BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:6th Summer School on Theory\, Mechanisms and Hierarchical Modellin
 g of Climate Dynamics: Artificial Intelligence and Climate Modelling | (sm
 r 4067)
DTSTART;VALUE=DATE-TIME:20250505T060000Z
DTEND;VALUE=DATE-TIME:20250516T200000Z
DTSTAMP;VALUE=DATE-TIME:20260611T042140Z
UID:indico-event-10832@ictp.it
DESCRIPTION:An ICTP Hybrid meeting\n	Applications of ML/AI to weather and 
 climate modelling have experienced an exponential growth. Weather forecast
 s based on AI models trained on re-analysis data are now possible with for
 ecasting skills comparable to those of physical numerical models.\n\n	 \n
 \n	However\, to what extent the AI approach can be extended to longer time
  scales is a research topic of increasing importance. At the same time\, t
 raditional atmospheric and ocean models based on numerical solutions of PD
 Es have increased their resolution to a few kilometers\, which makes their
  application on climate time scale very challenging. In order to test the 
 validity of these methodologies on climate time scales in a statistically 
 sound way\, experiments on several multi-decadal simulations are required.
  In this context\, intermediate-complexity climate models provide convenie
 nt 'numerical laboratories'. The goal of this workshop is to present state
 -of-the-art applications of AI/ML\, advanced numerical methods and innovat
 ive hardware/software solutions tested on intermediate-complexity models\,
  such as the SPEEDY global model developed at ICTP. The workshop will also
  review the state-of-the-art of AI development.\n\n	 \n\n	Topics: \n\n		
 General introduction to AI/ML techniques\n	\n		Review of state-of-the art 
 of AI developments in global and regional Weather and Climate Modelling\n	
 \n		AI/ML applications in Climate Modelling\n	\n		Can AI be used to genera
 te larger ensembles from physical simulations with just few members?\n	\n	
 	Uncertaincy estimation from numerical models and AI\n	\n		Can AI replace 
 physical numerical models on sub-seasonal to multi-decadal time scales for
  climate applications?\n	\n		AI for physical parametezations: parameter ca
 libration or full-AI modules?\n	\n		AI models and convection-peremitting p
 hysical models: Complementary or contradictory?\n	\n		Testing AI methods i
 n an intermediate complexity modelling framework\n\n	Speakers and Panelist
 s include:\n\n	Tom Beucler\, University of Lausanne\, Switzerland\n\n	\n		
 Matthew Chantry\, ECMWF\, UK\n		Erika Coppola\, ICTP\, Italy\n	\n		Alban F
 archi\, ECMWF\, UK\n		Pierre Gentine\, Columbia University\, USA\n		Grazia
 no Giuliani\, ICTP\, Italy\n		Scott Martin\, University of Washington\, US
 A\n	Shruti Nath\, University of Oxford\, UK\n\n	Tim Palmer\, University of
  Oxford\, UK\n	Erik van Sebille\, Utrecht University\, Netherlands\n	Jakob
  Schloer\, ECMWF\, UK\n\n	 \n\n	Research abstracts: In the application f
 orm\, all applicants are requested to submit a brief research abstract for
  a poster presentation and/or contributed talk. A limited number of abstra
 cts will be selected for the poster session or to give a talk. Please use 
 ICTP templates available for download here and below under 'Material'.\n\
 n	Grants: A limited number of grants are available to support the attendan
 ce of selected participants\, with priority given to participants from dev
 eloping countries. There is no registration fee.\n\n//indico.ictp.it/event
 /10832/
LOCATION:ICTP Kastler Lecture Hall (AGH)
URL://indico.ictp.it/event/10832/
END:VEVENT
END:VCALENDAR