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:Davos
DTSTART;TZID=Europe/Stockholm:20230627T100400
DTEND;TZID=Europe/Stockholm:20230627T100600
UID:submissions.pasc-conference.org_PASC23_sess110_pos129@linklings.com
SUMMARY:P34 - Interpretable Compression of Fluid Flows Using Graph Neural 
 Networks
DESCRIPTION:Poster\n\nShivam Barwey (Argonne National Laboratory) and Romi
 t Maulik (Argonne National Laboratory, University of Pennsylvania)\n\nNeur
 al network (NN) based reduced-order models (ROMs) via autoencoding have be
 en shown to drastically accelerate traditional computational fluid dynamic
 s (CFD) simulations for rapid design optimization and prediction of fluid 
 flows. However, many real-world applications (e.g. hypersonic propulsion, 
 pollutant dispersion in cities, wildfire spread) rely on complex geometry 
 treatment and unstructured mesh representations in the simulation workflow
  — in this setting, conventional NN-based modeling approaches break down. 
 Instead, it is necessary to use frameworks that (a) easily interface with 
 unstructured grid data, and (b) are not restricted to single geometric con
 figurations after training. The goal here is to address this through the d
 evelopment of an interpretable autoencoding strategy based on the graph ne
 ural network (GNN) paradigm. More specifically, a novel graph autoencoder 
 architecture is developed for ROM-amenable autoencoding. An adaptive graph
  pooling strategy, combined with multiscale message passing operations, is
  shown to produce interpretable latent spaces through the identification o
 f coherent structures. With this notion of interpretability established, a
 nalysis is then conducted on effects of compression factors, physical sign
 ificance of identified coherent structures, and impact of multi-scale mess
 age passing on reconstruction errors.\n\nSession Chair: Jibonananda Sanyal
  (National Renewable Energy Laboratory)
END:VEVENT
END:VCALENDAR