Accelerated Data-Driven Discovery and Screening of Two-Dimensional Magnets Using Graph Neural Networks

Author:

Ahmed Elrashidy, James Della-Giustina, Jia-An Yan

Keyword:

Condensed Matter, Disordered Systems and Neural Networks, Disordered Systems and Neural Networks (cond-mat.dis-nn), Mesoscale and Nanoscale Physics (cond-mat.mes-hall), Materials Science (cond-mat.mtrl-sci)

journal:

date:

2023-11-01 16:00:00

Abstract

Two-dimensional (2D) magnets have transformative potential in spintronics applications. In this study, we use Graph Neural Networks (GNNs) to accelerate the discovery of novel 2D magnetic materials. Using data from the Materials Project database and the Computational 2D materials database (C2DB), we train three GNN architectures on a dataset of 1190 magnetic monolayers with energy above the convex hull $E_{\text{hull}}$ less than 0.3 eV/atom. Our Crystal Diffusion Variational Auto Encoder (CDVAE) generates around 11,000 material candidates. Subsequent training on two Atomistic Line Graph Neural Networks (ALIGNN) achieves a 93$\%$ accuracy in predicting magnetic monolayers and a mean average error of 0.039 eV/atom for $E_{\text{hull}}$ predictions. After narrowing down candidates based on magnetic likelihood and predicted energy, and constraining the atom count in the monolayer to four or fewer, we identified 158 candidates. These are validated using Density-Functional Theory (DFT) to confirm their magnetic and energetic favorability resulting in 150 materials magnetic monolayer with $E_{\text{hull}} < 0.3$ eV/atom. Our methodology offers a way to accelerate exploring and predicting potential 2D magnetic materials, contributing to the ongoing computational and experimental efforts aimed at the discovery of new 2D magnets.

PDF: Accelerated Data-Driven Discovery and Screening of Two-Dimensional Magnets Using Graph Neural Networks.pdf