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:20230831T095747Z
LOCATION:Sertig
DTSTART;TZID=Europe/Stockholm:20230628T153000
DTEND;TZID=Europe/Stockholm:20230628T160000
UID:submissions.pasc-conference.org_PASC23_sess109_msa246@linklings.com
SUMMARY:Capabilities, Limitations and Validation of Statistical Earth Syst
 em Models
DESCRIPTION:Minisymposium\n\nChristian Lessig (Otto-von-Guericke-Universit
 at Magdeburg)\n\nThe last year has seen tremendous progress on deep learni
 ng based forecasting models trained on reanalysis data. An extension of th
 ese to Earth system models (ESMs) and to training on observational data fo
 r obtaining predictions that are not bound by the reanalysis process (and 
 hence classical models) is an exciting frontier in the coming years. I wil
 l first discuss how machine learning-based models are conceptually differe
 nt from classical ESMs in that they are statistical representations of the
  dynamical processes modeled by p( y|x ). Some capabilities that statistic
 al models can provide that are very difficult to impossible to achieve wit
 h classical ESMs will be showcased and potential fundamental limitations o
 f such models will be discussed. Based on this, I will examine novel chall
 enges for validating machine learning-based Earth system models, in partic
 ular when trained on observational data.\n\nDomain: Climate, Weather and E
 arth Sciences\n\nSession Chair: Tobias Weigel (German Climate Computing Ce
 ntre, DKRZ)
END:VEVENT
END:VCALENDAR