Microsoft has collaborated with the Pacific Northwest National Laboratory (PNNL) to leverage artificial intelligence (AI) for the rapid identification of a material that could potentially lead to batteries requiring 70% less lithium.
According to Reuters, the breakthrough involves replacing much of the lithium with sodium, a widely available and inexpensive element found in table salt.
While the shift to sodium still requires thorough evaluation by scientists at PNNL to determine its viability for mass production, the process has showcased the power of AI in accelerating materials discovery. The collaboration has significantly compressed the timeline for identifying potential solutions from years to just two weeks.
The breakthrough involved a combination of AI models trained on molecular science data and traditional scientific supercomputers. Microsoft’s AI narrowed down more than 32 million possibilities to 18 candidates, which were then examined by PNNL scientists for synthesis and testing in a lab.
Jason Zander, Executive Vice President at Microsoft, expressed excitement about the rapid progress, stating, “Something that could have taken years, we did in two weeks. That’s the part we’re most excited about… We just picked one problem. There are thousands of problems to go solve, and it’s applicable to all of them.”
This innovative technology has broader implications, potentially impacting various sectors such as automotive, energy grids, and any other applications that rely on batteries.
By reducing reliance on lithium, which is expensive and concentrated in a few countries, and increasing the use of sodium, a cheap and abundant element, the technology could address resource constraints in battery production.
Brian Abrahamson, Chief Digital Officer of PNNL emphasized the transformative potential of AI, stating, “The magic here is in the speed of artificial intelligence, assisting in the identification of products and materials and our ability to put those ideas into action in a laboratory. All of that being brought to bear at the disposal of an individual scientist – this is a paradigm shift that we’re looking at. To us, it holds tremendous promise.”