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:20210402T160559Z
LOCATION:Track 11
DTSTART;TZID=America/New_York:20201113T100000
DTEND;TZID=America/New_York:20201113T140000
UID:submissions.supercomputing.org_SC20_sess229@linklings.com
SUMMARY:AI4S: Workshop on Artificial Intelligence and Machine Learning for
  Scientific Applications
DESCRIPTION:Workshop\n\nAI4S – Panel\n\n\n\n---------------------\nAI4S – 
 Introduction: Workshop on Artificial Intelligence and Machine Learning for
  Scientific Applications\n\nKestor, Li\n\nArtificial intelligence (AI)/mac
 hine learning (ML) is a game-changing technology that has shown tremendous
  advantages and improvements in algorithms, implementation and application
 s. We have seen many successful implementations of AI/ML to scientific app
 lications. There are, however, a number of pro...\n\n---------------------
 \nAI4S – Keynote\n\nLee\n\n---------------------\nAutomatic Particle Traje
 ctory Classification in Plasma Simulations\n\nMarkidis, Peng, Podobas, Jon
 gsuebchoke, Bengtsson...\n\nNumerical simulations of plasma flows are cruc
 ial for advancing our understanding of microscopic processes that drive th
 e global plasma dynamics in fusion devices, space, and astrophysical syste
 ms. Identifying and classifying particle trajectories allows us to determi
 ne specific on-going acceleratio...\n\n---------------------\nHow Good Is 
 Your Scientific Data Generative Model?\n\nYang, Gremillion, Zhang, Lin, Wo
 hlberg\n\nNowadays, leveraging data augmentation methods on helping resolv
 ing scientific problems becomes prevailing. And many scientific problems b
 enefit from data augmentation methods build with deep generative models. Y
 et due to the complexity of the scientific data, commonly used evaluation 
 methods of gen...\n\n---------------------\nDeep Learning-Based Low-Dose T
 omography Reconstruction with Hybrid-Dose Measurements\n\nWu, Bicer, Liu, 
 Andrade, Zhu...\n\nSynchrotron-based X-ray computed tomography is widely u
 sed for investigating inner structures of specimens at high spatial resolu
 tions. However, potential beam damage to samples often limits the X-ray ex
 posure during tomography experiments. Proposed strategies for eliminating 
 beam damage also decrea...\n\n---------------------\nReinforcement Learnin
 g-Based Solution to Power Grid Planning and Operation Under Uncertainties\
 n\nShang, Ye, Zhang, Yang, Xu...\n\nWith the ever-increasing stochastic an
 d dynamic behavior observed in today’s bulk power systems, securely and ec
 onomically planning future operational scenarios that meet all reliability
  standards under uncertainties becomes a challenging computational task, w
 hich typically involves searching feasib...\n\n---------------------\nPred
 ictions of Steady and Unsteady Flows Using Machine-Learned Surrogate Model
 s\n\nBhushan\n\nThe research focuses on investigation of the ability of ne
 ural networks to learn correlation between desired modeling variables and 
 flow parameters, thereby providing a surrogate model that can used in comp
 utational fluid dynamics (CFD) simulations. Investigation is performed for
  two different class...\n\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR