Linearized machine-learning interatomic potentials for non-magnetic elemental metals: Limitation of pairwise descriptors and trend of predictive power

Abstract

Machine-learning interatomic potential (MLIP) has been of growing interest as a useful method to describe the energetics of systems of interest. In the present study, we examine the accuracy of linearized pairwise MLIPs and angular-dependent MLIPs for 31 elemental metals. Using all of the optimal MLIPs for 31 elemental metals, we show the robustness of the linearized frameworks, the general trend of the predictive power of MLIPs and the limitation of pairwise MLIPs. As a result, we obtain accurate MLIPs for all 31 elements using the same linearized framework. This indicates that the use of numerous descriptors is the most important practical feature for constructing MLIPs with high accuracy. An accurate MLIP can be constructed using only pairwise descriptors for most non-transition metals, whereas it is very important to consider angular-dependent descriptors when expressing interatomic interactions of transition metals.

18 pages, 14 figures

References in corpus (4)

• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Accurate Force Field for Molybdenum by Machine Learning Large Materials Data
• Conceptual and practical bases for the high accuracy of machine learning interatomic potential

Cited by in corpus (7)

• Group-theoretical high-order rotational invariants for structural representations: Application to linearized machine learning interatomic potential
• Combining quantum mechanics and machine-learning calculations for anharmonic corrections to vibrational frequencies
• Ab-initio based models for temperature-dependent magneto-chemical interplay in bcc Fe-Mn alloys
• Anharmonic Thermodynamics of Vacancies Using a Neural Network Potential
• Infrared spectra of neutral polycyclic aromatic hydrocarbons by machine learning
• Building nonparametric $n$-body force fields using Gaussian process regression
• Theory of dynamical stability for two- and three-dimensional Lennard-Jones crystals