Uploaded September 2026 | Updated September 2026, 1 week ago
Argonne National Laboratory is a multidisciplinary science and engineering research center where scientists and engineers pioneer breakthroughs that address some of the world’s most pressing challenges. In this video, geoscientist Eugene Yan discusses an Argonne-led project under DOE’s Genesis Mission that uses artificial intelligence to improve predictions of water availability and flood risk across the United States.
Water shortages and flooding pose significant risks to energy production, infrastructure and communities across the country. Yet predicting these risks accurately is difficult: large-scale hydrologic models can be too computationally demanding to capture local detail across an entire continent, while also oversimplifying interactions between surface water and groundwater. Many models also struggle to account for human activities such as groundwater pumping, making it harder to anticipate droughts, floods and changing water demands.
To address these challenges, Argonne is leading a team that includes Lawrence Berkeley National Laboratory, Princeton University, the University of Arizona, the University of Illinois Urbana-Champaign, Georgia Institute of Technology and Cognition AI to develop a new AI foundation model. The model will learn from physics-based simulations at multiple scales, combining continental, regional and local information to improve predictions of groundwater levels, soil moisture, streamflow and flood hazards. The system is also designed to incorporate real-time observations and estimate forecast uncertainty without requiring computationally expensive retraining.
The team will initially focus on water availability and flood risks in the Midwest, with the goal of scaling the approach into a high-resolution, AI-driven water forecasting system for the continental United States. The technology could give communities, energy providers and other decision-makers better tools to anticipate water shortages, manage flood risks and strengthen the resilience of energy systems. Learn more about how Argonne is advancing this work under DOE’s Genesis Mission.
Find out more about Argonne’s role supporting the DOE’s Genesis Mission ►► anl.gov/genesis-mission/projects/multi-fidelity-ai-foundation-model-for-coupled-surface-groundwater-predictions-of-water-availability-and-flood-hazards-across-conus
Still haven't subscribed to Argonne National Laboratory on YouTube? ►► bit.ly/2Vyzwvm
Join us on Facebook ► bit.ly/ArgonneFacebook
Follow us on X ► bit.ly/ArgonneTwitter
We’re on Instagram ► bit.ly/ArgonneInstagram
Connect with us on LinkedIn ► bit.ly/ArgonneLinkedIn
ABOUT ARGONNE
Argonne National Laboratory seeks solutions to pressing national problems in science and technology by conducting leading-edge basic and applied research in virtually every scientific discipline. Argonne is managed by UChicago Argonne, LLC for the U.S. Department of Energy’s Office of Science.
ABOUT THE DEPARTMENT OF ENERGY OFFICE OF SCIENCE
The U.S. Department of Energy’s Office of Science is the single largest supporter of basic research in the physical sciences in the United States and is working to address some of the most pressing challenges of our time. For more information, visit the Office of Science website.
Argonne National Laboratory is a multidisciplinary science and engineering research center where scientists and engineers pioneer breakthroughs that address some of the world’s most pressing challenges. In this video, geoscientist Eugene Yan discusses an Argonne-led project under DOE’s Genesis Mission that uses artificial intelligence to improve predictions of water availability and flood risk across the United States.
Water shortages and flooding pose significant risks to energy production, infrastructure and communities across the country. Yet predicting these risks accurately is difficult: large-scale hydrologic models can be too computationally demanding to capture local detail across an entire continent, while also oversimplifying interactions between surface water and groundwater. Many models also struggle to account for human activities such as groundwater pumping, making it harder to anticipate droughts, floods and changing water demands.
To address these challenges, Argonne is leading a team that includes Lawrence Berkeley National Laboratory, Princeton University, the University of Arizona, the University of Illinois Urbana-Champaign, Georgia Institute of Technology and Cognition AI to develop a new AI foundation model. The model will learn from physics-based simulations at multiple scales, combining continental, regional and local information to improve predictions of groundwater levels, soil moisture, streamflow and flood hazards. The system is also designed to incorporate real-time observations and estimate forecast uncertainty without requiring computationally expensive retraining.
The team will initially focus on water availability and flood risks in the Midwest, with the goal of scaling the approach into a high-resolution, AI-driven water forecasting system for the continental United States. The technology could give communities, energy providers and other decision-makers better tools to anticipate water shortages, manage flood risks and strengthen the resilience of energy systems. Learn more about how Argonne is advancing this work under DOE’s Genesis Mission.
Find out more about Argonne’s role supporting the DOE’s Genesis Mission ►► anl.gov/genesis-mission/projects/multi-fidelity-ai-foundation-model-for-coupled-surface-groundwater-predictions-of-water-availability-and-flood-hazards-across-conus
Still haven't subscribed to Argonne National Laboratory on YouTube? ►► bit.ly/2Vyzwvm
Join us on Facebook ► bit.ly/ArgonneFacebook
Follow us on X ► bit.ly/ArgonneTwitter
We’re on Instagram ► bit.ly/ArgonneInstagram
Connect with us on LinkedIn ► bit.ly/ArgonneLinkedIn
ABOUT ARGONNE
Argonne National Laboratory seeks solutions to pressing national problems in science and technology by conducting leading-edge basic and applied research in virtually every scientific discipline. Argonne is managed by UChicago Argonne, LLC for the U.S. Department of Energy’s Office of Science.
ABOUT THE DEPARTMENT OF ENERGY OFFICE OF SCIENCE
The U.S. Department of Energy’s Office of Science is the single largest supporter of basic research in the physical sciences in the United States and is working to address some of the most pressing challenges of our time. For more information, visit the Office of Science website.
