Machine-learned multi-system surrogate models for materials prediction

TL;DR

This paper develops machine learning surrogate models that accurately predict the energies of multiple alloy systems simultaneously, significantly reducing computational costs in materials science.

Contribution

It introduces multi-system surrogate models capable of interpolating energies across various alloys and crystal structures with high accuracy, demonstrating scalability and efficiency.

Findings

Prediction errors increase less than 1 meV/atom with more alloys.

Prediction errors of formation enthalpy are under 2.5% across systems.

Models perform consistently across different materials representations.

Abstract

Surrogate machine-learning models are transforming computational materials science by predicting properties of materials with the accuracy of ab initio methods at a fraction of the computational cost. We demonstrate surrogate models that simultaneously interpolate energies of different materials on a dataset of 10 binary alloys (AgCu, AlFe, AlMg, AlNi, AlTi, CoNi, CuFe, CuNi, FeV, NbNi) with 10 different species and all possible fcc, bcc and hcp structures up to 8 atoms in the unit cell, 15\,950 structures in total. We find that the deviation of prediction errors when increasing the number of simultaneously modeled alloys is less than 1\,meV/atom. Several state-of-the-art materials representations and learning algorithms were found to qualitatively agree on the prediction errors of formation enthalpy with relative errors of $<$2.5\% for all systems.