BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240116T191658Z
LOCATION:DEF Concourse
DTSTART;TZID=America/Denver:20231114T100000
DTEND;TZID=America/Denver:20231114T170000
UID:submissions.supercomputing.org_SC23_sess291_rpost105@linklings.com
SUMMARY:HPC Accelerated Generative Deep Learning Approach for Creating Dig
 ital Twins of Climate Models
DESCRIPTION:Posters, Research Posters\n\nJohannes Meuer, Christopher Kadow
 , and Thomas Ludwig (German Climate Computing Centre (DKRZ)) and Claudia T
 immreck (Max Planck Institute for Meteorology)\n\nClimate models cannot pe
 rfectly represent the complex climate system, but by running them multiple
  times with small variations in input parameters, it's possible to estimat
 e uncertainties and explore different climate scenarios. Generating these 
 ensembles demands significant computational resources and time, which can 
 be crucial for risk assessments and decision-making. This study utilizes g
 enerative adversarial networks (GANs) and deep diffusion models (DDMs) to 
 produce low-resolution ensemble runs trained on data provided by climate m
 odel simulations with low computational expense. Additionally, convolution
 al neural networks (CNNs) are employed for downscaling as well as parallel
 ization techniques to enhance performance and reduce computation time. Thi
 s approach allows for time-efficient exploration of high-resolution ensemb
 le members, facilitating climate modeling investigations that were previou
 sly challenging due to resource constraints.\n\nRegistration Category: Tec
 h Program Reg Pass, Exhibits Reg Pass
END:VEVENT
END:VCALENDAR