Experimental investigation of magnetic properties of MnFeCo$_{4}$Si$_{2}$ discovered by GNoME
Shuhei Naganuma, Jiro Kitagawa
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 MnFeCo$_{4}$Si$_{2}$ (Materials ID: mp-3203253), which possesses a layered-like structure. Consistent with the GNoME prediction, MnFeCo$_{4}$Si$_{2}$ crystallizes in a rhombohedral structure with a single-phase nature. We have characterized its magnetic properties and determined that MnFeCo$_{4}$Si$_{2}$ is a soft ferromagnet with a Curie temperature of 1039 K.
