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:20250822T115807Z
LOCATION:Room 5.0B15 & 16
DTSTART;TZID=Europe/Stockholm:20250616T112000
DTEND;TZID=Europe/Stockholm:20250616T132000
UID:submissions.pasc-conference.org_PASC25_sess139@linklings.com
SUMMARY:MS1B - Advances in Foundation Models for Weather and Climate
DESCRIPTION:In this minisymposium, we will survey the state-of-the-art of 
 foundation models for weather and climate. These promise a second revoluti
 on for Earth system modeling, after the emergence of highly skilful machin
 e learning-based weather forecasting models in the last two years. Foundat
 ion models aim to provide a machine learning-based, rich representation of
  the Earth system at many scales in space and time through training on man
 y different datasets. With this, they can be used for a wide range of task
 , not unlike conventional, equation-based Earth system models. The first l
 arge foundation models are becoming available now and their applicability 
 to a range of tasks is explored. The three talks in the minisymposium cove
 r both model development as well as the application and the physicality of
  the output and will provide a comprehensive overview of the state of the 
 field. In the panel discussion at the end of the minisymposium, the paneli
 sts will share their insights about the state of the field and where it wi
 ll be developing to in the future. The panel also provides the audience wi
 th the opportunity to engage with the panelists and to share their experie
 nces and opinions.\n\nPanel Discussion\n\nThis session will be an open dis
 cussion on developments and future directions. Machine learning for Earth 
 system modeling is a highly dynamic field and this format will allow the p
 anelists to also share the latest, yet-unpublished developments and to put
  these into the context of the overall state o...\n\n\nIlaria Luise (ECMWF
 , CERN)\n---------------------\nAdvancing Probabilistic Weather Forecast t
 hrough Machine Learning at Scale\n\nWe present recent advancements in glob
 al weather modeling based on spherical neural operators. This innovative a
 pproach demonstrates superior skill and reduced computational costs compar
 ed to current state-of-the-art models. Our model is trained as a probabili
 stic ensemble, respecting spherical geom...\n\n\nBoris Bonev, Thorsten Kur
 th, and Mauro Bisson (NVIDIA); Ankur Mahesh (Lawrence Berkeley National La
 boratory); Kamyar Azizzadeneshli and Karthik Kashinath (NVIDIA); Michael S
 . Pritchard (NVIDIA; University of California, Irvine); William D. Collins
  (Lawrence Berkeley National Laboratory); and Anima Anandkumar (California
  Institute of Technology)\n---------------------\nFrugal Extension of Auro
 ra Weather Foundation Model: Applications to the Water Cycle\n\nFoundation
  models have achieved remarkable accuracy in short- to medium-range weathe
 r forecasts, primarily focusing on atmospheric variables. However, predict
 ing new physical variables typically requires training or fine-tuning the 
 model with additional datasets, incurring significant costs. We show...\n\
 n\nFanny Lehmann, Torsten Hoefler, Siddhartha Mishra, Sebastian Schemm, an
 d Benedikt Soja (ETH Zurich)\n---------------------\nCan AI-Based Numerica
 l Weather Prediction Models Help us to Understand Future Climate?\n\nAI-dr
 iven Numerical Weather Prediction (AI-NWP) models, trained on the ERA5 rea
 nalysis are currently our best representation of historical day-to-day wea
 ther evolution. They have demonstrated significant skill in forecasting pr
 esent-day weather, outperforming traditional physics-based forecasting sy.
 ..\n\n\nNikolay Koldunov (Alfred Wegener Institute), Thomas Rackow (ECMWF)
 , and Amal John (Alfred Wegener Institute)\n\nDomain: Climate, Weather, an
 d Earth Sciences, Computational Methods and Applied Mathematics\n\nSession
  Chairs: Christian Lessig (ECMWF, Otto-von-Guericke-Universitat Magdeburg)
  and Ilaria Luise (CERN)
END:VEVENT
END:VCALENDAR