Google DeepMind has trained a deep learning model to predict the structure of over 2.2 million crystalline materials, potentially revolutionizing the development of key future technologies.
Of the new materials discovered, some 381,000 are thought to be stable, with potential applications in semiconductors, supercomputers, batteries, and more.
The AI model found thousands of new layered compounds and potential lithium-ion conductors that could be used to develop more efficient superconductors and boost the performance of EV batteries.