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:20260422T000629Z
LOCATION:405-406-407
DTSTART;TZID=America/Denver:20231116T133000
DTEND;TZID=America/Denver:20231116T150000
UID:submissions.supercomputing.org_SC23_sess175@linklings.com
SUMMARY:Applications of Machine Learning
DESCRIPTION:Rapid Simulations of Atmospheric Data Assimilation of Hourly-S
 cale Phenomena with Modern Neural Networks\n\nAtmospheric data assimilatio
 n is essential for numerical weather prediction. Ensemble-based data assim
 ilation connects multiple instances of atmospheric model through Kalman-fi
 lter-based algorithm, which is regarded as a challenging computing task to
 day. In this work, we present our efforts to build...\n\n\nYiyuan Li, Xiti
 ng Ju, Yi Xiao, Qilong Jia, and Yongxiao Zhou (Tsinghua University, China)
 ; Simeng Qian (National Supercomputing Center in Wuxi); Rongfen Lin (Natio
 nal Research Center of Parallel Computer Engineering and Technology, China
 ); Bin Yang (Tsinghua University, China); Shupeng Shi (National Supercompu
 ting Center in Wuxi); Xin Liu, Jie Gao, Zhen Wang, Sha Liu, Jian Tan, and 
 Xuan Wang (National Research Center of Parallel Computer Engineering and T
 echnology, China); Zhengding Hu (University of Science and Technology of C
 hina); Limin Yan (Beijing Sankuai Online Technology Co, Ltd; National Supe
 rcomputing Center in Wuxi); and Wei Xue (Tsinghua University, China; Depar
 tment of Computer Technology and Application, Qinghai University)\n-------
 --------------\nFORGE: Pre-Training Open Foundation Models for Science\n\n
 Large language models (LLMs) are poised to revolutionize the way we conduc
 t scientific research, yet their complexity and cost hinder adoption by th
 e wider science community. Identifying suitable scientific use cases, opti
 mizing model and data sizes, and scaling up training are among the most pr
 essi...\n\n\nJunqi Yin, Sajal Dash, Feiyi Wang, and Mallikarjun Shankar (O
 ak Ridge National Laboratory (ORNL))\n---------------------\nBreaking Boun
 daries: Distributed Domain Decomposition with Scalable Physics-Informed Ne
 ural PDE Solvers\n\nMosaic Flow is a novel domain decomposition method des
 igned to scale physics-informed neural PDE solvers to large domains. Its u
 nique approach leverages pre-trained networks on small domains to solve pa
 rtial differential equations on large domains purely through inference, re
 sulting in high reusabil...\n\n\nArthur Feeney, Zitong Li, Ramin Bostanaba
 d, and Aparna Chandramowlishwaran (University of California, Irvine)\n\nTa
 g: Artificial Intelligence/Machine Learning, Applications, Modeling and Si
 mulation, State of the Practice\n\nRegistration Category: Tech Program Reg
  Pass\n\nSession Chair: Wei Xu (Brookhaven National Laboratory)
END:VEVENT
END:VCALENDAR