
FathomNet Solutions
PHOTO: SCHMIDT OCEAN INSTITUTE
FathomNet enables accurate, rapid processing of underwater visual data through a globally integrated network that can accelerate ocean discovery, inform all sectors of the Blue Economy, and lead to effective marine stewardship. To achieve this, the program is creating an ecosystem of interconnected tools and services that connect machine learning data analysis resources with a spectrum of users–from experts to enthusiasts–to analyze ocean imagery.
FathomNet Portal is an online, collaborative tool for end-to-end AI-assisted processing of ocean imagery.

Within the FathomNet Portal, users can upload and view video, run machine learning algorithms to automatically identify and classify organisms (or do it manually themselves), and search for observations recorded by others. The web-based tool interfaces with both the FathomNet Database and FathomVerse.
By automating the analysis of visual data, the Portal helps users train their own machine learning models by providing intuitive interfaces for annotation, streamlined access to the necessary computational power, and accessible tools to analyze the output.
The Portal is available now and seeking early adopters. Submit an expression of interest form to work with us.
PORTAL RESOURCES
FathomNet Database is an open-source database for machine learning models and expertly labeled ocean imagery to help understand our ocean and its inhabitants.

Recent advances in machine learning enable fast, sophisticated analysis of visual data, but the use of artificial intelligence in ocean research has been limited by the lack of annotated images needed to train models to recognize and catalog concepts and marine life.
FathomNet Database addresses this need by providing tools and services for data manipulation and aggregating images from multiple sources to create a publicly available, expertly curated ocean image database.
The constantly expanding collection of imagery is available to a spectrum of users from marine biologists and data scientists to graduate students and ocean enthusiasts. Users can access years of image data contributed by organizations and collaborators around the globe.
The Database is integrated with the FathomNet Portal and through its Application Programming Interface (API) can be linked to a number of external services. Its images are used in a new mobile game, FathomVerse.
DATABASE RESOURCES
Access open-source machine learning models.

FathomNet offers a collection of pretrained models on HuggingFace that are maintained by our team. We encourage submitting models that are trained on the FathomNet Database to help the community share and build on each other's work.
FathomNet Models enables researchers, developers, and enthusiasts to efficiently access and deploy a variety of sophisticated algorithms. By harnessing the extensive data and models offered by FathomNet, you can significantly elevate your projects and explore groundbreaking applications in machine learning.
FathomVerse inspires a new wave of ocean explorers and helps scientists discover all life in the ocean

The ocean covers more than 70% of our planet, yet most of the life within it remains undiscovered and undescribed. FathomVerse is changing that, one dive at a time.
FathomVerse is a free app that invites everyone with a smartphone or tablet to take part in real ocean exploration and discovery. Developed by the Monterey Bay Aquarium Research Institute (MBARI) and partners through the FathomNet Program, FathomVerse connects a global community of ocean enthusiasts—called FathomNauts—with cutting-edge science.
Through interactive mini-games, FathomNauts identify animals in real underwater photos and contribute to a growing library of labeled images that helps scientists catalog and understand marine life.
Whether you're a lifelong ocean lover or simply curious about what lives in the depths, FathomVerse makes it easy to contribute to meaningful scientific research. Dive into FathomVerse to help scientists discover all life in the ocean.




























