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:20260202T201804Z
LOCATION:America's Ballroom Tu-Th
DTSTART;TZID=America/Chicago:20251120T103000
DTEND;TZID=America/Chicago:20251120T111500
UID:submissions.supercomputing.org_SC25_sess386_inv107@linklings.com
SUMMARY:From Gordon Bell Finalist to the Osaka Expo: The Evolution of Real
 -Time Forecasting on Fugaku
DESCRIPTION:Takemasa Miyoshi (RIKEN Center for Computational Science (R-CC
 S))\n\nBuilding directly upon our work that was a finalist for the Gordon 
 Bell Prize for Climate Modelling at SC23, this talk presents the next stag
 e of our pioneering research in real-time weather prediction with unpreced
 ented precision on the supercomputer Fugaku. Our new experiment for the Ex
 po 2025 Osaka Kansai marks a world's first: the simultaneous use of two Mu
 lti-Parameter Phased Array Weather Radars for data assimilation (DA). This
  novel configuration provided an unprecedented data stream assimilated in 
 real time by our Big Data Assimilation system on the supercomputer Fugaku,
  enabling 30-second-refresh, 30-minute-lead precipitation forecasts at a 5
 00-meter resolution. \n\nBuilding on the capabilities of this system, the 
 talk then shifts focus to the future of prediction science, exploring our 
 multifaceted research at RIKEN to fuse DA with AI/ML. Motivated by the nee
 d to combine the strengths of physics-based models with data-driven techni
 ques and adapt to modern GPU-centric architectures, we will present five e
 xamples of our hybrid methodologies. These include integrating convolution
 al LSTMs with numerical weather prediction, developing deep neural network
  observation operators for satellite data, and using DA to iteratively ref
 ine AI surrogate models. The talk will conclude with a forward-looking per
 spective on fully Bayesian estimation, discussing how emerging techniques 
 like conditional diffusion models could achieve the ultimate goal of DA: d
 irectly sampling atmospheric states from observations.\n\nTag: AI, Machine
  Learning, & Deep Learning, Big Data, Weather Prediction\n\nRecording: Liv
 estreamed, Recorded\n\nRegistration Category: Technical Program Reg Pass\n
 \nSession Chair: Miwako Tsuji (University of Tsukuba, RIKEN Center for Com
 putational Science (R-CCS))\n\n
END:VEVENT
END:VCALENDAR