BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230124T171524Z
LOCATION:C1-2-3
DTSTART;TZID=America/Chicago:20221117T083000
DTEND;TZID=America/Chicago:20221117T170000
UID:submissions.supercomputing.org_SC22_sess275_rpost123@linklings.com
SUMMARY:Artificial Intelligence Reconstructs Missing Climate Information
DESCRIPTION:Posters, Research Posters\n\nArtificial Intelligence Reconstru
 cts Missing Climate Information\n\nKadow, Plésiat, Meuer, Hall, Ulbrich...
 \n\nHistorical temperature measurements are the basis of important global 
 climate datasets like HadCRUT4 and HadCRUT5 to analyze climate change. The
 se datasets contain many missing values and have low resolution grids. Her
 e we demonstrate that artificial intelligence can skillfully fill these ob
 servational gaps and upscale these when combined with numerical climate mo
 del data. We show that recently developed image inpainting techniques perf
 orm accurate reconstructions via transfer learning. In addition, high reso
 lution in weather and climate was always a common and ongoing goal of the 
 community. We gain a neural network which reconstructs and downscales the 
 important observational data sets (IPCC AR6) at the same time, which is un
 ique and state-of-the-art in climate research.\n\nRegistration Category: T
 ech Program Reg Pass, Exhibits Reg Pass
END:VEVENT
END:VCALENDAR