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:20230627T173000
DTEND;TZID=Europe/Stockholm:20230627T180000
UID:submissions.pasc-conference.org_PASC23_sess170_msa181@linklings.com
SUMMARY:Accurate Medium-Range Global Weather Forecasting with 3D Deep Neur
 al Networks
DESCRIPTION:Minisymposium\n\nKaifeng Bi, Lingxi Xie, Hengheng Zhang, Xin C
 hen, Xiaotao Gu, and Qi Tian (Huawei)\n\nWeather forecasting is important 
 for science and society. Currently, the most accurate forecast system is t
 he numerical weather prediction (NWP) method, which represents atmospheric
  states as discretized grids and numerically solves partial differential e
 quations (PDEs) that describe the transition between those states. However
 , this procedure is computationally expensive. Recently, AI-based weather 
 forecasting methods have shown potential in accelerating weather forecasti
 ng by orders of magnitudes, but the forecast accuracy is still significant
 ly lower than that of NWP methods. In this paper, we introduce an AI-based
  method for accurate, medium-range global weather forecasting. We show tha
 t 3D deep networks equipped with Earth-specific priors are effective at de
 aling with complex patterns in weather data, and that a hierarchical tempo
 ral aggregation strategy reduces accumulation errors in medium-range forec
 asting. Trained on 39 years of global data, our program, Pangu-Weather, is
  the first to obtain stronger deterministic forecast results on reanalysis
  data in all tested variables, when compared with the world’s best NWP sys
 tem, the operational integrated forecasting system (IFS) of the European C
 entre for Medium-Range Weather Forecasts (ECMWF). Our method also works we
 ll with extreme weather forecasts and ensemble forecasts. When initialized
  with reanalysis data, the accuracy of tracking tropical cyclones is highe
 r than ECMWF-HRES.\n\nDomain: Climate, Weather and Earth Sciences\n\nSessi
 on Chair: Karthik Kashinath (NVIDIA Inc., Lawrence Berkeley National Labor
 atory)
END:VEVENT
END:VCALENDAR