CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 10898 > Article
Presentation
4 March 2019 Learning-based predictive models: a new approach to integrating large-scale simulations and experiments (Conference Presentation)
Brian K. Spears
Author Affiliations +
Proceedings Volume 10898, High Power Lasers for Fusion Research V; 108980H (2019) https://doi.org/10.1117/12.2507513
Event: SPIE LASE, 2019, San Francisco, California, United States
Abstract
We will describe a large research effort at Lawrence Livermore National Laboratory (LLNL) aimed at using recent advances in deep learning, computational workflows, and computer architectures to develop an improved predictive model – the learned predictive model. Our goal is to first train these new models, typically cyclic generative adversarial networks, on simulation data to capture the theory implemented in advanced simulation codes. Later, we improve, or elevate, the trained models by incorporating experimental data. The training and elevation process both improves our predictive accuracy and provides a quantitative measure of uncertainty in such predictions. We will present work using inertial confinement fusion research and experiments at the National Ignition Facility (NIF) as a testbed for development. We will describe advances in machine learning architectures and methods necessary to handle the challenges of ICF science, including rich, multimodal data (images, scalars, time series) and strong nonlinearities. We will also cover state-of-the-art tools that we developed to manage our computational workflow. The tools manage a wide range of tasks, including developing enormous (PB-class) simulated training data sets, driving the training of learned models on simulation data, and elevating learned models through exposure to experiment. We will end by drawing ties to a broad range of scientific applications.
Conference Presentation
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Brian K. Spears "Learning-based predictive models: a new approach to integrating large-scale simulations and experiments (Conference Presentation)", Proc. SPIE 10898, High Power Lasers for Fusion Research V, 108980H (4 March 2019); https://doi.org/10.1117/12.2507513
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
INSTITUTIONAL
Select your institution to access the SPIE Digital Library.
SELECT YOUR INSTITUTION
PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
PERSONAL SIGN IN
No SPIE Account? Create one
PURCHASE THIS CONTENT
SUBSCRIBE TO DIGITAL LIBRARY
50 downloads per 1-year subscription
Members: $195
Non-members: $335 ADD TO CART
25 downloads per 1 - year subscription
Members: $145
Non-members: $250 ADD TO CART
PURCHASE SINGLE ARTICLE
Includes PDF, HTML & Video, when available
Members: $17.00
Non-members: $21.00 ADD TO CART
PROCEEDINGS
 PRESENTATION
WATCH
PRESENTATION SAVE TO MY LIBRARY
GET CITATION
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
KEYWORDS
Data modeling
Process modeling
National Ignition Facility
Computer architecture
Image fusion
Machine learning
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top