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:20220812T074334Z
LOCATION:Foyer 2nd Floor
DTSTART;TZID=Europe/Stockholm:20220628T090000
DTEND;TZID=Europe/Stockholm:20220628T110000
UID:submissions.pasc-conference.org_PASC22_sess181_pos126@linklings.com
SUMMARY:P15 - Building a Physics-Constrained, Fast and Stable Machine Lear
 ning-Based Radiation Emulator
DESCRIPTION:Poster\n\nP15 - Building a Physics-Constrained, Fast and Stabl
 e Machine Learning-Based Radiation Emulator\n\nBertoli, Schemm, Ozdemir, S
 zékely, Perez-Cruz\n\nIn climate models, the transfer of radiation is appr
 oximated by parameterizations. The current operational radiative transfer 
 solver in the Icosahedral Nonhydrostatic Weather and Climate Model (ICON) 
 is ecRad. It is an accurate radiation parameterization but remains computa
 tionally expensive. Therefore, the radiation solver is only run on a reduc
 ed spatial grid, which can affect prediction accuracy. In this project, we
  are trying to develop a radiative transfer solver improved by machine lea
 rning to speed up the computation without loss of accuracy. Our research f
 ocuses on two methods: random forests and physics-informed neural networks
 . We continue to call ecRad at constant though significantly reduced time 
 intervals and on a reduced spatial grid thereby using it as a regularizer 
 while reducing computation costs. The underlying idea is to avoid unphysic
 al climate drifts and to support the generalization capabilities of the ML
  method.
END:VEVENT
END:VCALENDAR