Conceptual and practical bases for the high accuracy of machine learning interatomic potential

Abstract

Machine learning interatomic potentials (MLIPs) based on a large dataset obtained by density functional theory (DFT) calculation have been developed recently. This study gives both conceptual and practical bases for the high accuracy of MLIPs, although MLIPs have been considered to be simply an accurate black-box description of atomic energy. We also construct the most accurate MLIP of the elemental Ti ever reported using a linearized MLIP framework and many angular-dependent descriptors, which also corresponds to a generalization of the modified embedded atom method (MEAM) potential.

References in corpus (2)

• Classical potential describes martensitic phase transformations between the $\alpha$, $\beta$ and $\omega$ titanium phases
• Development of an Interatomic Potential for the Simulation of Defects, Plasticity and Phase Transformations in Titanium

Cited by in corpus (6)

• Physically Motivated Recursively Embedded Atom Neural Networks: Incorporating Local Completeness and Nonlocality
• Group-theoretical high-order rotational invariants for structural representations: Application to linearized machine learning interatomic potential
• Accurate machine learning force fields via experimental and simulation data fusion
• Predictive power of polynomial machine learning potentials for liquid states in 22 elemental systems
• REANN: A PyTorch-based End-to-End Multi-functional Deep Neural Network Package for Molecular, Reactive and Periodic Systems
• Systematic global structure search of bismuth-based binary systems under pressure using machine learning potentials