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:20260421T090514Z
LOCATION:Bldg. 6 - Room 103
DTSTART;TZID=Europe/Stockholm:20260630T141500
DTEND;TZID=Europe/Stockholm:20260630T144500
UID:submissions.pasc-conference.org_PASC26_sess145_msa214@linklings.com
SUMMARY:Near Real Time Resilient Workflows
DESCRIPTION:Scott Klasky (Oak Ridge National Laboratory)\n\nIn this presen
 tation, we advocate for information driven methodologies that construct ad
 aptive surrogates for data and workflow components. Rather than replicatin
 g entire pipelines, we selectively reduce data and computation based on qu
 antified uncertainty and relevance. Central to this strategy is physics in
 formed AI, which enables principled uncertainty estimation, preserves key 
 physical constraints, and accelerates analysis. By dynamically compressing
  data representations and replacing expensive workflow stages with learned
  surrogates, we reduce memory and computational footprints while adapting 
 accuracy to meet strict timeliness requirements. This allows workflows to 
 satisfy hard time guarantees without sacrificing scientific fidelity. Furt
 hermore, these strategies must leverage GPUs and specialized hardware, alo
 ng with including cross disciplinary design principles for resilient, scal
 able NRT workflows in data intensive science.\n\nDomain: Engineering, Phys
 ics, Computational Methods and Applied Mathematics\n\nSession Chairs: Raee
 s Ahmad Khan (University of Pittsburgh, CERN); Tatiana Korchuganova (Unive
 rsity of Pittsburgh, CERN); and Alexei Klimentov (Brookhaven National Labo
 ratory)\n\n
END:VEVENT
END:VCALENDAR