AI Discovery of New Material Reduces Lithium
Through collaborative efforts of artificial intelligence (AI) and supercomputing technologies Discovery of New Material Reduces Lithium, an unprecedented material with the potential to reduce the reliance on lithium in batteries has been identified.
Microsoft and the Pacific Northwest National Laboratory (PNNL), a component of the U.S. Department of Energy, teamed up to make these discoveries. Scientists believe that this new material can reduce the use of lithium by 70%.
Since its discovery, the novel material has been successfully used to power lightbulbs. Microsoft researchers used AI and supercomputers to rapidly narrow down 32 million potential inorganic materials to 18 promising candidates in under a week. This screening process, if done through traditional laboratory research methods, could have taken more than two decades.
Remarkably, the entire process from material identification to the development of a working battery prototype took less than nine months. This accelerated timeline was made possible by leveraging advanced AI and high-performance computing, combining multiple computers to solve complex scientific and mathematical tasks.
Microsoft Executive Vice President Jason Zander emphasized the tech giant’s mission to “wrap 250 years of scientific discovery into the next 25 years.” He expressed confidence that technologies such as AI and supercomputing will play an important role in achieving this goal, saying, “I think this is how this type of science is going to develop in the future.”
The challenge associated with lithium
Often called “white gold” because of its market value and silvery color, lithium plays a vital role as one of the primary components in rechargeable batteries, particularly lithium-ion batteries. These batteries power a variety of devices, from electric vehicles (EVs) to smartphones.
The International Energy Agency has warned that surging demand for lithium driven by the growing popularity of EVs could lead to a shortage of the material as early as 2025. Additionally, the U.S. Department of Energy projects a tenfold increase in demand for lithium-ion batteries by 2030, prompting manufacturers to build additional battery plants to meet this demand.
However, lithium mining is not without controversy. This process could take many years to develop and would have a large environmental impact. Extraction requires significant amounts of water and energy, leaving scars on the landscape and producing toxic waste.
Dr. Nuria Tapia-Ruiz, who leads a team of battery researchers in the Department of Chemistry at Imperial College London, emphasizes that materials with low lithium content and strong energy storage capabilities are in high demand in the lithium-ion battery industry.
Also Read: American XL Bully Ban in Scotland
He predicts that AI and supercomputing will become indispensable tools for battery researchers in the coming years, aiding in the prediction of new high-performance materials.
However, Dr Edward Brightman, lecturer in chemical engineering at the University of Strathclyde, advises caution in adopting this technology. He warns of possible spurious results or initially promising results that may later prove to be impractical with known materials or to be synthesized in the laboratory.
The AI-derived material, currently named N2116, represents a solid-state electrolyte that has been tested by scientists from its raw material stage to its functional prototype. With the ability to be a permanent energy storage solution, solid-state batteries like the N2116 are considered safer than traditional liquid or gel-like lithium batteries.
The prospect of fast-charging solid-state lithium batteries shortly promises even greater energy density and thousands of charge cycles.
What sets this AI apart?
The technology operates using a new form of AI developed by Microsoft trained on molecular data capable of understanding chemistry.
Microsoft’s Mr. Zander explained, “This AI is completely rooted in scientific materials, databases, and properties. The data is highly reliable for scientific discovery.”
Once the software identified 18 potential candidates, PNNL’s battery experts examined them and selected the final substance for laboratory work.
PNNL’s Karl Mueller emphasized that Microsoft’s AI insights have significantly sped up the process, pointing them to “potentially much faster fruitful areas” than traditional methods.
Join YouTube channel: weekly wakeup
