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:20230831T095746Z
LOCATION:Sertig
DTSTART;TZID=Europe/Stockholm:20230627T163000
DTEND;TZID=Europe/Stockholm:20230627T170000
UID:submissions.pasc-conference.org_PASC23_sess170_msa234@linklings.com
SUMMARY:GraphCast: Learning Skillful Medium-Range Global Weather Forecasti
 ng
DESCRIPTION:Minisymposium\n\nPeter Battaglia (DeepMind, Alphabet)\n\nWe pr
 esent our recent paper “GraphCast: Learning skillful medium-range global w
 eather forecasting” (https://arxiv.org/abs/2212.12794). GraphCast is a mac
 hine-learning (ML) based weather simulator, trained from the ERA5 reanalys
 is archive, which can make forecasts, at 6-hour time intervals, of five su
 rface variables and six atmospheric variables (37 vertical pressure levels
 ), on a 0.25-degree grid (~25 km at the equator). GraphCast can generate a
  10-day forecasts (35 gigabytes of data) in under 60 seconds, while outper
 forming ECMWF's deterministic operational forecasting system, HRES, on 90.
 0% of the 2760 variable and lead time combinations we evaluated, as well a
 s all other ML baselines. These results represent a key step forward in co
 mplementing and improving weather modeling with ML, opening new opportunit
 ies for fast, accurate forecasting. In this talk we will go into the detai
 ls of the model architecture, as well as providing a detailed evaluation a
 gainst HRES.4 presentation abstract/overview.\n\nDomain: Climate, Weather 
 and Earth Sciences\n\nSession Chair: Karthik Kashinath (NVIDIA Inc., Lawre
 nce Berkeley National Laboratory)
END:VEVENT
END:VCALENDAR