Microsoft and PNNL screen 32m materials with AI to find a lower-lithium electrolyte
See how this story connectsMicrosoft and the US Department of Energy’s Pacific Northwest National Laboratory used AI models and high-performance computing on Azure Quantum Elements to screen more than 32 million candidate materials, cutting them to 18 top candidates. PNNL made one of them, a solid electrolyte that replaces some lithium with sodium for up to 70% less lithium, and built a working battery with it. PNNL said the whole process took under nine months.
Why it matters
A national laboratory took an AI-screened material from more than 32 million candidates to a working battery prototype in under nine months.
- When
- 9 Jan 2024
- ID
WTA-N-2024-0018- Where
- United States
- Who
- Microsoft, Pacific Northwest National Laboratory, Department of Energy
- Topics
- Materials, Energy and power, Data centres
Summary by wheresthe.ai, from Microsoft Azure Quantum Blog and the reporting credited above. Checked against the source on 9 Oct 2026.
Source copy: download the page as saved on 18 Oct 2026 (PDF). Also held by the Internet Archive.
Cite this story
WTA-N-2024-0018: “Microsoft and PNNL screen 32m materials with AI to find a lower-lithium electrolyte.” wheresthe.ai, 9 Jan 2024. https://wheresthe.ai/d/microsoft-pnnl-ai-battery-electrolyte-2024-01/ (source: Microsoft Azure Quantum Blog).
Spotted an error? Email [email protected].