Neural-networks model for force prediction in multi-principal-element alloys

TL;DR

This paper introduces a deep 3D CNN framework with voxelization to accurately predict interatomic potentials in complex multi-principal-element alloys, surpassing classical methods and matching DFT accuracy.

Contribution

The novel 3D CNN-based approach effectively captures quantum effects in alloy simulations, demonstrating high accuracy and efficiency for complex materials.

Findings

The 3D CNN model achieves DFT-level accuracy in potential prediction.

Voxel resolution impacts the model's performance and computational efficiency.

The framework enables more accurate atomistic simulations of complex alloys.

Abstract

Atomistic simulations can provide useful insights into the physical properties of multi-principal-element alloys. However, classical potentials mostly fail to capture key quantum (electronic-structure) effects. We present a deep 3D convolutional neural network (3D CNN) based framework combined with a voxelization technique to design interatomic potentials for chemically complex alloys. We highlight the performance of the 3D CNN model and its efficacy in computing potentials using the medium-entropy alloy TaNbMo. In order to provide insights into the effect of voxel resolution, we implemented two approaches based on the inner and outer bounding boxes. An efficient 3D CNN model, which is as accurate as the density-functional theory (DFT) approach, for calculating potentials will provide a promising schema for accurate atomistic simulations of structure and dynamics of general multi-principle element alloys.