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.
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 NEWS
FathomNet
FathomNet 1.0: Taxonomic Discussions, Annotation Verification, and Community Collaboration
Nature Scientific Reports
FathomNet: A global image database for enabling artificial intelligence in the ocean
UIST '24: Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology
FathomGPT: A Natural Language Interface for Interactively Exploring Ocean Science Data
DATABASE RESOURCES
Access open-source machine learning models.
.png)
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 empowers anyone with a smartphone or tablet to take part in ocean exploration and discovery.
.png)
Welcome to FathomVerse. Now available for download on the App Store and Google Play, FathomVerse allows players to interact with real underwater images to improve the artificial intelligence that helps researchers study ocean life. The game combines immersive imagery, compelling gameplay, and cutting-edge science to inspire a new wave of ocean explorers.
Scientists are collecting massive amounts of images and video to study marine life and assess ocean health. AI can help researchers analyze this deluge of visual data more efficiently. Before AI can be used for ocean exploration, machine learning models need to be trained to identify ocean animals. FathomVerse, a new mobile game, seeks to address this challenge by engaging ocean enthusiasts around the world to help review and label images so AI can correctly recognize ocean animals.
“With an enormous challenge comes an enormous opportunity: How do we scale our capacity for analyzing valuable data about the ocean while realizing a new and inclusive vision for ocean exploration and discovery? By combining expertise in ocean science, human-AI interactions, and gaming, FathomVerse offers a solution,” said MBARI Principal Engineer Kakani Katija, who led the development of FathomVerse.
To develop FathomVerse, Katija and MBARI software engineers collaborated with game design experts &ranj Serious Games—a Netherlands-based game development studio focused on positive behavioral change through play—and Internet of Elephants—a nature tech enterprise based in Kenya focused on rekindling relationships between people and wildlife.
FATHOMVERSE NEWS
NOAA-NCEI
NCEI Collaborates with FathomVerse to Celebrate Citizen Science Month
FathomVerse
FathomVerse Levels Up Ocean Exploration
MBARI 2024 Annual Report
Inspiring a new wave of ocean explorers
FATHOMVERSE RESOURCES
