An assessment of the structural resolution of various fingerprints commonly used in machine learning

Abstract

Atomic environment fingerprints are widely used in computational materials science, from machine learning potentials to the quantification of similarities between atomic configurations. Many approaches to the construction of such fingerprints, also called structural descriptors, have been proposed. In this work, we compare the performance of fingerprints based on the Overlap Matrix(OM), the Smooth Overlap of Atomic Positions (SOAP), Behler-Parrinello atom-centered symmetry functions (ACSF), modified Behler-Parrinello symmetry functions (MBSF) used in the ANI-1ccx potential and the Faber-Christensen-Huang-Lilienfeld (FCHL) fingerprint under various aspects. We study their ability to resolve differences in local environments and in particular examine whether there are certain atomic movements that leave the fingerprints exactly or nearly invariant. For this purpose, we introduce a sensitivity matrix whose eigenvalues quantify the effect of atomic displacement modes on the fingerprint. Further, we check whether these displacements correlate with the variation of localized physical quantities such as forces. Finally, we extend our examination to the correlation between molecular fingerprints obtained from the atomic fingerprints and global quantities of entire molecules.

18 pages, 11 figures

References in corpus (3)

• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• A Novel Approach to Describe Chemical Environments in High Dimensional Neural Network Potentials

Cited by in corpus (13)

• Efficient implementation of atom-density representations
• Global optimization of atomic structures with gradient-enhanced Gaussian process regression
• Roadmap on machine learning glassy dynamics
• Dimensionality reduction of local structure in glassy binary mixtures
• Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting failure to machine learn four-body interactions
• Completeness of Atomic Structure Representations
• Optimal radial basis for density-based atomic representations
• Ab initio machine learning of phase space averages
• Decomposing Chemical Space: Applications to the Machine Learning of Atomic Energies
• Shadow molecular dynamics and atomic cluster expansions for flexible charge models
• A smooth basis for atomistic machine learning
• Machine learning frontier orbital energies of nanodiamonds
• Compressing local atomic neighbourhood descriptors