Researchers used AI to design a new material that they used to build a working battery – it requires up to 70 percent less lithium than some competing designs.
They designed and built a battery that uses up to 70 per cent less lithium than some competing designs.
This is probably a way of phrasing that means it's up to 70% less than the absolute most lithium-requiring designs that few/no one uses, and probably only marginally better than most designs actually used. Since they're very vague about it, I will be sceptical and assume it is way less revolutionary than the headline suggests.
Also, lithium is of pretty low concern when it comes to the materials in current cells. Stuff like cobalt and nickel are more critical and would be larger news.
LFP batteries are both nickel and cobalt free, and are being used in production cars right now (e.g. Tesla model 3/Y standard range options). That technology has long arrived.
this work does nothing to address this, and they also include yttrium, because they focus on solid electrolytes for some reason (probably because chemical space is smaller)
Also, AI would have just sped up an existing plan they had to try new approaches because AI doesn't create new ideas or think of things out of nowhere.
If you tell AI to do things within a certain range and it gives you results then AI came up with a design as much as google came up with search results when you put something into the search bar.
It can apply existing concepts in ways we haven't thought of. AI has been used for exactly this thing for years in chemistry. When given constraints (less lithium) and parameters (with this much capacity) it can try permutations of various designs that theoretically meet those conditions.
Yes AI is overhyped, yes it's often exaggerated by news sources, but that doesn't mean AI is a non-invention or something. It's a long way off from any of the lofty goals that are often thrown around by tech ceos, but that doesn't mean it's useless.
That's not true at all. AI can in fact generate novel techniques and solutions and has already done so in biotech and electrical engineering. I don't think you understand how AI works or what it is
That's the point, it takes all the factors we know about and speed runs through all the possible ways it could work. Humans don't have the time to look for every single possible way a battery could be constructed, but a ML model can just work it's way through the issue faster and without human intervention.
Plus just like with the new group of antibiotics we just used AI to discover, it will allow truly thinking Humans to expand upon it.
Really sick of this "oh but you don't realize AI don't actually think! Therefore it's all worthless!" With this smug bullshit like you think you're bringing anything of value to the conversation.
What a terribly ignorant thing to say, when people make these armchair comments they’re only hurting ordinary people that can make real benefits from using the technology.
you would know that if you read the article. they replaced part of lithium in electrolyte with sodium, so that they can use less lithium. the problem is decreased ion mobility ie less power density in real life terms.
Baker and Murugesan both say that lots of work is left to optimise the new battery.
bet
i'm gonna mostly ignore this finding because it sounds like extension of AI hype. real lab work is still absolutely critical in order to make it work
And then there's a hundred other factors. How many charge cycles does it get? Cold weather performance? Can it be mass produced? Does it improve safety over current cells?
It might be useful for what it leads to. Batteries get better because we explore ten different options and then one of them works out. People have gotten less excited over individual discoveries like this for mostly fair reasons. But then there's another layer of understanding beyond that where you see it as one path of many.
Let's see if this one isn't total bullshit like the 3646263841 ones before it!
Seriously this is getting ridiculous, I've seen these some literally 40 years ago, 99.99% is bullshit, and now I'm seeing literally over 5 new articles per week.
ITS BULLSHIT.
Call me when there is an actual battery based off peer reviewed research that has been successfully tested in production systems by at least 5 major companies. Until then, BULLSHIT.
The main problem is just that getting a product from a one-off in a lab to a cost-competitive mass-market product is hard and can take a lot of time, to say the least.
It's less that these breakthroughs are bullshit, and more that commercializing these things is hard. The articles about the breakthroughs are often bullshit, though, or at least way too rosy.
I wonder if novelty products can be made with the one-off batteries. Imagine a $3000 flagship phone but it had 3x the battery capacity of the normal flagship phone while having the same weight and volume. I'd bet some people would pay for that.
A few years ago I completely checked out of all the future tech hype. A million videos and articles about the next big thing and nothing ever comes to fruition.
The article says they were searching for new solid electrolytes... which are meant to be incredibly thin, so they contribute a negligible amount to the total lithium need. It's far more important to look for ones with a high conductivity to compete with liquid electrolytes.
Yeah, that's been my take on pretty much every single battery article I've read, going back to the 90s. like 2 out of 100s has actually come to market.
Tech like this needs to perform well, be economical, and scalable for manufacturing. Articles come out usually when tech hits the first one or two, but very rarely do all 3 end up true.
But the ones currently in commercial production didn’t come out of nowhere. There were lots of incremental improvements that didn’t make headlines. What you see in tech articles is just a thin slice of the whole story.
"His team built a working battery with this material, albeit with a lower conductivity than similar prototypes that use more lithium."
I do know that because of Ohm's law, this directly translates to less available current than conventional electrolytes. There's not enough info to determine mAh though.
Yeah, batteries internal resistance is a huge factor in their usability and the speed they charge.
Especially in the modern day where a lot of their use is towards high amperage applications like cars.
People need to understand tho, Lithium batteries are usually only about 11% lithium, Lithium Ion batteries are mostly Cobalt and other metals. So at most you're replacing 6% of a batteries total mass.
They used the AI to narrow 23 milliom candidate materials down to a few hundred, then focused on testing the ones out of that set that hadn’t been tested yet.
In terms of AI speeding up research this is enormous.
I wish I had a solution. But its the same with all shitty titles, you have to hope people click and read the article/comments in order to get the nuanced information.
I hate those sensationalist titles that portrait AI as if some sort of sentient being, and not just a tool the researchers used. The secondary title should have been the main one.
Yes, it is just using our Data bases. what people are calling AI is a chat bot on Steroids and Meth with lots of stolen data, if the mass lawsuits win, a lot of this AI Stuff will be gone overnight.
Every time we get one of these articles we see some advancement in battery tech. But that is usually superseded by the amount of power hungry components new tech uses. So phones have gotten more complex with more power hungry components and every time we improve battery tech, the tech giants engineers figure out a way to utilise that new tech to cram more power hungry components inside and that's why batteries don't last as long as we remember.
There's no need to get excited. Even if we end up using this in new gadgets, you're not going to see an improvement in battery life.
On my S10E I could adjust the CPU power limit to 80%. I had great battery life. Like two days of battery life. Until one android update when it went away.
This is why we need to change the way we do things every few years, move faster than our waste stream.
Which is faster turning your phone on and checking your email or turning your desktop on and checking your email? Which lasts long your cellphone battery or your laptop battery? Which has more free software that has been vetted for problems in one location your computer or your cellphone?
It isn't that your phone is better, it is not, it has just not yet become shitty. Give it time, and then move on to the next thing. The thing that hasn't yet been shat on.
Not really sure what your comment has to do with the article.
The headline is a battery that uses less lithium, not a battery that generates more voltage, has a longer life, or is otherwise better at powering things. The advancement here is a materials advancement that we desperately need as lithium is a finite resource.
In response to the naysayers who don't think we ever use these battery technologies that we developed. The people in the comments of this post specifically.
As soon as they figure out how to actually mass produce them at an affordable price, and fix the swelling issues during high charging currents, they'll be available.
this article is about changes to solid electrolyte only, you'd know that if you read the article. these have less conductivity ( = lower power density) tho
And have better capacity and a longer life?
it took 9 months of real lab work by real material scientists just to make it work, things like dendrite formation or swelling aren't part of this optimization (well at least AI stage), the linked preprint doesn't even mention dendrites once
It stood out because half of what Murugesan would have expected to be lithium atoms were replaced with sodium.
This isn't new I think. Sodium-ion batteries were already known. Maybe there was still dendrite formation and this recipe might reduce or eliminate that? We'll have to wait and see.
In any case, if it can drastically reduce lithium usage that would be good progress.
I want a semi-solid state batter that turns kinetic energy into stored charge. I want to be able to drop it on the ground, fire a .45 round into it, and have it immediately be fully charged.
The issue of eliminating cobalt is specific to Lithium batteries as without it lithium likes to grow dendrites which then causes a short.
And cobalt really wouldn't be much of an issue if the Congo wasn't the shithole that it is, it has over 50% of known reserves. Even with addressing child labour making definite inroads "artisanal" and "mining" isn't something you generally want to hear in the same term short of say gold panning (hey that's even a hobby for some), as soon as mine shafts get involved it's a recipe for disaster. Australia, Cuba, the Phillipines, Russia and Canada all have very significant deposits.
[Edit: Maybe it's cobalt I was thinking of. But one problem I'm sure about is that lithium demand is predicted to be greater than the supply of lithium batteries continue to grow in popularity.
I work in a lithium mine, we make big rocks into little rocks the same as any other. What's the problem? Unless you're against mining in general, hard rock lithium should be fine
Yes do look into it. There are MANY ways to harvest lithium and most are better than what the oil and gas companies does when fracking or drilling on land.