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:20250822T115809Z
LOCATION:Room 5.0B56
DTSTART;TZID=Europe/Stockholm:20250616T112000
DTEND;TZID=Europe/Stockholm:20250616T132000
UID:submissions.pasc-conference.org_PASC25_sess109@linklings.com
SUMMARY:MS1C - Machine Learning Methods for the Simulation of Magnetic Fus
 ion Plasmas
DESCRIPTION:The quest for fusion as an environmentally benign, virtually i
 nexhaustible energy source has recently taken frontstage thanks to a numbe
 r of breakthroughs such as a new world record for fusion power or the firs
 t demonstration of energetic breakeven. This minisymposium is dedicated to
  addressing challenges in the simulation of magnetic fusion plasmas and, m
 ore specifically, on the latest data-driven approaches, complementing the 
 more traditional ones. These include the use of deep learning methods to c
 ontrol the operation of tokamaks, the application of physics-informed neur
 al networks to accelerate the solution of the plasma kinetic equations, th
 e development of innovative techniques to accelerate the gathering of trai
 ning sets for neural surrogate models, as well as the development of neura
 l networks that preserve the symplectic nature of the underlying equations
  used for performing reduced-order modelling.\n\nAdvancing Fusion Research
  through AI and Machine Learning\n\nRecent advances in Artificial Intellig
 ence (AI), Machine Learning (ML), and data-driven methods have opened prom
 ising pathways for addressing complex computational and control challenges
  in nuclear fusion and Tokamak research. Tokamak devices, a key configurat
 ion for magnetic confinement fusion, pro...\n\n\nAlessandro Pau (EPFL, Swi
 ss Plasma Center)\n---------------------\nData-Efficient Surrogate Models 
 for Digital Twinning\n\nNeural surrogate models of physics simulators are 
 emerging ubiquitously in the Fusion community to satisfy the pressing need
  of fast optimisation tasks and flight simulator applications. However, ga
 thering the training sets for these surrogates can be very expensive, and 
 storing the data long-term m...\n\n\nLorenzo Zanisi (UKAEA)\n-------------
 --------\nStructure-Preserving Neural Networks for Hamiltonian Systems\n\n
 In this talk we perform structure-preserving reduced order modeling for th
 e semi-discretized Hamiltonian PDEs. Reduced order modeling can alleviate 
 the cost involved in applications such as optimization, uncertainty quanti
 fication and inverse problems, that require the repeated solution of large
 -dim...\n\n\nBenedikt Brantner and Michael Kraus (Max Planck Institute for
  Plasma Physics)\n---------------------\nHybrid Modeling and Numerical Met
 hods for Vlasov Equations\n\nPlasma physics simulations for fusion are par
 ticularly demanding in terms of computing time and memory consumption. Lea
 rning methods offer a way to reduce these costs, but at the expense of los
 ing theoretical guarantees and explainability. To mitigate these shortcomi
 ngs, we propose exploring hybrid ...\n\n\nemmanuel Franck (INRIA), Laurent
  Navoret (Unistra), Leo Bois and Victor Michel Dansac (INRIA), and Vincent
  Vigon (Unistra)\n\nDomain: Physics, Computational Methods and Applied Mat
 hematics\n\nSession Chair: Laurent Villard (EPFL)
END:VEVENT
END:VCALENDAR