Trevor Rhone1,Romakanta Bhattarai1,Haralambos Gavras1,Bethany Lusch2,Misha Salim2,Marios Mattheakis3,Daniel Larson3,Yoshiharu Krockenberger4,Efthimios Kaxiras3
Rensselaer Polytechnic Institute1,Argonne National Laboratory2,Harvard University3,NTT Basic Research Laboratory4
Trevor Rhone1,Romakanta Bhattarai1,Haralambos Gavras1,Bethany Lusch2,Misha Salim2,Marios Mattheakis3,Daniel Larson3,Yoshiharu Krockenberger4,Efthimios Kaxiras3
Rensselaer Polytechnic Institute1,Argonne National Laboratory2,Harvard University3,NTT Basic Research Laboratory4
The discovery of van der Waals (vdW) materials with intrinsic magnetic order in 2017 has given rise to new avenues for the study of emergent phenomena in two dimensions. In particular, monolayer CrI<sub>3</sub> was found to be ferromagnetic. Other vdW transition metal halides were later found to have different magnetic properties. How many vdW magnetic materials exist in nature? What are their properties? How do these properties change with the number of layers? A conservative estimate for the number of candidate vdW materials (including monolayers, bilayers and trilayers) exceeds ~10<sup>6</sup>. Recent studies show that artificial intelligence (AI) can be harnessed to discover new vdW Heisenberg ferromagnets based on Cr<sub>2</sub>Ge<sub>2</sub>Te<sub>6</sub> [1, 2]. In this talk, we will harness AI to efficiently explore the large chemical space of vdW transition metal halides and to guide the discovery of magnetic vdW materials with desirable spin properties [3]. That is, we investigate crystal structures based on monolayer Cr<sub>2</sub>I<sub>6</sub> of the form A<sub>2</sub>X<sub>6</sub>, which are studied using density functional theory (DFT) calculations and AI. Magnetic properties, such as the magnetic moment are determined. The formation energy is also calculated and used as a proxy for the chemical stability. We show that AI, combined with DFT, can provide a computationally efficient means to predict the thermodynamic and magnetic properties of vdW materials. We use semi-supervised learning to mitigate the challenge of data scarcity in AI-guided materials discovery. This study paves the way for the rapid discovery of chemically stable magnetic vdW materials with applications in spintronics, data storage and quantum computing.<br/>[1] T. D. Rhone, et al., Sci. Rep. 10, 15795 (2020).<br/>[2] Y. Xie, et al., J. Phys. Chem. Lett., 12, 50, 12048–12054 (2021).<br/>[3] T. D. Rhone <i>et al.</i>, “Artificial Intelligence Guided Studies of van der Waals Magnets,” <i>Adv. Theory Simulations</i>, p. 2300019 (2023).<br/>This research was primarily supported by the NSF CAREER, under award number DMR-2044842.