Machine-learning-based dynamic-importance sampling for adaptive multiscale simulations

Harsh Bhatia, Timothy S. Carpenter, Helgi I. Ingólfsson, Gautham Dharuman, Piyush Karande, Shusen Liu, Tomas Oppelstrup, Chris Neale, Felice C. Lightstone, Brian Van Essen, James N. Glosli, Peer-Timo Bremer

Abstract: Tackling scientific problems often requires computational models that bridge several spatial and temporal scales. A new simulation framework employing machine learning, which is scalable and can be used on standard laptops as well as supercomputers, promises exhaustive multiscale explorations.