BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210402T160544Z
LOCATION:Poster Module
DTSTART;TZID=America/New_York:20201119T083000
DTEND;TZID=America/New_York:20201119T170000
UID:submissions.supercomputing.org_SC20_sess337_rpost116@linklings.com
SUMMARY:Material Interface Reconstruction Using Machine Learning
DESCRIPTION:Posters, Research Posters\n\nMaterial Interface Reconstruction
  Using Machine Learning\n\nFenn, Lewis, Doutriaux\n\nIn multi-material sim
 ulations, it is important to track material interfaces. These are frequent
 ly not tracked explicitly and must be reconstructed from zone data. Curren
 t methods provide either material conservation or interface continuity, bu
 t not both, meaning that many interfaces may be constructed erroneously, a
 ffecting simulation accuracy. Meanwhile, progress in image-related machine
  learning (ML) fields is noteworthy, and several of such fields exhibit co
 nceptual similarity to the material interface reconstruction (MIR) problem
 . Here we investigate the application of image-based, supervised learning 
 methods to MIR. We generate images by taking “snapshots” of a mesh, with t
 he material information encoded as a pixel value. We feed these images to 
 a network that infers the interface morphology. We use an autoencoder desi
 gn and generate synthetic data. Our network is able to accurately reproduc
 e correct interfaces for most cases. Our promising results indicate that t
 he application of ML to MIR warrants further study.\n\nRegistration Catego
 ry: Tech Program Reg Pass, Exhibits Reg Pass
END:VEVENT
END:VCALENDAR