BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000711Z
LOCATION:501-502
DTSTART;TZID=America/Denver:20231113T170000
DTEND;TZID=America/Denver:20231113T171500
UID:submissions.supercomputing.org_SC23_sess440_ws_ai4s116@linklings.com
SUMMARY:Entropy-Driven Optimal Sub-Sampling of Fluid Dynamics for Developi
 ng Machine-Learned Surrogates
DESCRIPTION:Wesley Brewer (Oak Ridge National Laboratory (ORNL)); Daniel M
 artinez (Science and Technology Corporation); Muralikrishnan Gopalakrishna
 n Meena, Aditya Kashi, Katarzyna Borowiec, and Siyan Liu (Oak Ridge Nation
 al Laboratory (ORNL)); and Christopher Pilmaier, Greg Burgreen, and Shanti
  Bhushan (Mississippi State University)\n\nOptimal sub-sampling of large d
 atasets from fluid dynamics simulations is essential for training reduced-
 order machine learned models. A method using Shannon entropy was developed
  to weight flow features according to their level of information content, 
 such that the most informative features can be extracted and used for trai
 ning a surrogate model. The method is demonstrated in the canonical flow o
 ver a cylinder problem simulated with OpenFOAM. Both time-independent pred
 ictions and temporal forecasting were investigated as well as two types of
  prediction targets: local per-grid-point predictions and global per-time-
 step predictions. When tested on training a surrogate model, results indic
 ate that our entropy-based sampling method typically outperforms random sa
 mpling and yields more reproducible results in fewer iterations. Finally, 
 the method was used to train a surrogate model for modeling turbulence in 
 magnetohydrodynamic flows, which revealed various challenges and opportuni
 ties for future research.\n\nTag: Artificial Intelligence/Machine Learning
 \n\nRegistration Category: Workshop Reg Pass\n\nSession Chairs: Murali Ema
 ni (Argonne National Laboratory (ANL)); Gokcen Kestor (Barcelona Supercomp
 uting Center (BSC); University of California, Merced); and Dong Li (Univer
 sity of California, Merced)\n\n
END:VEVENT
END:VCALENDAR