BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260202T201249Z
LOCATION:Second Floor Atrium
DTSTART;TZID=America/Chicago:20251120T080000
DTEND;TZID=America/Chicago:20251120T170000
UID:submissions.supercomputing.org_SC25_sess533_post186@linklings.com
SUMMARY:Building the Foundation for Machine Learning-Based Mars Weather Fo
 recasting
DESCRIPTION:Mohammad Altiwainy (Wayne State University)\n\nMars is a leadi
 ng target for human exploration, yet its weather remains difficult to pred
 ict due to phenomena such as global dust storms. While Earth forecasting h
 as advanced through machine learning (ML), Mars lacks comparable systems. 
 This work investigates whether Microsoft’s Aurora, a state-of-the-art Eart
 h climate foundation model, can be adapted for Martian data. Using the EMA
 RS reanalysis, we regridded variables to Aurora’s expected layout and exec
 uted inference on the University of Michigan’s Great Lakes supercomputing 
 cluster. We verified Aurora’s Earth pipeline by reproducing ERA5 benchmark
 s and established a functional pathway for applying Aurora to Mars; howeve
 r, full predictive accuracy requires Mars-specific surface/static variable
 s and fine-tuning. The poster will present the adaptation pipeline, valida
 tion on ERA5, preliminary EMARS runs, and a roadmap to reliable ML-based M
 ars weather forecasting, emphasizing the role of HPC in data preparation a
 nd model execution.\n\nTag: Research & ACM SRC Posters\n\nRegistration Cat
 egory: Technical Program Reg Pass\n\nSession Chairs: Kento Sato (RIKEN Cen
 ter for Computational Science (R-CCS)); Chris Schlipalius (Pawsey Supercom
 puting Research Centre; Commonwealth Scientific and Industrial Research Or
 ganisation (CSIRO), Australia); and Anja Gerbes (Georg-August-Universität 
 Göttingen)\n\n
END:VEVENT
END:VCALENDAR