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:20230831T095746Z
LOCATION:Seehorn
DTSTART;TZID=Europe/Stockholm:20230627T143000
DTEND;TZID=Europe/Stockholm:20230627T150000
UID:submissions.pasc-conference.org_PASC23_sess184_pap127@linklings.com
SUMMARY:AI Super-Resolution Subfilter Modeling for Multi-Physics Flows
DESCRIPTION:Paper\n\nMathis Bode (Forschungszentrum Jülich)\n\nMany comple
 x simulations are extremely expensive and hardly if at all doable, even on
  current supercomputers. A typical reason for this are coupled length and 
 time scales in the application which need to be resolved simultaneously. A
 s a result, many simulation approaches rely on scale-splitting, where only
  the larger scales are simulated, while the small scales are modeled with 
 subfilter models. This work presents a novel subfilter modeling approach b
 ased on AI super-resolution. A physics-informed enhanced super-resolution 
 generative adversarial network (PIESRGAN) is used to accurately close subf
 ilter terms in the solved transport equations. It is demonstrated how a si
 mulation design with the PIESRGAN-approach can be used to accelerate compl
 ex simulations on current supercomputers, on the example of three fluid dy
 namics simulation setups with complex features on the supercomputer enviro
 nment JURECA-DC/JUWELS (Booster). Further advantages and shortcoming of th
 e PIESRGAN-approach are discussed.\n\nDomain: Engineering, Computer Scienc
 e, Machine Learning, and Applied Mathematics 
\n\nSession Chair: Nur Aiman
  Fadel (ETH Zurich / CSCS)
END:VEVENT
END:VCALENDAR