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:20220812T074334Z
LOCATION:Sydney Room
DTSTART;TZID=Europe/Stockholm:20220627T163000
DTEND;TZID=Europe/Stockholm:20220627T170000
UID:submissions.pasc-conference.org_PASC22_sess127_msa140@linklings.com
SUMMARY:Extreme Weather Forecasting using Fourier Neural Operator on HPC S
 ystems
DESCRIPTION:Minisymposium\n\nExtreme Weather Forecasting using Fourier Neu
 ral Operator on HPC Systems\n\nKurth, Pathak, Subramanian, Harrington, Raj
 a...\n\nWe present FourCastNet, short for Fourier Forecasting Neural Netwo
 rk, a global data-driven weatherforecasting model that provides accurate s
 hort to medium-range global predictions at 0.25-degree resolution. FourCas
 tNet accurately forecasts high-resolution, fast-timescale variables such a
 s the surface wind speed, precipitation, and atmospheric water vapor. It h
 as important implications for planning wind energy resources, predicting e
 xtreme weather events such as tropical cyclones, extra-tropical cyclones, 
 and atmospheric rivers. FourCastNet matches the forecasting accuracy of th
 e ECMWF Integrated Forecasting System (IFS), a state-of-the-art Numerical 
 Weather Prediction (NWP) model, at short lead times for large-scale variab
 les, while outperforming IFS for variables with complex fine-scale structu
 re, including precipitation. FourCastNet generates a week-long forecast in
  less than 2 seconds, orders of magnitude faster than IFS. The speed of Fo
 urCastNet enables the creation of rapid and inexpensive large-ensemble for
 ecasts with thousands of ensemble-members for improving probabilistic fore
 casting.<br />We discuss how data-driven deep learning models such as Four
 CastNet are a valuable addition to the meteorology toolkit to aid and augm
 ent NWP models.\n\nDomain: Climate, Weather and Earth Sciences, Computer S
 cience and Applied Mathematics, Engineering, Physics
END:VEVENT
END:VCALENDAR