AI On The Hunt For Better Batteries

Two researchers, a white woman and dark-skinned man look at a large monitor with a crystal structure displayed in red and white blocks.

While certain dystopian visions of the future have humans power the grid for AIs, Microsoft and Pacific Northwest National Laboratory (PNNL) set a machine learning system on the path of better solid state batteries instead.

Solid state batteries are the current darlings of battery research, promising a step-change in packaging size and safety among other advantages. While they have been working in the lab for some time now, we’re still yet to see any large-scale commercialization that could shake up the consumer electronics and electric vehicle spaces.

With a starting set of 32 million potential inorganic materials, the machine learning algorithm was able to select the 150 most promising candidates for further development in the lab. This smaller subset was then fed through a high-performance computing (HPC) algorithm to winnow the list down to 23. Eliminating previously explored compounds, the scientists were able to develop a promising Li/Na-ion solid state battery electrolyte that could reduce the needed Li in a battery by up to 70%.

For those of us who remember when energy materials research often consisted of digging through dusty old journal papers to find inorganic compounds of interest, this is a particularly exciting advancement. A couple more places technology can help in the sciences are robots doing the work in the lab or on the surgery table.

18 thoughts on “AI On The Hunt For Better Batteries

      1. > We should value not distributing more lead to our children.

        Sure, but we live in a world where cheap solar garden lights cost a dollar. After a few months in the garden, the solar light fails, and the nicad cell starts to leak into the soil. Multiply this by thousands of gardens, parks etc and your kids are exposed to way more heavy metals than they’d get from a few hobbyists using lead solder. Unless you make your kids eat your projects I guess?

        Next time we’ll talk about lead paint, and how it’s still hidden in all those lovely old heritage buildings, until those buildings are renovated to provide homes for a new generation of families.

        Banning leaded solder is greenwashing.

  1. It’s promising that it found a similar solution than what scientists are already trying. That’s saying it might work.

    It’s depressing that it didn’t find anything other than what scientists are already trying. That’s saying it either didn’t find any significant improvements given these boundary conditions, or couldn’t find anything better because there just isn’t.

    Sodium batteries have properties that are very similar but somewhat crappier than lithium batteries. The only advantage is that they cost about half as much, which isn’t that great of an advantage. Instead of being ludicrously expensive, they’re only ridiculously expensive for most interesting uses.

    1. The iron sulfur redox flow batteries have promise, but like anything else its a tradeoff. They’re supposed to last 20+ years but can’t charge/discharge quite as fast.

      They also don’t turn into a toxic delta fire if you poke a hole in them. ESS out of Oregon is doing better than a kilowatt-hour of storage in less than a thousand square feet of space.

      1. I think you meant megawatt-hour. Per their specs they do 145kW for 8 hours or 1.16MWh in a space that is roughly two shipping containers which is really impressive.

Leave a Reply to lucaspnwCancel reply

Please be kind and respectful to help make the comments section excellent. (Comment Policy)

This site uses Akismet to reduce spam. Learn how your comment data is processed.