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:20230831T095754Z
LOCATION:Sertig
DTSTART;TZID=Europe/Stockholm:20230626T120000
DTEND;TZID=Europe/Stockholm:20230626T130000
UID:submissions.pasc-conference.org_PASC23_sess177@linklings.com
SUMMARY:AP1C - ACM Papers Session 1C
DESCRIPTION:Paper\n\nApproximation and Optimization of Global Environmenta
 l Simulations with Neural Networks\n\nSolving a system of hundreds of chem
 ical differential equations in environmental simulations has a major compu
 tational complexity, and thereby requires high performance computing resou
 rces, which is a challenge as the spatio-temporal resolution increases. Ma
 chine learning methods and specially deep ...\n\n\nElnaz Azmi, Jörg Meyer,
  and Marcus Strobl (Karlsruhe Institute of Technology); Michael Weimer (Ma
 ssachusetts Institute of Technology); and Achim Streit (Karlsruhe Institut
 e of Technology)\n---------------------\nPerformance Study of Convolutiona
 l Neural Network Architectures for 3D Incompressible Flow Simulations\n\nR
 ecently, correctly handling spatial information from multiple scales has p
 roven to be essential in Machine Learning (ML) applications on Computation
 al Fluid Dynamics (CFD) problems. For these type of applications, Convolut
 ional Neural Networks (CNN) that use Multiple Downsampled Branches (MDBs) 
 to ...\n\n\nEkhi Ajuria Illarramendi (CERFACS, ISAE SUPAERO); Michael Baue
 rheim (ISAE SUPAERO); Neil Ashton (AWS); and Coretin Lapeyre and Bénédicte
  Cuenot (CERFACS)\n\nDomain: Climate, Weather and Earth Sciences\n\nSessio
 n Chair: William Sawyer (ETH Zurich / CSCS)
END:VEVENT
END:VCALENDAR