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:20240603T113000
DTEND;TZID=Europe/Stockholm:20240603T133000
UID:submissions.pasc-conference.org_PASC24_sess108@linklings.com
SUMMARY:MS1A - Foundation Models in Earth System Science
DESCRIPTION:Minisymposium\n\nFoundation models represent a new class of ar
 tificial intelligence models designed to encapsulate information from larg
 e amounts of data. The most prominent example are large language models, w
 hich have achieved significant breakthroughs in various applications, incl
 uding natural language processing (NLP), text generation, and machine tran
 slation. Some prominent examples of foundation models include GPT models, 
 BERT, PalmX and their derivatives. This workshop will explore the untapped
  potential of foundation models in Earth system science, bringing together
  three different perspectives. First, we will introduce AtmoRep, a foundat
 ion model for the atmosphere released by a multidisciplinary collaboration
  between Magdeburg University, CERN and JSC. After that, we will move the 
 discussion to the industry perspective, with Dr. Johannes Jakubik from IBM
 . In particular, Dr. Jakubik will present the Prithvi model for Earth Obse
 rvations data, developed in collaboration with NASA. After that, Troy Arco
 mano from Argonne National Laboratory will present two different models: C
 limaX, released in collaboration with Microsoft, and Stromer. The last par
 t of the workshop will be an interactive discussion with the audience on t
 he role of foundation models in fundamental science. It will be the occasi
 on for the community to brainstorm around the future and the potential of 
 these new technologies.\n\nEvaluation of a Foundation Model Approach for W
 eather and Climate\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 foreca
 st models, researchers have begun to create foundation models for the Eart
 h System. There several fo...\n\n\nTroy Arcomano (Argonne National Laborat
 ory), Alex Wikner (University of Chicago), Tung Nguyen (UCLA), Romit Mauli
 k (University of Pennsylvania), Sandeep Madireddy (Argonne National Labora
 tory), Aditya Grover (UCLA), and Rao Kotamarthi (Argonne National Laborato
 ry)\n---------------------\nAtmoRep: A Probabilistic Multi-Purpose Model f
 or Atmospheric Dynamics\n\nAtmoRep is a first example of probabilistic mul
 ti-purpose model that extends the concept of representation learning to Ea
 rth system science, and in particular to atmospheric dynamics. Starting fr
 om a single pre-trained architecture used as a backbone, AtmoRep is able t
 o achieve skilful results in mu...\n\n\nChristian Lessig (ECMWF, Otto-von-
 Guericke-Universitat Magdeburg) and Ilaria Luise (CERN)\n-----------------
 ----\nFoundation Models in Earth Science and Remote Sensing\n\nSignificant
  progress in the development of highly adaptable and reusable Artificial I
 ntelligence (AI) models is expected to have a significant impact on Earth 
 science and remote sensing. Foundation Models (FMs), AI models designed to
  replace task-specific models, are increasingly being recognized fo...\n\n
 \nJohannes Jakubik (IBM Research)\n---------------------\nDiscussion Panel
 : Future Perspectives\n\nThe last part of the workshop will be an interact
 ive discussion on the following open questions: “Where foundation models c
 ould be useful in Earth system science?”, “What would be the advantages an
 d limitations of foundation models in Earth system science?” and “Can we .
 ..\n\n\nChristian Lessig (ECMWF, Otto-von-Guericke-Universitat Magdeburg) 
 and Ilaria Luise (CERN)\n\nDomain: Climate, Weather, and Earth Sciences, C
 omputational Methods and Applied Mathematics\n\nSession Chair: Christian L
 essig (ECMWF, Otto-von-Guericke-Universitat Magdeburg)
END:VEVENT
END:VCALENDAR