AI System Discovers 25 New Magnetic Materials That Could Replace Rare Earth Elements
University of New Hampshire researchers used AI to scan 67,000+ compounds and found 25 high-temperature magnets that could reshape the clean energy supply chain.
The quest for sustainable alternatives to rare earth magnets just took a massive leap forward, thanks to artificial intelligence.
Researchers at the University of New Hampshire, led by doctoral student Suman Itani and Professor Jiadong Zang, have built an AI system that scanned a database of 67,573 magnetic compounds and identified 25 previously unrecognized materials that maintain their magnetic properties at high temperatures — a critical requirement for real-world applications.
The system works by reading scientific papers to extract experimental data, then training predictive models to forecast magnetic properties without expensive laboratory testing. What would have taken decades of manual lab work — testing millions of potential element combinations — was accomplished in a fraction of the time.
Why This Matters
Rare earth elements are essential for everything from electric vehicle motors to wind turbines, smartphones, and MRI machines. But the supply chain is fragile and geographically concentrated, creating both economic and geopolitical risks. Finding viable alternatives has been one of the most pressing challenges in materials science.
These 25 newly identified materials could provide exactly that — high-performance magnets made from more abundant and accessible elements.
The Bigger Picture
The project, funded by the U.S. Department of Energy's Office of Basic Energy Sciences, demonstrates something profound about where AI is headed: it is not just generating text or images, but accelerating fundamental scientific discovery.
By systematically mining decades of published research and finding patterns that human researchers might miss, AI is becoming an indispensable tool in the laboratory. The implications extend far beyond magnets — this same approach could be applied to superconductors, battery materials, catalysts, and more.
For the clean energy transition, this is exactly the kind of breakthrough that turns ambitious goals into achievable timelines.
More AI Stories
Intel Diamond Rapids Packs 256 Cores for Agentic AI
Intel's Hot Chips 2026 lineup pairs a 256-core Diamond Rapids Xeon with Crescent Island, a 350W inference GPU holding up to 480GB of LPDDR5X.
Nvidia Vera Rubin NVL72 Targets 30x Tokens Per Watt
Nvidia detailed the Vera Rubin NVL72 rack at Hot Chips 2026: 72 GPUs, 2 ZFLOPS of NVFP4 inference and up to 30x more tokens per megawatt.
Edge AI Model Zoo Logs 837 Reproducible NPU Tests
EdgeFirst's new model zoo publishes 837 validation sessions for YOLO models across NXP, Hailo, Jetson, Qualcomm and Apple Neural Engine hardware.