MARVEL seminar: "AI guided materials discovery of van der Waals magnets" (Trevor David Rhone)

AI guided materials discovery of van der Waals magnets

Trevor David Rhone

Department of Physics, Applied Physics and Astronomy, Rensselaer Polytechnic Institute 

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 CrI3 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? A conservative estimate for the number of candidate two-dimensional (2D) materials (including monolayers, bilayers and trilayers) exceeds ~10⁶. A recent study showed that artificial intelligence (AI) can be harnessed to discover new vdW Heisenberg ferromagnets based on Cr₂Ge₂Te₆ [1,2]. In this talk, we will harness AI to efficiently explore the large chemical space of vdW materials to guide the discovery of vdW magnets with desirable properties. That is, we investigate 2D atomic crystals, 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 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 [3,4]. In addition, we will examine how graph neural networks create new avenues for both materials and knowledge discovery. This study paves the way for the rapid discovery of chemically stable vdW magnets with applications in spintronics, data storage and quantum computing. 

This research was primarily supported by the NSF CAREER, under award number DMR- 2044842. 

_{[1] T. D. Rhone, et al., “Data-driven Studies of Magnetic Two-dimensional Materials,” Scientific Reports 10, 15795 (2020). 
[2] Y. Xie, et al., “Data-Driven Studies of the Magnetic Anisotropy of Two-Dimensional Magnetic Materials,” J. Phys. Chem. Lett., 12, 50, 12048–12054 (2021). 
[3] T. D. Rhone et al., “Artificial Intelligence Guided Studies of van der Waals Magnets,” Adv. Theory Simulations, 6, 2300019 (2023). 
[4] R. Bhattarai, P. Minch, and T. D. Rhone, “Investigating magnetic van der Waals materials using data-driven approaches,” J. Mater. Chem. C, 11, 5601 (2023).} 

About the speaker

Trevor David Rhone received a liberal arts education from Macalester College in Saint Paul. He went on to pursue his doctoral studies at Columbia University in the city of New York where he did experimental studies of two-dimensional electron systems in the extreme quantum limit. Trevor David spent several years at NTT Basic research laboratories in Japan.  During a research stint at the National Institute of Materials Science in Japan, he transitioned to materials informatics research - exploiting machine learning tools to perform materials research. He continued this work at Harvard University where he used machine learning tools to search for new 2D magnetic materials.

Trevor David Rhone's research interests involve using machine learning tools for materials discovery and knowledge discovery. Materials discovery could manifest in the search new 2D materials with exotic properties, the prediction of the outcome of industrially relevant catalytic reactions or for other compelling research problems. In addition, data analytics tools will be used to aid in developing a better understanding of physical systems.