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:20260624T171340Z
LOCATION:Bldg. 8 - Entrance Hall
DTSTART;TZID=Europe/Stockholm:20260630T173000
DTEND;TZID=Europe/Stockholm:20260630T194500
UID:submissions.pasc-conference.org_PASC26_sess135_pos120@linklings.com
SUMMARY:P41 - Using Generative Machine Learning to Produce High-Resolution
  Weather Data
DESCRIPTION:Petar Stamenkovic and Mary McGlohon (MeteoSwiss, ETH Zurich); 
 David Leutwyler and Xavier Lapillonne (MeteoSwiss); Fabian Bösch, Lukas Dr
 escher, and Henrique Mendonça (ETH Zurich / CSCS); Sebastian Schemm (Unive
 rsity of Cambridge); Siddhartha Mishra (ETH Zurich); and Oliver Fuhrer (Me
 teoSwiss)\n\nGenerative  machine learning techniques show promise for perf
 orming atmospheric downscaling (super-resolution for meteorological data) 
 to produce high-resolution weather and climate simulations. Previous work 
 has evaluated the quality of these models using standard error scores such
  as RMSE, absolute error, or power spectra. These techniques are somewhat 
 limited in evaluating the quality of meteorological data, where long-term 
 trends and prediction of extreme events are important, so to truly test th
 e performance of ML methods for downscaling, we must use metrics better su
 ited to meteorological models. \n\nIn this work, we adapt CorrDiff downsca
 ling model (Mardani et al. [1]) to the Alpen region, projecting from a glo
 bal dataset at ~30-km resolution grid (ERA5), to target regional datasets 
 at 2km (COSMO) and 1km (ICON) resolution grids. We report on the computati
 onal performance of the model and introduce evaluation techniques to analy
 ze model quality and compare with the results of numerical weather predict
 ion. We evaluate the quality of the model’s outputs on a single sample, a 
 day, and seasonal basis.\n\n
END:VEVENT
END:VCALENDAR