Lithium-ion rechargeable batteries rely on lithium and other rare earth metals but also pose environmental concerns, challenges for recycling, and global dependence on lithium. Microsoft collaborated with the Department of Energy’s Pacific Northwest National Laboratory (PNNL) to discover a unique material that could decrease reliance on lithium. Using AI and the Azure Quantum Elements cloud platform, the Microsoft team significantly sped up research on materials not found in nature.
Microsoft’s high-performance computing (HPC) systems allowed AI algorithms to predict new materials’ characteristics, resulting in a much faster 1,500 times prediction of materials properties compared to traditional density functional theory calculations. Starting with 32.6 million candidate materials, AI algorithms identified 500,000 predicted stable materials, which was then narrowed down to 800 potential candidates and further narrowed to 150 materials through “AI-accelerated” simulations of dynamic properties.”
Those 150 candidates were further reduced to a group of 18 top choices. Microsoft researchers pinpointed the final candidate: an electrolyte material that uses approximately 70 percent less lithium and substitutes some lithium with sodium. The new material has been synthesized by PNNL, and additional tests are planned to verify its stability and efficiency. A PNNL spokesperson stated that this AI development is crucial in addressing the global challenge of more efficient batteries.
The whytry.ai article you just read is a brief synopsis; the original article can be found here: Read the Full Article…
