Continuous and optimally complete description of chemical environments using Spherical Bessel descriptors
Open Access
- 1 January 2020
- journal article
- conference paper
- Published by AIP Publishing in AIP Advances
- Vol. 10 (1) , 015021
Abstract
Recently, machine learning potentials have been advanced as candidates to combine the high-accuracy of electronic structure methods with the speed of classical interatomic potentials. A crucial component of a machine learning potential is the description of local atomic environments by some set of descriptors. These should ideally be invariant to the symmetries of the physical system, twice-differentiable with respect to atomic positions (including when an atom leaves the environment), and complete to allow the atomic environment to be reconstructed up to symmetry. The stronger condition of optimal completeness requires that the condition for completeness be satisfied with the minimum possible number of descriptors. Evidence is provided that an updated version of the recently proposed Spherical Bessel (SB) descriptors satisfies the first two properties and a necessary condition for optimal completeness. The Smooth Overlap of Atomic Position (SOAP) descriptors and the Zernike descriptors are natural counterparts of the SB descriptors and are included for comparison. The standard construction of the SOAP descriptors is shown to not satisfy the condition for optimal completeness and, moreover, is found to be an order of magnitude slower to compute than that of the SB descriptors.Keywords
All Related Versions
Funding Information
- National Science Foundation (1839370)
This publication has 28 references indexed in Scilit:
- Accuracy and transferability of Gaussian approximation potential models for tungstenPhysical Review B, 2014
- Fast and Accurate Modeling of Molecular Atomization Energies with Machine LearningPhysical Review Letters, 2012
- High-dimensional neural network potentials for metal surfaces: A prototype study for copperPhysical Review B, 2012
- Support vector machine regression (SVR/LS-SVM)—an alternative to neural networks (ANN) for analytical chemistry? Comparison of nonlinear methods on near infrared (NIR) spectroscopy dataThe Analyst, 2011
- Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the ElectronsPhysical Review Letters, 2010
- Generalized Neural-Network Representation of High-Dimensional Potential-Energy SurfacesPhysical Review Letters, 2007
- 3D zernike descriptors for content based shape retrieval2003
- Neural network models of potential energy surfacesThe Journal of Chemical Physics, 1995
- Computer simulation of local order in condensed phases of siliconPhysical Review B, 1985
- Double Exponential Formulas for Numerical IntegrationPublications of the Research Institute for Mathematical Sciences, 1973