|
"We propose to develop an open-source agentic science assistant that helps students and researchers explore, visualize, and interpret large, heterogeneous datasets focused on the ocean. Approximately half of the data the National Oceanic and Atmospheric Administration (NOAA) has collected (32 petabytes) is hosted by Amazon Web Services [1]. The Rutgers University Center for Ocean Observing Leadership (RUCOOL) and other geoscience researchers (there are approximately 300,000 in the United States) are looking for more efficient methods for discovering, accessing and utilizing the ever expanding ocean datasets. The system will deploy cooperating AI agents that retrieve, clean, and summarize real-time and historical ocean data including remote sensing and in situ data collections. The proposed AI agent will deliver natural-language insights and data visualizations to potential users. A large-language-model-driven “science copilot” will interact conversationally with users, grounded in verified ocean data, enabling rapid hypothesis testing and discovery. This work directly aligns with the AWS Agentic AI call by advancing AI-enhanced productivity tools, human–AI collaboration, and responsible open-source agent frameworks.
[1] F. Konkel, ""Cloud and AI are ‘Fundamentally Changing’ Ability to Forecast Weather, NOAA Chief Says,"" ed, 2024."
|
Sign in
to view more information about this project.
