We are employing machine learning techniques to develop more accurate predictive models that are trained jointly on both simulation and experimental data, comparing more forms of data than is typical, such as images, vector-valued data, and scalars. This research supports the national energy and security missions that rely on predictive models.
Ahn, D. H., et al. 2018. "Flux: Overcoming Scheduling Challenges for Exascale Workflows." WORKS, Dallas, TX, Nov. 2018. LLNL-CONF-756663.
Spears, B. 2018. "Deep Learning: A Guide for Practitioners in the Physical Sciences." Phys. Plasmas. 25. doi: 10.1063/1.5020791. LLNL-JRNL-743970.
Lawrence Livermore National Laboratory • 7000 East Avenue • Livermore, CA 94550
Operated by Lawrence Livermore National Security, LLC, for the Department of Energy's National Nuclear Security Administration.