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

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.

A database of refractive indices and dielectric constants auto-generated using ChemDataExtractor

“…For instance, a user may wish to use this database as a source to develop a data-driven “design-to-device” operational pipeline 22 . Successful studies that have generated and used auto-generated databases via similar efforts to this work have been reported in recent papers 13 , 23 – 26 , whereby a small short-list of leading candidates can be progressively filtered down from the database for a target material application 22 , 23 , 27 . In such scenarios, false positive database entries would likely be filtered out naturally during downstream analysis, while a data source that carries a large amount of data is essential for such a data-driven task.…”

Machine-learning approach for discovery of conventional superconductors

“…Finally, the ML models will be integrated in an inverse design strategy to explore the practically infinite materials space in an efficient manner. Currently, (inverse) design of functional materials with targeted properties is a very active research area with many success stories [94][95][96][97][98][99][100][101]. We hope that superconducting materials discoveries can be added to this list in the near future.…”

XERUS: An Open‐Source Tool for Quick XRD Phase Identification and Refinement Automation

“…On the other hand, candidate-based materials search often involves different materials spanning a large chemical space, where sometimes even the optimal synthesis route can be unknown. For example, in the search of new magnetocaloric materials, [15][16][17] both the work of Bocarsly et al [16] and Court et al, [17] all the proposed candidate materials belonged to different chemical spaces, for example, Mn-Nb-S and Co-Sc-V. Moreover, in the recent work of Xiong et al, [18] by the high throughput screening of the MP database for efficient photocatalysts, 71 different materials were selected for experimental evaluation and only 11 were successfully synthesized, all belonging to different chemical spaces, such as Ca-Pb-O, Ba-Nb-Mn-O, Sr-In-O, Ca-In-O.…”

“…On the other hand, candidate‐based materials search often involves different materials spanning a large chemical space, where sometimes even the optimal synthesis route can be unknown. For example, in the search of new magnetocaloric materials, [ 15–17 ] both the work of Bocarsly et al. [ 16 ] and Court et al., [ 17 ] all the proposed candidate materials belonged to different chemical spaces, for example, Mn‐Nb‐S and Co‐Sc‐V.…”