Fast and stable deep-learning predictions of material properties for solid solution alloys

TL;DR

This paper introduces a multitasking deep learning approach that predicts multiple physical properties of solid solution alloys simultaneously, achieving high accuracy and stability while significantly reducing computation time compared to traditional methods.

Contribution

The novel use of multitasking neural networks incorporating physical property constraints improves prediction accuracy and stability for alloy properties over previous single-task models.

Findings

Multitasking neural networks accurately predict alloy properties.

Models are hundreds of times faster than density functional theory.

Including physical constraints enhances model stability and reduces uncertainty.

Abstract

We present a novel deep learning (DL) approach to produce highly accurate predictions of macroscopic physical properties of solid solution binary alloys and magnetic systems. The major idea is to make use of the correlations between different physical properties in alloy systems to improve the prediction accuracy of neural network (NN) models. We use multitasking NN models to simultaneously predict the total energy, charge density and magnetic moment. These physical properties mutually serve as constraints during the training of the multitasking NN, resulting in more reliable DL models because multiple physics properties are correctly learned by a single model. Two binary alloys, copper-gold (CuAu) and iron-platinum (FePt), were studied. Our results show that once the multitasking NN's are trained, they can estimate the material properties for a specific configuration hundreds of times faster than first-principles density functional theory calculations while retaining comparable accuracy. We used a simple measure based on the root-mean-squared errors (RMSE) to quantify the quality of the NN models, and found that the inclusion of charge density and magnetic moment as physical constraints leads to more stable models that exhibit improved accuracy and reduced uncertainty for the energy predictions.