Abstract
Large-scale atomistic simulations of materials heavily rely on interatomic potentials, which predict the system energy and atomic forces. One of the recent developments in the field is constructing interatomic potentials by machine-learning (ML) methods. ML potentials predict the energy and forces by numerical interpolation using a large reference database generated by quantum-mechanical calculations. While high accuracy of interpolation can be achieved, extrapolation to unknown atomic environments is unpredictable. The recently proposed physically-informed neural network (PINN) model improves the transferability by combining a neural network regression with a physics-based bond-order interatomic potential. Here, we demonstrate that general-purpose PINN potentials can be developed for body-centered cubic (BCC) metals. The proposed PINN potential for tantalum reproduces the reference energies within 2.8 meV/atom. It accurately predicts a broad spectrum of physical properties of Ta, including (but not limited to) lattice dynamics, thermal expansion, energies of point and extended defects, the dislocation core structure and the Peierls barrier, the melting temperature, the structure of liquid Ta, and the liquid surface tension. The potential enables large-scale simulations of physical and mechanical behavior of Ta with nearly first-principles accuracy while being orders of magnitude faster. This approach can be readily extended to other BCC metals.
Highlights
The critical ingredient of all large-scale molecular dynamics (MD) and Monte Carlo (MC) simulations of materials is the classical interatomic potential, which predicts the system energy and atomic forces as a function of atomic positions and, for multicomponent systems, their occupation by chemical species
The reference database has been generated by density functional theory (DFT) calculations employing the Vienna Ab Initio Simulation Package (VASP) [48, 49]
The body-centered cubic (BCC) structure was sampled in the greatest detail, including a wide range of isotropic and uniaxial deformations
Summary
The critical ingredient of all large-scale molecular dynamics (MD) and Monte Carlo (MC) simulations of materials is the classical interatomic potential, which predicts the system energy and atomic forces as a function of atomic positions and, for multicomponent systems, their occupation by chemical species. Computations with interatomic potentials are much faster than quantum-mechanical calculations explicitly treating the electrons. The computational efficiency of interatomic potentials enables simulations on length scales up to ∼ 102 nm (∼ 107 atoms) and time scales up to ∼ 102 ns. Interatomic potentials partition the total potential energy E into a sum of energies Ei assigned to individual atoms i: E = i Ei. Each atomic energy Ei is expressed as a function of the local atomic positions Ri ≡ (ri, ri2, ..., rini) in the vicinity of the atom.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have