DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Representing local atomic environment using descriptors based on local correlations

Journal Article · · Journal of Chemical Physics
DOI: https://doi.org/10.1063/1.5055772 · OSTI ID:1502005
 [1]
  1. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States). Physics Division

Statistical learning of material properties is an emerging topic of research and has been tremendously successful in areas such as representing complex energy landscapes as well as in technologically relevant areas, like identification of better catalysts and electronic materials. However, analysis of large data sets to efficiently learn characteristic features of a complex energy landscape, for example, depends on the ability of descriptors to effectively screen different local atomic environments. Thus, discovering appropriate descriptors of bulk or defect properties and the functional dependence of such properties on these descriptors remains a difficult and tedious process. To this end, we develop here a framework to generate descriptors based on many-body correlations that can effectively capture intrinsic geometric features of the local environment of an atom. These descriptors are based on the spectrum of two-body, three-body, four-body, and higher order correlations between an atom and its neighbors and are evaluated by calculating the corresponding two-body, three-body, and four-body overlap integrals. They are invariant to global translation, global rotation, reflection, and permutations of atomic indices. By systematically testing the ability to capture the local atomic environment, it is shown that the local correlation descriptors are able to successfully reconstruct structures containing 10-25 atoms which was previously not possible.

Research Organization:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA)
Grant/Contract Number:
AC52-07NA27344
OSTI ID:
1502005
Report Number(s):
LLNL-JRNL-757813; 945702
Journal Information:
Journal of Chemical Physics, Vol. 149, Issue 24; ISSN 0021-9606
Publisher:
American Institute of Physics (AIP)Copyright Statement
Country of Publication:
United States
Language:
English
Citation Metrics:
Cited by: 4 works
Citation information provided by
Web of Science

References (29)

Normalized cuts and image segmentation journal January 2000
A universal strategy for the creation of machine learning-based atomistic force fields journal September 2017
wACSF—Weighted atom-centered symmetry functions as descriptors in machine learning potentials journal June 2018
Representing potential energy surfaces by high-dimensional neural network potentials journal April 2014
Learning molecular energies using localized graph kernels journal March 2017
Neural networks vs Gaussian process regression for representing potential energy surfaces: A comparative study of fit quality and vibrational spectrum accuracy journal June 2018
Computational aspects of many-body potentials journal May 2012
Erratum: On representing chemical environments [Phys. Rev. B 87 , 184115 (2013)] journal July 2017
Using Force Matching To Determine Reactive Force Fields for Water under Extreme Thermodynamic Conditions journal December 2016
Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space journal June 2015
Laplacian Eigenmaps for Dimensionality Reduction and Data Representation journal June 2003
Efficient Sampling of Atomic Configurational Spaces journal August 2010
Exploring the free energy surface using ab initio molecular dynamics journal April 2016
A fingerprint based metric for measuring similarities of crystalline structures journal January 2016
Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials journal March 2015
Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies journal July 2013
Adaptive machine learning framework to accelerate ab initio molecular dynamics journal December 2014
Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations journal January 2011
Linearized machine-learning interatomic potentials for non-magnetic elemental metals: Limitation of pairwise descriptors and trend of predictive power journal June 2018
Geometric diffusions as a tool for harmonic analysis and structure definition of data: Diffusion maps journal May 2005
Efficient non-parametric fitting of potential energy surfaces for polyatomic molecules with Gaussian processes journal October 2016
Order-parameter-aided temperature-accelerated sampling for the exploration of crystal polymorphism and solid-liquid phase transitions journal June 2014
ChIMES: A Force Matched Potential with Explicit Three-Body Interactions for Molten Carbon journal November 2017
Diffusion maps, spectral clustering and reaction coordinates of dynamical systems journal July 2006
Deep Potential Molecular Dynamics: A Scalable Model with the Accuracy of Quantum Mechanics journal April 2018
Extending the accuracy of the SNAP interatomic potential form journal June 2018
Sampling saddle points on a free energy surface journal April 2014
Atom-centered symmetry functions for constructing high-dimensional neural network potentials journal February 2011
On Unique Numbering of Atoms and Unique Codes for Molecular Graphs journal May 1975