Bulletin of the American Physical Society
63rd Annual Meeting of the APS Division of Plasma Physics
Volume 66, Number 13
Monday–Friday, November 8–12, 2021; Pittsburgh, PA
Session UM10: Mini-Conference: Machine Learning in Plasma Sciences: Today and TomorrowOn Demand
|
Hide Abstracts |
Chair: Luc Peterson, Lawrence Livermore Natl Lab Room: Room 406 |
Thursday, November 11, 2021 2:00PM - 2:30PM |
UM10.00001: Driving AI in Plasma Physics: building scientific collaboration Brian K Spears Artificial Intelligence methods are becoming essential plasma physics tools. The methods have been developed by early adopters in pockets of excellence across our discipline. Now, we need a deliberate strategy to steer research priorities. This includes not just physics research, but also machine learning algorithm work, new computing hardware, and new organizational structures to bring these disciplines together. We present here a model for collaborative research in the field of AI for science. We will describe new partnerships aimed a bringing together academic, national laboratory, and industrial partners to work on focused challenge problems. We will also present a view of the new AI Center of Excellence at Lawrence Livermore National Laboratory that plans stimulate and enable this transformational work. Finally, we will present some important challenge problems, the collaborative partners, and initial results. |
Thursday, November 11, 2021 2:30PM - 3:00PM |
UM10.00002: The data-driven future of high-energy-density physics Peter W Hatfield, Jim A Gaffney, Gemma J Anderson The study of high-energy-density physics is important for our understanding of astrophysics, nuclear fusion and fundamental physics—however, the nonlinearities and strong couplings present in these extreme physical systems makes them challenging to understand theoretically or to optimize experimentally. Here we argue that machine learning models and data-driven methods are in the process of reshaping our exploration of these extreme systems that have hitherto proved far too non-linear for human researchers. From a fundamental perspective, our understanding can be improved by the way in which machine learning models can rapidly discover complex interactions in large datasets. From a practical point of view, the newest generation of extreme physics facilities can perform experiments multiple times a second (as opposed to approximately daily), thus moving away from human-based control towards automatic control based on real-time interpretation of diagnostic data and updates of the physics model. To make the most of these emerging opportunities, we suggest proposals for the community in terms of research design, training, best practice and support for synthetic diagnostics and data analysis. This talk will summarise Hatfield et al., (2021), Nature, 593, 7859, 351–361. |
Thursday, November 11, 2021 3:00PM - 3:30PM |
UM10.00003: Machine Learning for Real-time Fusion Plasma Behavior Prediction and Manipulation Egemen Kolemen, Mark D Boyer, Ryan Coffee, Jeff Schneider, David R Smith, Azarakhsh Jalalvand, Rory Conlin, Joseph A Abbate An overview is presented of a new multi-institution collaboration funded by DOE among researchers from Princeton University, Carnegie Mellon University, PPPL, SLAC, University of Wisconsin – Madison to build the fundamental basis for use of Artificial Intelligence (AI)/Deep Learning (DL)/Machine Learning (ML) to augment real-time fusion plasma modeling, prediction, and manipulation. The group is developing a hierarchy of AI/DL/ML (in short ML) algorithms to 1) enable real-time simultaneous analysis of high- resolution multi-channel ECE, BES diagnostics, 2a) label and predict proximity to instability limits (specifically Alfven Eigenmodes and edge instabilities), 2b) produce real-time control-relevant predictions of plasma evolution that are difficult to obtain from physics simulations alone, and 3) manipulate experimental actuators in real-time. We are installing and testing this system on the DIII-D National Fusion Facility Plasma Control System. This work brings the power of ML techniques to plasma control. This will set the stage for successful operation of ITER, which requires plasma control at a level beyond current capabilities and will also expand the scientific understanding of plasma evolution and instabilities. |
Thursday, November 11, 2021 3:30PM - 4:00PM |
UM10.00004: Advancing Fusion with Machine Learning Research Needs Workshop and Report David A Humphreys, Ana Kupresanin, Mark D Boyer, John Canik, Choongseok Chang, Eric Cyr, Robert S Granetz, Jeffrey A Hittinger, Egemen Kolemen, Earl Lawrence, Valerio Pascucci, Abani Patra, David P Schissel Data-driven machine learning (ML) methods have been applied to fusion energy research for over two decades, including significant advances in the areas of disruption prediction, surrogate model generation, and experimental planning. Advances in large-scale parallel computation and statistical inference mathematics, along with the need to bridge key gaps in knowledge for design and operation of reactors such as ITER, have driven expansion of efforts in ML within the US government and worldwide. The Department of Energy (DOE) Office of Science programs in Fusion Energy Sciences (FES) and Advanced Scientific Computing Research (ASCR) have organized several activities to identify best strategies and approaches for applying ML methods to fusion energy research. We describe the results of a joint FES/ASCR DOE-sponsored Research Needs Workshop on Advancing Fusion with Machine Learning, held April 30 – May 2, 2019, in Gaithersburg, MD (https://science.osti.gov/-/media/fes/pdf/workshop-reports/FES_ASCR_Machine_Learning_Report.pdf). The workshop had broad representation from both FES and ASCR scientific communities, and identified seven Priority Research Opportunities (PRO's) with high potential for advancing fusion energy. |
Thursday, November 11, 2021 4:00PM - 5:00PM |
UM10.00005: Town Hall on the Future of the Machine Learning and Plasma Science Luc Peterson, Cristina Rea, Ralph Kube, Zhehui Wang Panel Discussion: J. Luc Peterson (LLNL),Ralph Kube (PPPL), Zhehui Wang (LANL), Cristina Rea (MIT) |
Follow Us |
Engage
Become an APS Member |
My APS
Renew Membership |
Information for |
About APSThe American Physical Society (APS) is a non-profit membership organization working to advance the knowledge of physics. |
© 2024 American Physical Society
| All rights reserved | Terms of Use
| Contact Us
Headquarters
1 Physics Ellipse, College Park, MD 20740-3844
(301) 209-3200
Editorial Office
100 Motor Pkwy, Suite 110, Hauppauge, NY 11788
(631) 591-4000
Office of Public Affairs
529 14th St NW, Suite 1050, Washington, D.C. 20045-2001
(202) 662-8700