Inverse Design of Materials That Exhibit the Magnetocaloric Effect by Text-Mining of the Scientific Literature and Generative Deep Learning

Callum J Court,Jacqueline M Cole,Apoorv Jain

doi:10.1021/acs.chemmater.1c01368

Abstract

Magnetic materials play an important role in a wide variety of everyday applications, and they are critical components in many devices used for energy conversion. However, there are very few materials known to exhibit magnetism of any kind, and the slow process of experimentally driven magnetic-materials discovery has limited the development of devices for functional applications. In this work, a complete magnetic-materials discovery pipeline is presented that uses natural language processing (NLP), machine learning, and generative models to predict ferromagnetic compounds in the Heusler alloy family. Using the “chemistry-aware” NLP toolkit, ChemDataExtractor, a database of 2910 magnetocaloric compounds is autogenerated by sourcing from the scientific literature. These data are then used to train property-prediction models for key figures of merit that describe the magnetocaloric effect. The predictive models are applied to novel Heusler alloy material candidates that have been created using deep generative representation learning. Convex-hull meta-stability analysis and ab initio validation of these candidates identify six potential materials for solid-state refrigeration applications.

Highlights

Magnetism plays an important role in a number of applications, such as transformers, memory devices, and magnetometers.[1]
The first stage of the materials discovery process that is described in Figure 1 involves creating an autogenerated database of chemical records that contain magnetocaloric compounds and their associated Curie temperature, absolute magnetic-entropy change, and relative cooling power (RCP) values
The datacleaning process, which was fully detailed in Methods, removed records containing incorrect chemical formulae and other spurious records

Summary

Introduction

Magnetism plays an important role in a number of applications, such as transformers, memory devices, and magnetometers.[1] the availability of magnetic materials for these devices is limited by the relative lack of known magnetic compounds. In a typical magnetic material, the magnetic behavior is controlled by the exchange interaction. This interaction governs the coupling between magnetic moments[2] and is highly dependent on crystal geometry and atomic valency. There is a subtle interplay between the structure and properties that gives rise to delicate magnetic states.[3] There are countless ways in which magnetic ions can interact with each other and their environments. It is difficult to predict magnetic behavior

Methods

Results

Conclusion