Autonomous MultiScale Library
Harsh Bhatia, Tapasya Patki, Stephanie Brink, Loïc Pottier, Thomas Stitt, Konstantinos Parasyris, Daniel J. Milroy, Daniel Laney, Robert Blake, Jae-Seung Yeom, Peer‐Timo Bremer, Charles M. Doutriaux · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · 2023
AMSLib provides infrastructure to tightly couple multi-scale physics simulation code with ML surrogate model inference. It provides a wholistic runtime execution paradigm to supports uncertainty quantification, surrogate model inference, persistent data storing throughout the execution of a simulation.