High throughput inverse design and Bayesian optimization of functionalities: spin splitting in two-dimensional compounds

TL;DR

This paper presents a comprehensive workflow combining inverse design and Bayesian optimization to identify and engineer 2D materials with desirable spin splitting properties for spintronic devices, demonstrated through a database and predictive modeling.

Contribution

It introduces a novel integrated workflow for materials design that combines physical principles, DFT calculations, and Bayesian inference, applicable to various material properties.

Findings

Classified 358 2D materials by spin splitting type

Identified trends for designing materials with optimal band gap and spin splitting

Demonstrated the workflow's applicability to other properties

Abstract

The development of spintronic devices demands the existence of materials with some kind of spin splitting (SS). In this Data Descriptor, we build a database of ab initio calculated SS in 2D materials. More than that, we propose a workflow for materials design integrating an inverse design approach and a Bayesian inference optimization. We use the prediction of SS prototypes for spintronic applications as an illustrative example of the proposed workflow. The prediction process starts with the establishment of the design principles (the physical mechanism behind the target properties), that are used as filters for materials screening, and followed by density functional theory (DFT) calculations. Applying this process to the C2DB database, we identify and classify 358 2D materials according to SS type at the valence and/or conduction bands. The Bayesian optimization captures trends that are used for the rationalized design of 2D materials with the ideal conditions of band gap and SS for potential spintronics applications. Our workflow can be applied to any other material property.