Artificial intelligence guided studies of van der Waals magnets
Trevor David Rhone1, Bethany Lusch2, Misha Salim2, Vaishnavi Neema1, Daniel T.
Larson3, Efthimios Kaxiras3
[1] Department of Physics, Applied Physics and Astronomy, Rensselaer Polytechnic Institute;
[2] Argonne Leadership Computing Facility, Argonne National Laboratory; [3] Department of
Physics, Harvard University
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, a monolayer of CrI3 was found to be an Ising ferromagnet. Other vdW transition metal halides, such as CrBr3, were later found to have different magnetic properties. How many vdW magnetic materials exist in nature? What are their magnetic 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 ~106. A recent study showed that machine learning can be exploited to discover new vdW Heisenberg ferromagnets based on Cr2Ge2Te6 [1]. In this talk, we will use materials informatics – materials science combined with artificial intelligence (AI) – as a tool 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. That is, we investigate crystal structures based on monolayer Cr2I6 of the form A2X6, 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 properties of vdW magnets. In addition, data analytics provides insights into the microscopic origins of magnetic ordering in two dimensions. We also explore how our study of magnetic monolayers can be extended, with proper modification, to multilayer vdW materials. This non-traditional approach to materials research paves the way for the rapid discovery of chemically stable magnetic vdW materials with
potential applications in spintronics and data storage.
[1] T. D. Rhone, et al., Sci Rep 10, 15795 (2020).
This research was primarily supported by the NSF CAREER, under award number DMR-
2044842.
Bio:
Trevor David Rhone received a liberal arts education from Macalester College in Saint Paul. He pursued his doctoral studies at Columbia University where he did experimental studies of two-dimensional electron systems in the extreme quantum limit using inelastic light scattering. Rhone spent several years at NTT Basic research laboratories in Japan where he received the BRL director award for his research. While working at the National Institute of Materials Science in Tsukuba, Japan, he transitioned to materials informatics – an emerging field combining materials science with machine learning. He continued this work at Harvard University as a postdoctoral prize fellow where he used machine learning tools to search for new 2D magnetic materials.
Rhone is now a member of the faculty at RPI, where his research interests are at the intersection of materials science and AI. His research goals include the discovery of 2D magnetic materials, in addition to creating physical insight into their behavior. He recently received the NSF CAREER award for his research.
