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:20241120T082410Z
LOCATION:HG E 3
DTSTART;TZID=Europe/Stockholm:20240603T170000
DTEND;TZID=Europe/Stockholm:20240603T173000
UID:submissions.pasc-conference.org_PASC24_sess177_pap109@linklings.com
SUMMARY:Toward Improving Boussinesq Flow Simulations by Learning with Comp
 ressible Flow
DESCRIPTION:Paper\n\nNurshat Mangnike and David Hyde (Vanderbilt Universit
 y)\n\nIn computational fluid dynamics, the Boussinesq approximation is a p
 opular model for the numerical simulation of natural convection problems. 
 Although using the Boussinesq approximation leads to significant performan
 ce gains over a full-fledged compressible flow simulation, the model is on
 ly plausible for scenarios where the temperature differences are relativel
 y small, which limits its applicability. This paper bridges the gap betwee
 n Boussinesq flow and compressible flow via deep learning: we introduce a 
 computationally-efficient CNN-based framework that corrects Boussinesq flo
 w simulations by learning from the full compressible model. Based on a mod
 ified U-Net architecture and incorporating a weighted physics penalty loss
 , our model is trained with and evaluated against a specific natural conve
 ction problem. Our results show that by correcting Boussinesq simulations 
 using the trained network, we can enhance the accuracy of velocity, temper
 ature, and pressure variables over the Boussinesq baseline—even for cases 
 beyond the regime of validity of the Boussinesq approximation.\n\nDomain: 
 Engineering\n\nSession Chair: Carla Judith López Zurita (ETH Zurich)
END:VEVENT
END:VCALENDAR