BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Machine Learning Force Field for Organic Liquids: EC/EMC Binary So
 lvent - Ioan-Bogdan Magdau\, Cambridge
DTSTART:20220307T140000Z
DTEND:20220307T143000Z
UID:TALK167297@talks.cam.ac.uk
CONTACT:Dr Christoph Schran
DESCRIPTION:Machine learning methods have been employed successfully to mo
 del small molecules in vacuum where the highly directional bonding interac
 tions dominate\, as well as inorganic solids and liquids where the interac
 tions are weaker but homogeneous.  The molecular condensed phase presents 
 unique challenges to ML owing to a large energy scale separation between t
 heir intra- and inter-molecular interactions. Molecular liquids with mixed
  compositions present the additional complication of large dimensionality 
 imbalances between intra-/inter- molecular environments.  In practice this
  makes it difficult to fit the inter- contribution which underlies the the
 rmodynamics of the liquid state. Typical loss functions are on total energ
 ies and forces and since inter-molecular interactions are weaker\, the int
 ra-molecular force dominates by about an order of magnitude. Therefore\, a
  typical fit would get good intra- and poor inter- relative accuracy. Prev
 ious attempts to model molecular liquids with ML have employed several str
 ategies to tackle the intra-/inter- imbalance. One approach is to separate
  the interaction scales by creating independent force fields for the molec
 ule and for the liquids\, respectively. This of course solves the problem 
 of scale separation neatly\; however\, it also makes it impossible to exte
 nd such a model to the reactive regime where the bonds can break and refor
 m allowing chemical reactions to take place. Here we demonstrate that by c
 rafting a sufficiently diverse training set through iterative training and
  by carefully testing the accuracy of our models on the relevant inter-mol
 ecular scale\, we can fit a general purpose potential which describes the 
 EC:EMC binary solvent liquid.  This paves the way for a more general full 
 reactive force field which will be needed to study the electrode-electroly
 te interface with ab initio accuracy.
LOCATION:Venue to be confirmed
END:VEVENT
END:VCALENDAR