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:20240603T123000
DTEND;TZID=Europe/Stockholm:20240603T130000
UID:submissions.pasc-conference.org_PASC24_sess163_msa202@linklings.com
SUMMARY:Accelerating Materials Modelling with Machine Learning: Challenges
  and Opportunities
DESCRIPTION:Minisymposium\n\nHossein Ehteshami and Scott Donaldson (Univer
 sity of York), Tamas Stenczel (University of Cambridge), and Phil Hasnip (
 University of York)\n\nFirst-principles materials modelling software can a
 ccurately predict many materials properties, but requires the numerical so
 lution of complex, non-linear partial differential equations. Solving thes
 e equations is computationally intensive, and first-principles simulations
  consume a significant fraction of HPC usage (e.g. ~40% of the UK ARCHER2 
 Tier-1 facility). In recent years, machine learning (ML) methods have been
  applied to some of these property simulations, to reduce the number of nu
 merical evaluations. The vast materials parameter space means that devisin
 g a "universal" ML model is challenging. One promising alternative is to c
 ouple the ML and direct numerical simulations more tightly, training and u
 sing the ML "on-the-fly". We will discuss these challenges and opportuniti
 es, along with results from embedding Gaussian Process-based ML models in 
 the popular CASTEP first-principles modelling software, to reproduce and p
 redict atomic forces substantially faster and with controllable uncertaint
 y.\n\nDomain: Chemistry and Materials, Climate, Weather, and Earth Science
 s, Engineering, Physics, Computational Methods and Applied Mathematics\n\n
 Session Chair: Jack Atkinson (University of Cambridge)
END:VEVENT
END:VCALENDAR