Microsoft is using artificial intelligence to try to revolutionize battery technology.
It cuts thousands of hours
Apple is certainly working on the same thing, as we reported in November of last year: “Custom-made batteries must have been in development since 2018, with patent applications and new employees associated with the project in the works. It should be a matter of some sort.” “Brand new” batteries with much better performance than is possible now.”
Now the arch-rival has reported that they are using AI to try to find new materials for battery cells, and they are using the opportunity to create PR about Azure Quantum and of course the AI project you won't miss this year.
“The AI is fast, but it's not completely accurate. The next set of filters I used is 'HPC', which provides high accuracy but uses a lot of computing power. This makes it a good tool for a smaller set of filters. Use HPC First Check Density functional theory calculates the energy of each substance relative to all the other states it could be in. We then ran molecular dynamics simulations that combine artificial intelligence and high-performance computing to analyze the motions of atoms and molecules within each substance.
Using Azure, artificial intelligence, and extremely fast hardware, Microsoft was able to narrow the list of materials down to just 150 materials, then run the machines for another 80 hours: the list was then whittled down to 18 candidate materials. Whether these technologies can accelerate battery technology, it is too early to say anything about it, as it is just one factor among many. Regardless, it demonstrates, in its infancy, what AI can be used for and perhaps how revolutionary it is.
“Explorer. Unapologetic entrepreneur. Alcohol fanatic. Certified writer. Wannabe tv evangelist. Twitter fanatic. Student. Web scholar. Travel buff.”