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:20260421T090513Z
LOCATION:Bldg. 6 - Room 103
DTSTART;TZID=Europe/Stockholm:20260701T140000
DTEND;TZID=Europe/Stockholm:20260701T160000
UID:submissions.pasc-conference.org_PASC26_sess162@linklings.com
SUMMARY:MS5E - Foundation Model for Weather and Climate
DESCRIPTION:In recent years weather forecasting and to a lower extent clim
 ate modeling have been undergoing a revolution driven by the emergence of 
 machine learning-based models. After having been successfully developed an
 d used in the field of Large Language Model, the foundation model concept 
 is being applied to machine learning-based weather-forecasting. The goal i
 s to capture rich, multi-scale representations of the Earth system across 
 space and time by training on diverse datasets. These models can then be a
 pplied to a wide range of tasks, much like traditional equation-based Eart
 h system models. The first large foundation models are now emerging, and t
 heir potential applications are actively being explored. The talks in this
  minisymposium will define the concept of foundation models for weather an
 d climate, discuss both their development and applications, and provide a 
 comprehensive overview of the current state of the field.\n\nEarth System 
 Foundation Model - heterogeneous data integration and forecasting\n\nThe t
 alk introduces the Earth System Foundation Model (ESFM), a fully open foun
 dation model tailored for weather and climate modeling tasks. Built upon t
 he Swin Transformer backbone of the pioneering Aurora model, ESFM introduc
 es several key extensions that allow it to process diverse and heterogene.
 ..\n\n\nFirat Ozdemir, Yun Cheng, and Salman Mohebi (Swiss data science ce
 nter); Fanny Lehmann, Simon Adamov, Langwen Huang, Leonardo Trentini, Oliv
 er Fuhrer, Torsten Hoelfer, and Siddhartha Mishra (ETH Zurich); Sebastian 
 Schemm (University of Cambridge); Benedikt Soja (ETH Zurich); and Mathieu 
 Salzmann (Swiss data science center)\n---------------------\nClimate in a 
 Bottle: Towards a foundation model for climate\n\nAI emulators offer a pat
 h to compressing, boosting limited ensembles, and improving the latency of
  interacting with petabyte-scale climate prediction data. However, prevail
 ing auto-regressive paradigms offer limited flexibility, and are challengi
 ng to train on climate time horizons due to drifts, in...\n\n\nKarthik Kas
 hinath (NVIDIA Inc.)\n---------------------\nWeatherGenerator: A Foundatio
 n Model for Weather and Climate\n\nThe WeatherGenerator project aims to de
 velop a foundation model for the European community that combines a wide v
 ariety of datasets to improve a broad range of applications across spatial
  and temporal scales. The WeatherGenerator model is a highly multimodal tr
 ansformer capable of ingesting and pred...\n\n\nJulian Kuehnert (ECMWF)\n-
 --------------------\nPanel Discussion Foundation model for weather and cl
 imate\n\nThe panel discussion will explore the challenges and opportunitie
 s of using foundation models for weather and climate.\n\n\nXavier Lapillon
 ne (MeteoSwiss)\n\nDomain: Climate, Weather, and Earth Sciences\n\nSession
  Chairs: Xavier Lapillonne (MeteoSwiss); Ilaria Luise (CERN); and Sebastia
 n Schemm (Cambridge University, UK)
END:VEVENT
END:VCALENDAR