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:20260422T000713Z
LOCATION:607
DTSTART;TZID=America/Denver:20231112T094000
DTEND;TZID=America/Denver:20231112T100000
UID:submissions.supercomputing.org_SC23_sess415_ws_esp103@linklings.com
SUMMARY:Efficient Probabilistic Tuning of Ensemble Forecasting Method
DESCRIPTION:Alessandro Fanfarillo and Nicholas Malaya (Advanced Micro Devi
 ces (AMD) Inc), Guido Cervone (Pennsylvania State University), and Luca De
 lle Monache (Scripps Research Institute)\n\nEnsemble forecasting technique
 s are gaining popularity in the weather and renewable energy communities, 
 thanks to their ability to produce accurate predictions and at the same ti
 me to provide a measure of the uncertainty in the forecast. Analog Ensembl
 e techniques are a class of computationally efficient ensemble forecasting
  methods that predict future weather events based on historical similar ca
 ses (i.e., analogs). The definition of "similar" is dependent on the type 
 of predictors used for searching in the historical dataset, and on how rel
 evant they are to identify a similar weather event happened in the past. F
 or a given geographical location, the relevancy of a predictor in identify
 ing good analogs requires a long tuning process usually performed via brut
 e-force. In this work, we provide several probabilistic alternatives to th
 e tuning process, based on the dataset size, computational cost of a singl
 e evaluation, and number of predictors.\n\nTag: Performance Optimization\n
 \nRegistration Category: Workshop Reg Pass\n\nSession Chairs: Tiernan Case
 y (Sandia National Laboratories) and Antigoni Georgiadou (Oak Ridge Nation
 al Laboratory (ORNL))\n\n
END:VEVENT
END:VCALENDAR