BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250626T234543Z
LOCATION:Exhibit Hall A3
DTSTART;TZID=America/New_York:20241120T090000
DTEND;TZID=America/New_York:20241120T093000
UID:submissions.supercomputing.org_SC24_sess501_awd102@linklings.com
SUMMARY:Validated AI-Powered Machine Learning for Accelerating Delivery of
  Scientific Grand Challenges (2024 IEEE-CS Sidney Fernbach Award)
DESCRIPTION:William Tang (Princeton Plasma Physics Laboratory)\n\nA US imp
 erative is to deliver a Fusion Pilot Plant to accelerate the fusion energy
  development timeline.  This will rely heavily on validated scientific and
  engineering advances driven by HPC together with advanced statistical met
 hods featuring artificial intelligence/deep learning/machine learning (AI/
 DL/ML) that must properly embrace verification, validation, and uncertaint
 y quantification (VVUQ).  Especially time-urgent is the need to predict an
 d avoid large­-scale “major disruptions” in tokamak systems.  \n\nThis tal
 k highlights the deployment of recurrent and convolutional neural networks
  in Princeton'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.  Moreover, the AI/DL capability can provide not only the “di
 sruption score,” as an indicator of the probability of an imminent disrupt
 ion but also a “sensitivity score” in real-time to indicate the underlying
  reasons for the predicted disruption.  A real-time prediction and control
  capability has recently been significantly advanced with a novel surrogat
 e model/HPC simulator ("SGTC")—a first-principles-based prediction and con
 trol surrogate necessary for projections to future experimental devices (e
 .g., ITER, FPP's) for which no "ground truth" observational data exist.\n\
 nRegistration Category: Tech Program Reg Pass\n\nSession Chairs: Venkatesh
  Kannan (Irish Centre for High‑End Computing (ICHEC)) and Scott Pakin (Los
  Alamos National Laboratory (LANL))\n\n
END:VEVENT
END:VCALENDAR