Researchers use AI to discover novel 2D magnets for data storage and quantum computing

Cutting-edge tools in artificial intelligence (AI) have enabled a team of researchers led by Rensselaer Polytechnic Institute’s Trevor David Rhone, assistant professor in the Department of Physics, Applied Physics, and Astronomy, to identify novel van der Waals (vdW) magnets. The team used semi-supervised learning to identify transition metal halide vdW materials with large magnetic moments that are predicted to be chemically stable.

These 2D vdW magnets have potential applications in spintronics, data storage, and quantum computing. Rhone specializes in materials informatics, which uses AI and materials science to discover new materials with unique properties. His team’s latest research, which was recently featured on the cover of Advanced Theory and Simulations, could pave the way for more efficient and cost-effective materials discovery processes.

2D magnets are significant because they retain their long-range magnetic ordering even when thinned down to one or a few layers. This is due to magnetic anisotropy. The interplay with this magnetic anisotropy and low dimensionality could give rise to exotic spin degrees of freedom, such as spin textures, that can be used in the development of quantum computing architectures.

Rhone and team combined high-throughput density functional theory (DFT) calculations with AI to implement semi-supervised learning. This approach saves time and money compared to traditional materials discovery methods that rely on supercomputer simulations or lab experiments. The team used an initial subset of 700 DFT calculations to train an AI model that could predict the properties of thousands of materials candidates in milliseconds on a laptop. The team then identified promising candidate vdW materials with large magnetic moments and low formation energy, which is an indicator of chemical stability.

Rhone pointed out that their framework can easily be extended to explore materials with various crystal structures. For instance, it can be applied to mixed crystal structure prototypes, such as a dataset containing both transition metal halides and transition metal trichalcogenides.

Curt Breneman, the dean of Rensselaer’s School of Science, commended Rhone’s application of AI to the field of materials science, stating that it continues to yield exciting results. Breneman added that Rhone’s discoveries and methods have the potential to contribute to the development of new quantum computing technologies, in addition to advancing our understanding of 2D materials with unique properties.

Source: Rensselaer Polytechnic Institute

Leave a Comment