麻豆app

Magnets are at the core of the technology that powers our world: smartphones, medical devices, power generators, electric vehicles, and more. But these magnets rely on expensive, imported, and increasingly difficult to obtain rare-earth elements, and no new permanent magnet has been discovered from the many magnetic compounds we know exist.

Now, UNH researchers have harnessed artificial intelligence to accelerate the discovery of new functional magnetic materials. The research, published recently in the journal , details the creation of the of 67,573 magnetic materials entries, including 25 previously unrecognized compounds that remain magnetic even at high temperatures.

鈥淏y 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,鈥� says lead author Suman Itani, a Ph.D. student in physics at UNH.

Scientists know that many undiscovered magnetic compounds exist, but testing every possible combination of elements 鈥� potentially millions 鈥� in the lab is prohibitively time-consuming and expensive.

鈥淏y 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.鈥�

Itani and his co-authors 鈥� physics professor who is Itani鈥檚 advisor, and Yibo Zhang, a postdoctoral researcher in both physics and chemistry 鈥� built an artificial intelligence system that can read scientific papers and extract those key experimental details. This data fed computer models that identified whether a material is magnetic, and how high a temperature it can withstand before losing its magnetism.

鈥淐ollecting this kind of information by hand would take an enormous amount of effort,鈥� says Itani. 鈥淥ur AI system can do it quickly and automatically organize everything into a single, searchable database.鈥�

鈥淲e are tackling one of the most difficult challenges in materials science 鈥� discovering sustainable alternatives to permanent magnets 鈥斕齛nd we are optimistic that our experimental database and growing AI technologies will make this goal achievable,鈥� says Zang.

Going forward, Zang says, the modern large language model behind this project could have widespread use beyond this database, particularly in higher education. For instance, converting images to modern rich text format could also be used to modernize library holdings.

This work was supported by the Office of Basic Energy Sciences, Division of Materials Sciences and Engineering, U.S. Department of Energy.