What is it about?
To simplify and speed up the search for new potential magnetic materials our team developed and verified computer model that can predict the magnetic ordering temperature of rare earth compounds with 59 K accuracy.
Featured Image
Photo by Thomas Reaubourg on Unsplash
Why is it important?
Development of critical-materials-free magnets is crucial for sustaining the nations need in permanent magnets for power generation, EVs, and consumer electronics. We show that adding physics-based descriptors adds accuracy to the machine learning model enabling it to be used in industry and academia to find such new materials.
Perspectives
This is the first step, but it is an important one. There remains wide skepticism about use of ML for materials science especially for predicting magnetic properties of intermetallic compounds. The hope is that the success of our work will spur more investment in ML discovery of new energy relevant materials.
Dr. Yaroslav Mudryk
Iowa State University
Read the Original
This page is a summary of: Physics-Informed Machine-Learning Prediction of Curie Temperatures and Its Promise for Guiding the Discovery of Functional Magnetic Materials, Chemistry of Materials, August 2023, American Chemical Society (ACS),
DOI: 10.1021/acs.chemmater.3c00892.
You can read the full text:
Contributors
The following have contributed to this page
