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:20241120T082408Z
LOCATION:HG E 3
DTSTART;TZID=Europe/Stockholm:20240603T113000
DTEND;TZID=Europe/Stockholm:20240603T133000
UID:submissions.pasc-conference.org_PASC24_sess163@linklings.com
SUMMARY:MS1E - Interfacing Machine Learning with Physics-Based Models
DESCRIPTION:Minisymposium\n\nMany fields of science make use of large nume
 rical models. Advances in artificial intelligence (AI) and machine learnin
 g (ML) have opened many new approaches, with modellers increasingly seekin
 g to enhance simulations by combining traditional approaches with ML/AI to
  form hybrid models. Examples of such approaches include ML emulation of c
 omputationally intensive processes and data-driven parameterisations of su
 b-grid processes. Successfully blending these approaches presents several 
 challenges requiring expertise from multiple areas: AI, domain science, an
 d numerical modelling through to research software and high performance co
 mputing. Whilst hybrid modelling has recently become an extremely active a
 rea in Earth sciences, the approach and challenges are in no way specific 
 to this domain. Progress is also underway in materials, fluid mechanics an
 d engineering, plasma physics, and chemistry amongst other fields. This in
 terdisciplinary session on hybrid modelling aims to allow scientific model
 lers to share techniques and breakthroughs in a cross-domain forum. We wil
 l hear from both academia and industry about the tools being developed and
  techniques being used to push forward on a range of fronts across multipl
 e fields. This will be followed by a discussion session in which attendees
  are invited to share their own challenges and successes with others.\n\nA
 ccelerating Materials Modelling with Machine Learning: Challenges and Oppo
 rtunities\n\nFirst-principles materials modelling software can accurately 
 predict many materials properties, but requires the numerical solution of 
 complex, non-linear partial differential equations. Solving these equation
 s is computationally intensive, and first-principles simulations consume a
  significant frac...\n\n\nHossein Ehteshami and Scott Donaldson (Universit
 y of York), Tamas Stenczel (University of Cambridge), and Phil Hasnip (Uni
 versity of York)\n---------------------\nCoupling Machine Learning to Nume
 rical (Climate) Models: Tools, Challenges, and Lessons Learned\n\nThe rise
  of machine learning (ML) has seen many scientists seeking to incorporate 
 these techniques into numerical models. Doing so presents a number of chal
 lenges, however. The Institute of Computing for Climate Science (ICCS) has
  explored this problem in the context of coupling ML components/parame...\
 n\n\nJack Atkinson (University of Cambridge)\n---------------------\nInter
 facing Machine Learning with Physics-Based Models - Discussion\n\nWith the
  recent rise of machine (ML) and deep learning there have been several eff
 orts to incorporate these techniques into numerical models. Doing so prese
 nts a number of challenges however, including but not limited to: framewor
 k and language interoperation; ensuring physical compatibility, stabil...\
 n\n\nJack Atkinson (University of Cambridge) and Phil Hasnip (University o
 f York)\n---------------------\nSmartSim: Success Stories and Future Chall
 enges\n\nSmartSim has always been developed with the goal of overcoming th
 e divide between standard HPC numerical libraries and AI toolkits. SmartSi
 m’s philosophy is based on loose coupling of different applications and pr
 ocessing units involved in a workflow and it is one of the main reasons fo
 r its g...\n\n\nAlessandro Rigazzi and Andrew Shao (HPE)\n\nDomain: Chemis
 try and Materials, Climate, Weather, and Earth Sciences, Engineering, Phys
 ics, Computational Methods and Applied Mathematics\n\nSession Chair: Jack 
 Atkinson (University of Cambridge)
END:VEVENT
END:VCALENDAR