BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241120T082409Z
LOCATION:HG F 26.3
DTSTART;TZID=Europe/Stockholm:20240604T113000
DTEND;TZID=Europe/Stockholm:20240604T120000
UID:submissions.pasc-conference.org_PASC24_sess116_msa246@linklings.com
SUMMARY:Artificial Intelligence/Machine Learning/HPC Acceleration of Progr
 ess in Fusion Energy R&D
DESCRIPTION:Minisymposium\n\nWilliam Tang (Princeton University, Princeton
  Plasma Physics Lab)\n\nThe US goal (March, 2022) to deliver a Fusion Pilo
 t Plant [1] has underscored urgency for accelerating the fusion energy dev
 elopment timeline.  This will rely heavily on validated scientific and eng
 ineering advances driven by HPC together with advanced statistical methods
  featuring artificial intelligence/deep learning/machine learning (AI/DL/M
 L) that must properly embrace verification, validation, and uncertainty qu
 antification (VVUQ).  Especially time-urgent is the need to predict and av
 oid large­ scale “major disruptions” in tokamak systems.  This keynote hig
 hlights the deployment of recurrent and convolutional neural networks in P
 rinceton's Deep Learning Code -- "FRNN" – that enabled the first adaptable
  predictive DL model for carrying out efficient "transfer learning" while 
 delivering validated predictions of disruptive events across prominent tok
 amak devices [2].  Moreover, the AI/DL capability can provide not only the
  “disruption score,” as an indicator of the probability of an imminent dis
 ruption but also a “sensitivity score” in real-time to indicate the underl
 ying reasons for the predicted disruption [3].  A real-time prediction and
  control capability has recently been significantly advanced with a novel 
 surrogate model/HPC simulator ("SGTC") [4] -- a first-principles-based pre
 diction and control surrogate necessary for projections to future experime
 ntal devices (e.g., ITER, FPP's) for which no "ground truth" observational
  data exist.\n\nDomain: Physics, Computational Methods and Applied Mathema
 tics\n\nSession Chairs: Stephan Brunner (EPFL); Eric Sonnendrücker (Max Pl
 anck Institute for Plasma Physics, Technical University of Munich); and La
 urent Villard (EPFL)
END:VEVENT
END:VCALENDAR