Skip to Content

ExaSheds: Advancing Watershed System Science using Machine Learning and Data Intensive Extreme-Scale Simulation

As the world population grows, so do concerns that water availability and water quality will continue to diminish. With leadership class computers, big data, and machine learning combined in learning-assisted, physics-based simulation tools, we have an opportunity to fundamentally change how watershed function is understood and predicted in this collaborative project.
Keywords big data, high performance computing, machine learning (ML), water, watershed
TYPE Project
Principal Investigator (PI)
Carl Steefel
Scott Painter
Lead Institution
Lawrence Berkeley National Laboratory
Other Collaborators
Los Alamos National Laboratory Oak Ridge National Laboratory Pacific Northwest National Laboratory
U.S. Geological Survey University of Texas, Austin
For more information
Other research you might be interested in
Ten year average of 1500-2500m ocean current velocity from an E3SM high resolution ocean - sea ice simulation. Current speed is contoured and velocity vectors are shown in white. (Image credit: Luke van Roekel, Los Alamos National Laboratory) ImPACTS: Improving Projections of AMOC and Collapse Through Advanced Simulations
Drought in the Colorado River in Rocky Mountain National Park. (Image by Charuleka Varadharajan, Lawrence Berkeley National Laboratory) iNAIADS: iNtegration, Artificial Intelligence Analytical Data Services for Rivers and Watersheds
East River photographed facing east in Gothic, CO. (Image credit: Roy Kaltschmidt, Lawrence Berkeley National Laboratory, July 2014) Watershed Function: Biogeochemical dynamics from genomes to watershed scales