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:20250822T115810Z
LOCATION:Room 5.0B56
DTSTART;TZID=Europe/Stockholm:20250616T122000
DTEND;TZID=Europe/Stockholm:20250616T125000
UID:submissions.pasc-conference.org_PASC25_sess109_msa258@linklings.com
SUMMARY:Advancing Fusion Research through AI and Machine Learning
DESCRIPTION:Alessandro Pau (EPFL, Swiss Plasma Center)\n\nRecent advances 
 in Artificial Intelligence (AI), Machine Learning (ML), and data-driven me
 thods have opened promising pathways for addressing complex computational 
 and control challenges in nuclear fusion and Tokamak research. Tokamak dev
 ices, a key configuration for magnetic confinement fusion, produce extensi
 ve and complex datasets that present unique challenges due to their multi-
 physics, nonlinear dynamics, and high-dimensional parameter spaces. This a
 bstract introduces key computational challenges in fusion research, highli
 ghting the critical importance of large-scale data analysis and advanced A
 I techniques for interpreting experimental results, optimizing plasma cont
 rol strategies, and reducing operational uncertainties in contexts where h
 igh-bandwidth diagnostics produce large amounts of data, even during real-
 time operations. We will discuss how AI-driven surrogate and reduced-order
  models can effectively complement or even replace computationally expensi
 ve, high-fidelity simulation codes in certain scenarios, significantly acc
 elerating analysis and enabling physics discovery. Another important aspec
 t is the integration of real-time ML algorithms, transforming plasma contr
 ol strategies and leading to significant performance improvements in extre
 mely challenging fields such as plasma stability and disruption prediction
 . Specific examples and results from recent experimental and computational
  studies will be presented, demonstrating the efficacy and reliability of 
 these data-driven approaches.\n\nDomain: Physics, Computational Methods an
 d Applied Mathematics\n\nSession Chair: Laurent Villard (EPFL)\n\n
END:VEVENT
END:VCALENDAR