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:20250822T115807Z
LOCATION:Room 5.2D02
DTSTART;TZID=Europe/Stockholm:20250617T113000
DTEND;TZID=Europe/Stockholm:20250617T133000
UID:submissions.pasc-conference.org_PASC25_sess134@linklings.com
SUMMARY:MS3F - Accelerating Sustainable Development through Coupled HPC Si
 mulations and AI
DESCRIPTION:High-performance computing (HPC) has a long history of driving
  scientific discovery through advances in hardware and numerical algorithm
 s, but the adoption of artificial intelligence (AI) and machine learning (
 ML) is transforming this landscape. By integrating traditional simulations
  with AI/ML training and inference tasks into complex workflows, computati
 onal scientists are unlocking new HPC applications, from AI-driven design 
 and optimization to online model fine-tuning and learning of dynamical sys
 tems, and revolutionizing how we tackle many of the UN’s sustainable devel
 opment goals. However, building and efficiently deploying large-scale coup
 led workflows on HPC systems still poses significant software and hardware
  challenges, including managing massive datasets on distributed systems, m
 aking efficient use of the interconnect and local memory to avoid I/O bott
 lenecks, and ensuring reproducibility and provenance. In this minisymposiu
 m, speakers from leading hardware vendors, HPC centers, and universities s
 hare the latest software innovations, new learning methodologies developed
 , and successful practices adopted to address the issues faced by coupled 
 simulation and AI workflows on modern HPC systems. Through applications in
  fields such as drug discovery and climate modeling, the talks will discus
 s lessons learned and the remaining challenges in adopting large-scale cou
 pled workflows for scientific discovery in the exascale era of supercomput
 ing.\n\nRAIN: Reinforcement Algorithms for Improving Numerical Weather and
  Climate Models\n\nThis study explores integrating reinforcement learning 
 (RL) with idealised climate models to address key parameterisation challen
 ges in climate science. Current climate models rely on complex mathematica
 l parameterisations to represent sub-grid scale processes, which can intro
 duce substantial uncert...\n\n\nPritthijit Nath, Henry Moss, and Emily Shu
 ckburgh (University of Cambridge) and Mark Webb (Met Office)\n------------
 ---------\nFive Years of SmartSim: The Fast Evolution of AI-Enhanced HPC W
 orkflows\n\nWhen SmartSim was first released in 2020, the intention was th
 at of supporting workflows where large numerical software needed an ML boo
 st. The ML models involved were small, fitting onto one single GPU, and co
 uld be easily re-trained and replaced at run-time. Nowadays, ML models are
  huge, spanning ...\n\n\nAlessandro Rigazzi and Andrew Shao (HPE)\n-------
 --------------\nSustainable, Trustworthy Coupled HPC+AI for Molecular Simu
 lation and Materials Design: Energy Consumption, Correctness, and Efficien
 t Training on Leadership Platforms\n\nThe promise of accelerating and adva
 ncing molecular simulation and materials design efforts with coupled HPC a
 nd deep learning (DL) workflows has motivated an explosion in a variety of
  approaches. In particular, leadership computing facilities have supported
  a diverse set of large-scale efforts in t...\n\n\nAda Sedova (Oak Ridge N
 ational Laboratory)\n---------------------\nMLDocking: Accelerated Drug Di
 scovery with Transformer-Based Surrogate Models and In-Memory Workflows on
  Heterogeneous HPC Systems\n\nThe use of AI in drug discovery workflows ha
 s accelerated the task of screening billions of molecules to identify top 
 candidates for binding to particular proteins. Typically, these workflows 
 are composed of distinct tasks run sequentially on HPC clusters to iterati
 vely screen through the list of co...\n\n\nRiccardo Balin, Christine Simps
 on, Harikrishna Tummalapalli, Archit Vasan, and Venkat Vishwanath (Argonne
  National Laboratory) and Kent Lee, Yian Chen, Nick Hill, Colin Wahl, and 
 Pete Mendygral (HPE)\n\nDomain: Chemistry and Materials, Climate, Weather,
  and Earth Sciences, Computational Methods and Applied Mathematics\n\nSess
 ion Chairs: Riccardo Balin (Argonne National Laboratory) and Alessandro Ri
 gazzi (HPE)
END:VEVENT
END:VCALENDAR