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:20260421T090512Z
LOCATION:Bldg. 6 - Room 103
DTSTART;TZID=Europe/Stockholm:20260701T143000
DTEND;TZID=Europe/Stockholm:20260701T150000
UID:submissions.pasc-conference.org_PASC26_sess162_msa183@linklings.com
SUMMARY:Earth System Foundation Model - heterogeneous data integration and
  forecasting
DESCRIPTION:Firat Ozdemir, Yun Cheng, and Salman Mohebi (Swiss data scienc
 e center); Fanny Lehmann, Simon Adamov, Langwen Huang, Leonardo Trentini, 
 Oliver Fuhrer, Torsten Hoelfer, and Siddhartha Mishra (ETH Zurich); Sebast
 ian Schemm (University of Cambridge); Benedikt Soja (ETH Zurich); and Math
 ieu Salzmann (Swiss data science center)\n\nThe talk introduces the Earth 
 System Foundation Model (ESFM), a fully open foundation model tailored for
  weather and climate modeling tasks. Built upon the Swin Transformer backb
 one of the pioneering Aurora model, ESFM introduces several key extensions
  that allow it to process diverse and heterogeneous datasets under a singl
 e unified framework. Its variable encoding scheme and training protocols a
 llow the model to natively handle missing values across all spatio-tempora
 l dimensions, processing everything from dense gridded data (like ERA5 and
  CMIP) to sparse gridded satellite data (MODIS) and non-gridded station da
 ta. Key architectural features include the use of axial attention to captu
 re inter-variable dependencies, and individual variable tokenization which
  allows for variable shuffling during training and simplifies the developm
 ent of new downstream tasks. Furthermore, ESFM employs a simple and cost e
 ffective means to convert the deterministic model into a probabilistic one
 . Overall, ESFM retains the key strengths and long-term stability of Auror
 a while significantly broadening its functionality, which is demonstrated 
 through empirical evaluations and case studies.\n\nDomain: Climate, Weathe
 r, and Earth Sciences\n\nSession Chairs: Xavier Lapillonne (MeteoSwiss); I
 laria Luise (CERN); and Sebastian Schemm (Cambridge University, UK)\n\n
END:VEVENT
END:VCALENDAR