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:20250822T115807Z
LOCATION:Room 5.0B15 & 16
DTSTART;TZID=Europe/Stockholm:20250616T122000
DTEND;TZID=Europe/Stockholm:20250616T125000
UID:submissions.pasc-conference.org_PASC25_sess139_msa198@linklings.com
SUMMARY:Can AI-Based Numerical Weather Prediction Models Help us to Unders
 tand Future Climate?
DESCRIPTION:Nikolay Koldunov (Alfred Wegener Institute), Thomas Rackow (EC
 MWF), and Amal John (Alfred Wegener Institute)\n\nAI-driven Numerical Weat
 her Prediction (AI-NWP) models, trained on the ERA5 reanalysis are current
 ly our best representation of historical day-to-day weather evolution. The
 y have demonstrated significant skill in forecasting present-day weather, 
 outperforming traditional physics-based forecasting systems. Emerging evid
 ence suggests that AI-NWP models do not merely replicate past atmospheric 
 states but effectively learn the underlying physical dynamics of the atmos
 phere. We anticipate that, especially at short time scales (on the order o
 f several days), AI-NWP models will outperform most existing climate model
 s in simulating realistic weather conditions, including weather in the fut
 ure climate scenarios. This improved performance may result from the riche
 r dynamics captured by high-resolution AI-NWP models (typically around 25 
 km) compared to conventional climate models (usually around 100 km), or si
 mply from their superior representation of atmospheric processes learned f
 rom ERA5. Such capabilities could even help to correct biases in current c
 limate models. In this study, we examine the applicability of AI-NWP model
 s to various climate scenarios and demonstrate their potential benefits fo
 r contemporary climate research. Specifically, we highlight their capabili
 ties for downscaling coarse-resolution climate simulations and explore the
 ir capabilities in investigating extreme weather events through a storylin
 e approach by reproducing present-day extreme events under altered climate
  conditions.\n\nDomain: Climate, Weather, and Earth Sciences, Computationa
 l Methods and Applied Mathematics\n\nSession Chairs: Christian Lessig (ECM
 WF, Otto-von-Guericke-Universitat Magdeburg) and Ilaria Luise (CERN)\n\n
END:VEVENT
END:VCALENDAR