Development of Interatomic Potential for Al-Tb Alloy by Deep Neural Network Learning Method

TL;DR

This paper presents a deep neural network-based interatomic potential for Al-Tb alloys, trained on ab initio data, accurately reproducing energies, forces, structural properties, and phase formation energies, validated against experimental data.

Contribution

The study introduces a novel DNN interatomic potential for Al-Tb alloys that achieves high accuracy in reproducing ab initio and experimental results, enhancing simulation capabilities.

Findings

DNN potential accurately reproduces AIMD energies and forces.

MD simulations with the DNN potential match structural properties and experimental data.

Predicted formation energies of crystalline phases are comparable to ab initio calculations.

Abstract

An interatomic potential for Al-Tb alloy around the composition of Al90Tb10 was developed using the deep neural network (DNN) learning method. The atomic configurations and the corresponding total potential energies and forces on each atom obtained from ab initio molecular dynamics (AIMD) simulations are collected to train a DNN model to construct the interatomic potential for Al-Tb alloy. We show the obtained DNN model can well reproduce the energies and forces calculated by AIMD. Molecular dynamics (MD) simulations using the DNN interatomic potential also accurately describe the structural properties of Al90Tb10 liquid, such as the partial pair correlation functions (PPCFs) and the bond angle distributions, in comparison with the results from AIMD. Furthermore, the developed DNN interatomic potential predicts the formation energies of crystalline phases of Al-Tb system with the accuracy comparable to ab initio calculations. The structure factor of Al90Tb10 metallic glass obtained by MD simulation using the developed DNN interatomic potential is also in good agreement with the experimental X-ray diffraction data.