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:20241120T082410Z
LOCATION:HG F 1
DTSTART;TZID=Europe/Stockholm:20240603T170000
DTEND;TZID=Europe/Stockholm:20240603T173000
UID:submissions.pasc-conference.org_PASC24_sess173_pap112@linklings.com
SUMMARY:Parametric Sensitivities of a Wind-driven Baroclinic Ocean Using N
 eural Surrogates
DESCRIPTION:Paper\n\nYixuan Sun (Argonne National Laboratory), Elizabeth C
 ucuzzella (Tufts University), Steven Brus and Sri Hari Krishna Narayanan (
 Argonne National Laboratory), Balasubramanya Nadiga and Luke Van Roekel (L
 os Alamos National Laboratory), Jan Hückelheim and Sandeep Madireddy (Argo
 nne National Laboratory), and Patrick Heimbach (University of Texas at Aus
 tin)\n\nNumerical models of the ocean and ice sheets are crucial for under
 standing and simulating the impact of greenhouse gases on the global clima
 te. Oceanic processes affect phenomena such as hurricanes, extreme precipi
 tation, and droughts. Ocean models rely on subgrid-scale parameterizations
  that require calibration and often significantly affect model skill. When
  model sensitivities to parameters can be computed by using approaches suc
 h as automatic differentiation, they can be used for such calibration towa
 rd reducing the misfit between model output and data. Because the SOMA mod
 el code is challenging to differentiate, we have created\nneural network-b
 ased surrogates for estimating the sensitivity of the ocean model to model
  parameters. We first generated perturbed parameter ensemble data for an i
 dealized ocean model and trained three surrogate neural network models. Th
 e neural surrogates accurately predicted the one-step forward ocean dynami
 cs, of which we then computed the parametric sensitivity.\n\nDomain: Clima
 te, Weather, and Earth Sciences\n\nSession Chair: Thorsten Kurth (NVIDIA I
 nc.)
END:VEVENT
END:VCALENDAR