ascr-discovery.science.doe.govASCR Discovery - ASCR DiscoveryASCR Discovery | Understanding Science through Computing

Main menu Skip to primary content Skip to secondary content SC Home Organization Jobs Contact DOE Home » #access ---------------------------------------------------------------------------------------------------------------------------------------- -- About ASCR Discovery» X About ASCR Discovery ASCR Discovery carries original articles about computational science from the research portfolio of the Office of Advanced Scientific Computing Research in the Department of Energy Office of Science, plus links to DOE science highlights and other computational science-related content. ASCR-supported research includes projects at DOE national laboratories, at many public and private universities and collaborations with other agencies and institutions. We hope you find ASCR Discovery enlightening, and we encourage your comments. Please direct queries to ascreditor@krellinst.org . ASCR Discovery Understanding Science through Computing ASCR Discovery Search Subscribe April 2020 | Geoscience Sizing up the beast With help from DOE supercomputers, a USC-led team expands models of the fault system beneath its feet, aiming to predict its outbursts. Climate, Genomics April 2020 Soil sifters Algorithms and supercomputers help tease out how soil microbes affect global climate. Aeronautics, Engineering January 2020 Beyond the tunnel Stanford-led team turns to Argonne’s Mira to fine-tune a computational route around aircraft wind-tunnel testing. Fusion Energy November 2019 Tracking tungsten Supercomputer simulations provide a snapshot of how plasma reacts with – and can damage – components in large fusion reactors. View Categories» View Archives » Science Highlights May 2019 AI and deep learning for fusion Princeton researchers apply deep learning to a new code, Fusion Recurrent Neural Network (FRNN), to forecast events that disrupt fusion reactions. Bagel-shaped fusion reactors called tokamaks produce energy of the kind that powers the sun. But massive disruptions can halt fusion reactions and damage the reactors. Princeton University researchers’ Fusion Recurrent Neural Network (FRNN) code harnesses an artificial-intelligence tool called deep-learning to predict disruptive events. Researchers can also use the code to make predictions that could open avenues for active reactor control and optimization. The method, reported in Nature , holds promise for enabling steady-state operation of tokamaks. View full highlight » View Science Highlights archives » DOE Home SC Home Contact Us Subscribe to ASCR Discovery Fields marked with an * are required Enter your name and e-mail address below to receive email notifications when ASCR Discovery posts news on computational science research from the Department of Energy Office of Science. We never share our mailing lists. Name* Email* X...