Artificial Intelligence and Digital Twins for Earth Systems

Artificial Intelligence/Machine Learning (AI/ML) technologies have grown exponentially over the past decade, and there is increasing interest to integrate these technologies into energy and Earth systems modeling. Digital twins (DTs) are computational models that are dynamically updated using data from their physical twins to persistently represent the behavior of unique physical systems or processes, and serve as a basis for model predictive decision making. They present unique opportunities for integrating emerging AI/ML technologies. This workshop will bring together researchers working to integrate AI/ML methods within Earth systems modeling towards creating predictive DTs. We expect this workshop to span a wide range of topics, including but not limited to:

• Data-driven subgrid-scale parameterizations for subgrid-scale physics

• Development of efficient data driven surrogates to reduce simulation times

• Development of coupling methodologies that rigorously bring together conventional and data driven models

• Data-driven discovery of unknown physics

• Mathematical, statistical, and computational foundations underlying DTs

• Data assimilation and statistical inverse problems

• Optimal control and decision making under uncertainty

• Optimal experimental design

We welcome contributions in subject areas relevant to the USACM Energy & Earth Systems (E&ES) Technical Thrust Area (TTA), which include:

• Climate and Earth systems modeling

• Climate couplings

• Geomechanics, geodynamics, and seismology

• Wind, solar, and nuclear energy

• Carbon sequestration, capture, and storage

• Oil & gas recovery

Organizing Committee

Irina Tezaur, Sandia National Laboratories

Omar Ghattas, The University of Texas at Austin

Steve WaiChing Sun, Columbia University

Yuri Bazilevs, Brown University

Clint Dawson, The University of Texas at Austin

Local Organizing Committee

Hannah Lu, The University of Texas at Austin

Patrick Heimbach, The University of Texas at Austin

If you have any questions, please contact:

Irina Tezaur, ikalash@sandia.gov