ocean exploration through their mobile devices. FathomVerse merges science with an innovative gaming experience, aiming to inspire curiosity, foster learning, and contribute to ocean exploration.
To develop FathomVerse, MBARI collaborated with game design experts &ranj Serious Games—a Netherlands-based game development studio focused on positive behavioral change through play.
The team spent 18 months developing the first version of FathomVerse. Working closely with &ranj game developers, the team created a cozy and engaging underwater world where casual gamers can explore, play, and learn. FathomVerse is designed to be easy to pick up, so gamers can enjoy it with their morning coffee or while waiting for the bus.
“By tapping into our collective curiosity, FathomVerse seeks to transform ocean exploration by engaging a community of ocean enthusiasts to work alongside researchers.”
—Principal Engineer Kakani Katija
After a successful beta launch in 2023 that drew nearly 1,400 players from 65 countries, the FathomVerse app launched publicly in the App Store and Google Play in global markets on May 1, 2024.
In the FathomVerse game, players can:
Launch mini-games to find and label ocean animals using real imagery collected by researchers.
Learn how to identify nearly 50 groups of ocean animals.
Save favorite images and curate a personal gallery.
Unlock awards to expand their knowledge of ocean animals and dive deeper into how gameplay improves artificial intelligence.
Listen to Ocean Radio channels and cycle through different soundtracks inspired by the ocean soundscape.
Be among the first to view new imagery collected by researchers exploring the ocean.
As of January 2025, 14,000 people in 142 countries have downloaded FathomVerse. The game includes more than 93,000 images contributed by MBARI, FathomNet, NOAA Office of Ocean Exploration and Research, Ocean Exploration Trust’s Nautilus Live program, Ocean Observatories Initiative, Ocean Networks Canada, and Schmidt Ocean Institute. Gamers have generated more than 7 million annotations, reaching community consensus on more than 44,000 images that were previously unknown and can now be used to train AI to identify marine life.
The team has begun work on the next version of the game, with plans to release version 2.0 in spring 2025. The updated version will introduce new mini-games, expanded rewards, achievement-based badges, and a streamlined user interface.
Leveraging the infrastructure behind FathomVerse, the team is also developing FathomVerse ID, a new app that will allow visitors to public aquariums to identify the animals they see on display in real time.
FathomVerse is one of three software solutions developed as part of the FathomNet Program, an innovative, collaborative project led by MBARI that seeks to make AI and ocean research more accessible and impactful.
In addition to FathomVerse, FathomNet has released FathomNet Database, containing expertly-labeled images and machine learning models that can be used to identify ocean animals. The FathomNet Database includes 100,000 expertly-labeled images provided by MBARI’s Video Lab.
In September 2024, FathomNet launched the Portal, an online, collaborative tool for end-to-end AI-assisted processing of ocean imagery. The Portal interfaces with both the FathomNet Database and FathomVerse to allow users to upload video, run machine learning algorithms to automatically classify organisms, and search for observations recorded by others in the ocean exploration community.
Funding for FathomVerse came from the National Science Foundation’s Convergence Accelerator, the David and Lucile Packard Foundation, and the Schmidt Marine Technology Partners, a program of the Schmidt Family Foundation.
