Physics-inspired equivariant descriptors of non-bonded interactions

Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="" xmlns:oai_dc="" xmlns:xsi="" xsi:schemaLocation="">
  <dc:creator>Huguenin-Dumittan, Kevin K.</dc:creator>
  <dc:creator>Loche, Philip</dc:creator>
  <dc:creator>Ni, Haoran</dc:creator>
  <dc:creator>Ceriotti, Michele</dc:creator>
  <dc:description>One essential ingredient in many machine learning (ML) based methods for atomistic modeling of materials and molecules is the use of locality. While allowing better system-size scaling, this systematically neglects long-range (LR) effects, such as electrostatics or dispersion interaction. We present an extension of the long distance equivariant (LODE) framework that can handle diverse LR interactions in a consistent way, and seamlessly integrates with preexisting methods by building new sets of atom centered features. We provide a direct physical interpretation of these using the multipole expansion, which allows for simpler and more efficient implementations. The framework is applied to simple toy systems as proof of concept, and a heterogeneous set of molecular dimers to push the method to its limits. By generalizing LODE to arbitrary asymptotic behaviors, we provide a coherent approach to treat arbitrary two- and many-body non-bonded interactions in the data-driven modeling of matter.</dc:description>
  <dc:publisher>Materials Cloud</dc:publisher>
  <dc:rights>Creative Commons Attribution 4.0 International</dc:rights>
  <dc:subject>machine learning</dc:subject>
  <dc:subject>long-range interactions</dc:subject>
  <dc:title>Physics-inspired equivariant descriptors of non-bonded interactions</dc:title>