Magnets are key components in modern technologies including electrical vehicles, wind turbines, medical equipment, cell phones, and computers. Most high-performance permanent magnets contain rare-earth elements such as neodymium (Nd) and dysprosium (Dy). These “strategic” elements are of particular importance to improve performance in permanent-magnet applications. The demand for rare-earth-based high-performance permanent magnets continues to grow, putting economic and national security pressure on the supply of rare-earth elements. China produces 97% of all rare-earth elements and their mining can have detrimental impacts including the release of dangerous radioactive elements such as uranium into the environment.
A collaborative National Science Foundation Designing Materials to Revolutionize and Engineer our Future team from the University of Texas at Austin, University of Nebraska-Lincoln, and Iowa State University has employed the MGI philosophy to accelerate the design of rare-earth-free magnetic materials. Specifically, they have developed an open-access database of magnetic materials to facilitate a data-intensive machine-learning design of new rare-earth free magnets.
The database currently has over 3800 entries. The team has demonstrated that its data-intensive methods improve efficiency of the experimental fabrication of new rare-earth-free and Pt-free magnetic materials and has predicted and synthesized a set of several cobalt nitride compounds that exhibit high magnetocrystalline anisotropy and Curie temperature (necessary properties for commercial applications). In order to translate promising magnetic materials toward application, the team has partnered with the Air Force Research Laboratory and industry.