Experimental investigation of magnetic properties of MnFeCo$_{4}$Si$_{2}$ discovered by GNoME
Shuhei Naganuma, Jiro Kitagawa

TL;DR
This study experimentally verifies the magnetic properties of MnFeCo4Si2, a compound predicted by the AI model GNoME, confirming its structure and ferromagnetic behavior with a high Curie temperature.
Contribution
First experimental validation of a GNoME-predicted compound's magnetic properties, demonstrating AI's effectiveness in guiding inorganic materials discovery.
Findings
MnFeCo4Si2 is a soft ferromagnet
Curie temperature is 1039 K
Crystallizes in a rhombohedral structure
Abstract
AI-driven inorganic materials research has garnered significant attention due to its ability to reduce the time, labor, and cost associated with experiments. An AI model known as GNoME, recently developed by Google DeepMind, is particularly fascinating because it is integrated with the Materials Project open database. The experimental verification of compounds identified by GNoME is a crucial process for advancing AI-driven materials research. Here, we focus on the magnetic compound MnFeCoSi (Materials ID: mp-3203253), which possesses a layered-like structure. Consistent with the GNoME prediction, MnFeCoSi crystallizes in a rhombohedral structure with a single-phase nature. We have characterized its magnetic properties and determined that MnFeCoSi is a soft ferromagnet with a Curie temperature of 1039 K.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning in Materials Science · Heusler alloys: electronic and magnetic properties · Chemical and Physical Properties of Materials
