Unified approach to generating a training set for machine learning interatomic potentials: The case of BCC tungsten

AA Kistanov and I Kosarev and SA Shcherbinin and A Shapeev and EA Korznikova and S Dmitriev, MATERIALS TODAY COMMUNICATIONS, 42, 111437 (2025).

DOI: 10.1016/j.mtcomm.2024.111437

Tungsten is used as a material capable of withstanding extreme conditions, particularly in Generation IV fusion and fission reactors. To relate structure and properties and to solve other problems in materials science, atomistic modeling is an indispensable approach. The predictive power of molecular dynamics modeling depends largely on the quality of the interatomic potentials used in the simulations. Recently, machine learning interatomic potentials (MLIPs) have become popular because they provide better accuracy compared to potentials based on the embedded atom method (EAM). MLIPs are often trained to reproduce the density functional theory (DFT) results obtained for the randomly generated atomic configurations. Here, we develop a MLIP for tungsten that is trained to reproduce the frequency response of the exact oscillatory solutions to the dynamic equations of atomic motion, called delocalized nonlinear vibrational modes (DNVMs). The quality of the potential is then improved by training on thermal fluctuations and uniform deformation configurations. The accuracy and high simulation speed of the developed potential are demonstrated, and the potential is prepared for public use by embedding it into the Large-scale Atomic/Molecular Massively Parallel Simulator (LAMMPS) code. The presented approach can be easily applied to other non-magnetic bcc crystals.

Return to Publications page