BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210402T160045Z
LOCATION:Track 2
DTSTART;TZID=America/New_York:20201117T103000
DTEND;TZID=America/New_York:20201117T110000
UID:submissions.supercomputing.org_SC20_sess179_pap485@linklings.com
SUMMARY:Recurrent Neural Network Architecture Search for Geophysical Emula
 tion
DESCRIPTION:Paper\n\nRecurrent Neural Network Architecture Search for Geop
 hysical Emulation\n\nMaulik, Egele, Lusch, Balaprakash\n\nDeveloping surro
 gate geophysical models from data is a key research topic in atmospheric a
 nd oceanic modeling because of the large computational costs associated wi
 th numerical simulation methods. Researchers have started applying a wide 
 range of machine learning models, in particular neural networks, to geophy
 sical data for forecasting without these constraints. Constructing neural 
 networks, however, for forecasting such data is nontrivial and often requi
 res trial and error. To that end, we focus on developing proper-orthogonal
 -decomposition-based long short-term memory networks (POD-LSTMs). We devel
 op a scalable neural architecture search for generating stacked LSTMs to f
 orecast temperature in the NOAA Optimum Interpolation Sea-Surface Temperat
 ure data set. Our approach identifies POD-LSTMs that are superior to manua
 lly designed variants and baseline time-series prediction methods. We also
  assess the scalability of different architecture search strategies on up 
 to 512 Intel Knights Landing nodes of the Theta supercomputer at the Argon
 ne Leadership Computing Facility.\n\nTag: Applications, Machine Learning, 
 Deep Learning and Artificial Intelligence, Parallel Programming Languages,
  Libraries, and Models\n\nRegistration Category: Tech Program Reg Pass
END:VEVENT
END:VCALENDAR