• English
  • Deutsch
  • Log In
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Artikel
  4. LC-GAP: Localized Coulomb Descriptors for the Gaussian Approximation Potential
 
  • Details
  • Full
Options
2017
  • Aufsatz in Buch

Titel

LC-GAP: Localized Coulomb Descriptors for the Gaussian Approximation Potential

Abstract
We introduce a novel class of localized atomic environment representations based upon the Coulomb matrix. By combining these functions with the Gaussian approximation potential approach, we present LC-GAP, a new system for generating atomic potentials through machine learning (ML). Tests on the QM7, QM7b and GDB9 biomolecular datasets demonstrate that potentials created with LC-GAP can successfully predict atomization energies for molecules larger than those used for training to chemical accuracy, and can (in the case of QM7b) also be used to predict a range of other atomic properties with accuracy in line with the recent literature. As the best-performing representation has only linear dimensionality in the number of atoms in a local atomic environment, this represents an improvement in both prediction accuracy and computational cost when compared to similar Coulomb matrix-based methods.
Author(s)
Barker, James
Bulin, Johannes
Hamaekers, Jan
Mathias, Sonja
Hauptwerk
Scientific Computing and Algorithms in Industrial Simulations
Thumbnail Image
DOI
10.1007/978-3-319-62458-7_2
Language
Englisch
google-scholar
SCAI
  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022