AI Finds 25 New Magnets to Replace Rare Earth Elements

Scientists just used artificial intelligence to crack open a treasure trove of magnetic materials that could transform how we power everything from smartphones to electric cars.

Researchers at the University of New Hampshire taught an AI system to speed-read through decades of scientific papers, hunting for magnetic compounds. The result? A searchable database containing 67,573 magnetic materials, including 25 that no one knew about before.

What makes these newly discovered materials special is that they stay magnetic even at high temperatures. That's crucial for real-world applications like power generators and medical devices.

The breakthrough comes at a critical time. Today's strongest permanent magnets depend heavily on rare earth elements that are expensive, mostly imported, and increasingly hard to secure. Despite knowing many alternatives exist, scientists haven't found a practical replacement that works as well.

"By accelerating the discovery of sustainable magnetic materials, we can reduce dependence on rare earth elements, lower the cost of electric vehicles and renewable energy systems, and strengthen the U.S. manufacturing base," said Suman Itani, a doctoral student in physics who led the study.

The team's approach solves a major problem in materials science. Testing every possible combination of elements in a lab could take years and cost millions of dollars. Instead, the AI extracts key details from published research and feeds them into computer models that predict which materials will work best.

The new resource, called the Northeast Materials Database, is now available for researchers worldwide. Anyone can search through it to find promising candidates for their work.

The Ripple Effect

This discovery could touch nearly every part of modern life. Electric vehicles could become more affordable without expensive rare earth magnets. Wind turbines and solar systems could cost less to build and maintain. Even everyday items like headphones and laptop speakers might get cheaper to manufacture.

The research team, which also includes postdoctoral researcher Yibo Zhang and physics professor Jiadong Zang, published their findings in Nature Communications. They received support from the U.S. Department of Energy.

Beyond magnets, the AI system could help modernize entire library collections by converting old images and documents into searchable digital text. Universities are already exploring how to use the technology in education.

"We are tackling one of the most difficult challenges in materials science, and we are optimistic that our experimental database and growing AI technologies will make this goal achievable," said Zang.

The path to rare-earth-free technology just got a whole lot shorter.