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:20210916T132528Z
LOCATION:Michel Mayor
DTSTART;TZID=Europe/Stockholm:20210705T153000
DTEND;TZID=Europe/Stockholm:20210705T173000
UID:submissions.pasc-conference.org_PASC21_sess119@linklings.com
SUMMARY:Incorporating Long Range Interactions Into Machine Learned Potenti
 als
DESCRIPTION:Minisymposium\n\nMachine learned potentials are an important t
 ool in materials science and chemistry since they provide a highly accurat
 e and computationally efficient approximation of the potential energy surf
 ace. Most of the currently used methods however, are based on a local desc
 ription of atomic environments and are thus unable to describe effects whi
 ch take place over long distances beyond the local cutoff, such as charge 
 transfer or a change in the total charge of a system. The established meth
 ods can therefore not be applied to systems where such long range effects 
 play an important role i.e. aromatic organic molecules, sp2 hybridized car
 bon systems or metal clusters adsorbed on  doped substrates. This inherent
  shortcoming has recently gained attention which caused the development of
  a new generation of methods. In this minisymposium, we will discuss, with
  prominent experts in the field, the current challenges of incorporating l
 ong range interactions into machine learned potentials.\n\nAccurate Descri
 ption of Long-Range Interaction Energy via Charge Equilibration Process\n\
 nGhasemi\n\nLong-Range electrostatic energy is an essential part of total 
 energy on an atomic scale. The standard machine learning methods such as h
 igh-dimensional neural network potentials take into account only short-ran
 ge interactions. We present an approach to separate long-range and short-r
 ange interaction...\n\n---------------------\nEnergy Functionals of Atom-B
 ased Electron Populations: An Approach to Robust ML PESs\n\nXie\n\nML PESs
  have shown great promise in reducing the computational cost of DFT calcul
 ations, however, most methods are not suitable for describing systems with
  variable electronic structure or where long-range interactions are essent
 ial, e.g. molecules with different charge states. In order to solve thi...
 \n\n---------------------\nFour Generations of Neural Network Potentials\n
 \nBehler\n\nA lot of progress has been made in recent years in the develop
 ment of atomistic potentials employing machine learning (ML). Neural netwo
 rk potentials (NNPs), which have first been proposed about two decades ago
 , are an important class of ML potentials. While first generation NNPs hav
 e been restricte...\n\n---------------------\nHigh Resolution Fingerprints
  to Detect Nonlocal Effects\n\nGoedecker\n\nFingerprints are a widely used
  tool to quantify the similarity/dissimilarity of atomic environments and 
 they are used as input into various machine learning schemes. I will first
  compare the resolution power of some widely used fingerprints. Such a com
 parison already shows that some standard fingerp...\n\n\nDomain: Chemistry
  and Materials
END:VEVENT
END:VCALENDAR