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:20230831T095745Z
LOCATION:Sertig
DTSTART;TZID=Europe/Stockholm:20230626T123000
DTEND;TZID=Europe/Stockholm:20230626T130000
UID:submissions.pasc-conference.org_PASC23_sess177_pap131@linklings.com
SUMMARY:Performance Study of Convolutional Neural Network Architectures fo
 r 3D Incompressible Flow Simulations
DESCRIPTION:Paper\n\nEkhi Ajuria Illarramendi (CERFACS, ISAE SUPAERO); Mic
 hael Bauerheim (ISAE SUPAERO); Neil Ashton (AWS); and Coretin Lapeyre and 
 Bénédicte Cuenot (CERFACS)\n\nRecently, correctly handling spatial informa
 tion from multiple scales has proven to be essential in Machine Learning (
 ML) applications on Computational Fluid Dynamics (CFD) problems. For these
  type of applications, Convolutional Neural Networks (CNN) that use Multip
 le Downsampled Branches (MDBs) to efficiently encode spatial information f
 rom different spatial scales have proven to be some of the most successful
  architectures. However, not many guidelines exist to build these architec
 tures, particularly when applied to more challenging 3D configurations. Th
 us, this work focuses on studying the impact of the choice of the number o
 f downsampled branches, accuracy and performance-wise in 3D incompressible
  fluid test cases, where a CNN is used to solve the Poisson equation. The 
 influence of this parameter is assessed by performing multiple trainings o
 f Unet architectures with varying MDBs on a cloud-computing environment. T
 hese trained networks are then tested on two 3D CFD problems: a plume and 
 a Von Karman vortex street at various operating points, where the solution
  of the neural network is coupled to a nonlinear advection equation.\n\nDo
 main: Climate, Weather and Earth Sciences\n\nSession Chair: William Sawyer
  (ETH Zurich / CSCS)
END:VEVENT
END:VCALENDAR