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:20240604T110000
DTEND;TZID=Europe/Stockholm:20240604T113000
UID:submissions.pasc-conference.org_PASC24_sess116_msa267@linklings.com
SUMMARY:Towards Neural Green's Operators for Magnetic Fusion
DESCRIPTION:Minisymposium\n\nMichael Abdelmalik (Eindhoven University of T
 echnology); Jonathan Citrin (DeepMind); and Josefine Proll, Joost Prins, a
 nd Hugo Melchers (Eindhoven University of Technology)\n\nOperator networks
  have emerged as promising machine learning tools for reduced order modeli
 ng of a wide range of physical systems described by partial differential e
 quations (PDEs).  This work describes a new architecture for operator netw
 orks that approximates the Green's operator to a linear PDE. Such a ‘Neura
 l Green’s Operator’ (NGO) acts as a surrogate for the PDE solution operato
 r: it maps the PDE’s input functions (e.g. forcings, boundary conditions, 
 material parameters) to its solution. We apply NGOs to relevant canonical 
 PDEs and ask the question whether the NGO architecture would lead to signi
 ficant computational benefits and conclude the discussion with numerical e
 xamples.\n\nDomain: Physics, Computational Methods and Applied Mathematics
 \n\nSession Chairs: Stephan Brunner (EPFL); Eric Sonnendrücker (Max Planck
  Institute for Plasma Physics, Technical University of Munich); and Lauren
 t Villard (EPFL)
END:VEVENT
END:VCALENDAR