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:20210916T132454Z
LOCATION:Michel Mayor
DTSTART;TZID=Europe/Stockholm:20210708T173000
DTEND;TZID=Europe/Stockholm:20210708T180000
UID:submissions.pasc-conference.org_PASC21_sess167_msa362@linklings.com
SUMMARY:Integrated Machine-Learning Schemes for Atomic-Scale Materials Mod
 eling
DESCRIPTION:Minisymposium\n\nIntegrated Machine-Learning Schemes for Atomi
 c-Scale Materials Modeling\n\nCeriotti\n\nInteratomic potentials based on 
 the statistical learning of energy and forces obtained from electronic-str
 ucture calculations have increased dramatically the time and length scales
  accessible to atomistic modeling. In this talk I will discuss how a new g
 eneration of machine-learning models is making it possible to learn and pr
 edict <em>any</em> property that can be computed with first-principles cal
 culations, such as dielectric response tensors, the charge density, or the
  electronic density of states. Oftentimes, these approaches incorporate a 
 degree of physical insight, either in the structure and the symmetry behav
 ior of the descriptors, or in the use of physically-motivated procedures t
 o manipulate data-driven predictions of intermediate quantities to obtain 
 the desired property - for instance using the electronic density of states
  to evaluate an electronic correction to the heat capacity of a material. 
 I will discuss applications to molecules and condensed phases, demonstrati
 ng the general applicability of these integrated machine-learning schemes,
  that combine the best features of data and physics driven modeling of mat
 ter.\n\nDomain: CS and Math, Chemistry and Materials, Physics
END:VEVENT
END:VCALENDAR