Generative deep learning as a tool for inverse design of high-entropy refractory alloys

TL;DR

This paper explores how generative deep learning can be used for the inverse design of high-entropy refractory alloys, demonstrating its potential to create novel materials for ultra-high-temperature applications.

Contribution

It introduces a computational workflow utilizing generative models for inverse materials design, highlighting their ability to learn complex relationships and generate new alloy compositions.

Findings

Generative models can learn complex material relationships.

The workflow enables the inverse design of novel alloys.

Preliminary results show promising potential for materials informatics.

Abstract

Generative deep learning is powering a wave of new innovations in materials design. In this article, we discuss the basic operating principles of these methods and their advantages over rational design through the lens of a case study on refractory high-entropy alloys for ultra-high-temperature applications. We present our computational infrastructure and workflow for the inverse design of new alloys powered by these methods. Our preliminary results show that generative models can learn complex relationships in order to generate novelty on demand, making them a valuable tool for materials informatics.