Microsoft and the Pacific Northwest National Laboratory (PNNL) used artificial intelligence to find a revolutionary new battery material. Their scientists say it could reduce the lithium consumption of batteries by up to 70%. Jason Zander, the executive vice president of Microsoft, told BBC the company wants to “compress 250 years of scientific discovery into the next 25.”
The computing giant’s latest discovery is an excellent example of innovations driving other innovations. Microsoft developed an artificial intelligence due to the success of ChatGPT, which eventually led to this tool that discovers new materials. Soon, this program may improve electric cars and other green technologies, and Elon Musk agrees!
This article will discuss how Microsoft’s artificial intelligence discovered this new battery component. Later, I will elaborate on a similar tool from Google.
How did they discover this new battery material?
Microsoft used its Azure Quantum Elements (AQE) to find battery materials that require less lithium. AQE is a platform with high-performance computing and AI.
Their artificial intelligence suggested 32 million candidates, and then it discerned which ones were stable enough to use. Consequently, it cut down the number to roughly 500,000.
Next, the researchers added filters to estimate how each material might conduct energy. They also simulated how molecules and atoms move within each material and assessed their cost and availability.
Eventually, the Microsoft experts only had 23 candidates, of which five were already known materials. Then, the Pacific Northwest National Laboratory synthesized one promising substance to test it.
PNNL produced a working battery from it to power a lightbulb and clock. Most importantly, the material has a combination of lithium and sodium.
Sodium is the main component of salt, making it an abundant element. Microsoft says the new material could cut down the lithium used in batteries by 70%.
The Verge says it could become part of a solid-state battery safer than today’s lithium-ion batteries. They contain liquid electrolytes with a higher overheating risk. PNNL staff scientist Vijay Murugesan and other experts praised the AI platform’s capabilities:
You may also like: World’s most powerful X-ray laser fired
“Thirty-two million is something that we would never ever be able to do … Imagine a human sitting and going through 32 million materials and choosing one or two out of it. It’s just not going to happen,” said Murugesan.
Microsoft CEO Satya Nadella posted an article about the new battery material on X, to which Tesla CEO Elon Musk responded by saying, “Interesting.” After all, Tesla vehicles run on lithium-ion batteries.
Financial news outlet Benzinga said the battery is the most expensive part of an EV. As a result, these automobiles are more expensive than conventional combustion engine vehicles.
How does Google use its AI material program?
Microsoft isn’t the only one that uses artificial intelligence to find new substances. Google DeepMind also has one that may find another battery material and more.
That Google division used data from the Lawrence Berkeley National Laboratory (LBNL) and other sources to train its artificial intelligence. It calls the program the Graph Networks for Materials Exploration or GNoME.
GNoME uses two deep learning models that represent atoms and bonds in a molecule as a graph. The first uses known crystal structures and substitutes elements with others to produce candidate structures.
On the other hand, the other uses the candidate’s chemical formula or composition to rate its stability. Then, it filters the candidate pool and evaluates them with quantum mechanics simulations.
Later, it returns the information to the model to complete an active learning training loop. DeepMind’s materials discovery leader, Ekin Dogus Cubuk, said the program found AI materials “which have proven to be difficult for human scientists.”
You may also like: ChatGPT Experience More Valuable Than College Degree
More importantly, this artificial intelligence could generalize beyond its training, improving its results. “If we really want to use these tools for discovery, we want to look where we haven’t looked before,” said Keith Butler, a professor of computational materials chemistry at University College London.
Of course, we want AI materials to work in real life. However, these tools usually don’t explain why they made specific combinations. “If you can ask the model, ‘What is it that made you make this decision?’ That is where you can get new knowledge,” Butler added.
Olexandr Isayev, a chemistry professor at Carnegie Mellon University, said some types of scientific experimentation are “really amenable for automation with machine learning and AI.” Also, he added, “Software plus hardware” is where “the next advances in the sciences are going to be.”
Conclusion
Pacific Northwest National Laboratory (PNNL) and Microsoft recently used artificial intelligence to find a new battery material that reduces lithium usage by 70%. As a result, it could make electric vehicles cheaper and safer than ever.
Krysta Svore from Microsoft Research revealed the AI’s long-term purpose. “We need to really compress the next 250 years of chemistry material science into the next two decades, right?”
“And that’s because we want to save our planet,” she added. Learn more about the study at Microsoft. Also, check out the latest digital tips and trends at Inquirer Tech.