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:20241120T082408Z
LOCATION:HG F 1
DTSTART;TZID=Europe/Stockholm:20240603T123000
DTEND;TZID=Europe/Stockholm:20240603T130000
UID:submissions.pasc-conference.org_PASC24_sess108_msa147@linklings.com
SUMMARY:Evaluation of a Foundation Model Approach for Weather and Climate
DESCRIPTION:Minisymposium\n\nTroy Arcomano (Argonne National Laboratory), 
 Alex Wikner (University of Chicago), Tung Nguyen (UCLA), Romit Maulik (Uni
 versity of Pennsylvania), Sandeep Madireddy (Argonne National Laboratory),
  Aditya Grover (UCLA), and Rao Kotamarthi (Argonne National Laboratory)\n\
 nFoundation models have demonstrated great success in the field of natural
  language processing (NLP) and for other vision-based tasks (e.g., DALL-E)
 . With the rise of data-driven, global weather forecast models, researcher
 s have begun to create foundation models for the Earth System. There sever
 al foundation models in development (e.g., ClimaX) to allow for rapid fine
 -tuning to specific tasks such as weather forecasting or climate. However,
  several open questions remain on how well this foundation model approach 
 will work with such a complex and diverse set of tasks typically needed fo
 r weather and climate. Here, we evaluate the ability for ClimaX to perform
  downstream tasks not seen during the pre-training phase. Specifically, we
  look at two tasks using ClimaX fine-tuned on ERA5 to 1) perform data assi
 milation using real, in-situ observations of the atmosphere and 2) replace
  the output layer of the foundation model with one that is parameterized b
 y a Gaussian to perform uncertainty quantification (UQ). We also use the l
 essons learned from these experiments to develop a state-of-the-art weathe
 r forecasting model called Stormer. Stormer is a simple transformer-based 
 model that achieves state-of-the-art performance on weather forecasting wi
 th minimal changes to the standard transformer backbone.\n\nDomain: Climat
 e, Weather, and Earth Sciences, Computational Methods and Applied Mathemat
 ics\n\nSession Chair: Christian Lessig (ECMWF, Otto-von-Guericke-Universit
 at Magdeburg)
END:VEVENT
END:VCALENDAR