AI-accelerated Materials Informatics Method for the Discovery of Ductile Alloys

TL;DR

This paper introduces an AI-accelerated materials informatics approach that combines machine-learning interatomic potentials with modeling to efficiently predict the ductility of alloys, enabling high-throughput screening of alloy compositions.

Contribution

It presents a novel methodology integrating machine-learning potentials with traditional modeling for rapid alloy property prediction, overcoming DFT computational limitations.

Findings

Successfully predicted room temperature ductility of Mo-Nb-Ta alloy.

Achieved DFT-like accuracy with significantly reduced computational cost.

Enabled high-throughput screening of alloy space.

Abstract

In computational materials science, a common means for predicting macroscopic (e.g., mechanical) properties of an alloy is to define a model using combinations of descriptors that depend on some material properties (elastic constants, misfit volumes, etc.), representative for the macroscopic behavior. The material properties are usually computed using special quasi-random structures (SQSs), in tandem with density functional theory (DFT). However, DFT scales cubically with the number of atoms and is thus impractical for a screening over many alloy compositions. Here, we present a novel methodology which combines modeling approaches and machine-learning interatomic potentials. Machine-learning interatomic potentials are orders of magnitude faster than DFT, while achieving similar accuracy, allowing for a predictive and tractable high-throughput screening over the whole alloy space. The proposed methodology is illustrated by predicting the room temperature ductility of the medium-entropy alloy Mo-Nb-Ta.