Posted on 08/05/2025 6:26:13 AM PDT by Red Badger
AI just helped scientists find five new materials that might outperform lithium in future batteries.
These discoveries could enable cheaper, safer, and more powerful energy storage by using elements like magnesium and zinc.
Tackling the Lithium-Ion Problem
Researchers at the New Jersey Institute of Technology (NJIT) are using artificial intelligence to address a major challenge in the future of energy storage: finding low-cost, environmentally friendly alternatives to lithium-ion batteries.
In a study published in Cell Reports Physical Science, a team led by Professor Dibakar Datta used generative AI to rapidly identify new porous materials that could transform the development of multivalent-ion batteries. These next-generation batteries rely on more widely available elements such as magnesium, calcium, aluminum, and zinc. Compared to lithium-ion batteries, which are increasingly strained by supply and sustainability concerns, multivalent-ion batteries represent a promising and more affordable path forward.
Why Multivalent-Ion Batteries Are the Future
Multivalent-ion batteries differ from conventional lithium-ion versions by using ions that carry two or three positive charges instead of just one. This allows them to store much more energy, making them a compelling option for future energy storage technologies.
The challenge, however, lies in the larger size and stronger charge of these multivalent ions, which makes it difficult for them to move efficiently within standard battery materials. The NJIT team’s AI-powered approach was designed specifically to overcome this barrier by discovering materials better suited for handling these high-charge ions.
Multivalent-Ion Movement - The open, sponge‑like network inside a porous transition‑metal oxide lets the larger, doubly- or triply-charged ions travel during a battery’s charge and discharge cycles. Credit: New Jersey Institute of Technology Turning to Generative AI for Solutions
“One of the biggest hurdles wasn’t a lack of promising battery chemistries — it was the sheer impossibility of testing millions of material combinations,” Datta said. “We turned to generative AI as a fast, systematic way to sift through that vast landscape and spot the few structures that could truly make multivalent batteries practical.
“This approach allows us to quickly explore thousands of potential candidates, dramatically speeding up the search for more efficient and sustainable alternatives to lithium-ion technology.”
The Power of Dual-AI: CDVAE and LLM
To overcome these hurdles, the NJIT team developed a novel dual-AI approach: a Crystal Diffusion Variational Autoencoder (CDVAE) and a finely tuned Large Language Model (LLM). Together, these AI tools rapidly explored thousands of new crystal structures, something previously impossible using traditional laboratory experiments.
The CDVAE model was trained on vast datasets of known crystal structures, enabling it to propose completely novel materials with diverse structural possibilities. Meanwhile, the LLM was tuned to zero in on materials closest to thermodynamic stability, crucial for practical synthesis.
Discovery of 5 Breakthrough Structures
“Our AI tools dramatically accelerated the discovery process, which uncovered five entirely new porous transition metal oxide structures that show remarkable promise,” said Datta. “These materials have large, open channels ideal for moving these bulky multivalent ions quickly and safely, a critical breakthrough for next-generation batteries.”
The team validated their AI-generated structures using quantum mechanical simulations and stability tests, confirming that the materials could indeed be synthesized experimentally and hold great potential for real-world applications.
Beyond Batteries: A Scalable Materials Revolution
Datta emphasized the broader implications of their AI-driven approach: “This is more than just discovering new battery materials — it’s about establishing a rapid, scalable method to explore any advanced materials, from electronics to clean energy solutions, without extensive trial and error.”
With these encouraging results, Datta and his colleagues plan to collaborate with experimental labs to synthesize and test their AI-designed materials, pushing the boundaries further towards commercially viable multivalent-ion batteries.
Reference:
“Generative AI for discovering porous oxide materials for next-generation energy storage”
by Joy Datta, Amruth Nadimpally, Nikhil Koratkar and Dibakar Datta, 26 June 2025, Cell Reports Physical Science.
DOI: 10.1016/j.xcrp.2025.102665
I concieved of something like this decades ago. Dang near drove me mad tinkering with it. The problem always comes with electrolytle compatability.
This will probably take decades to develop.
////
Next year’s AI is going to be several orders of magnitude more powerful than this year’s AI. Same goes for the next coupe years.
That suggests a shorter timeline to development.
Yes, you have to have a large surplus of ‘free’ electrons available to carry the current...............
It wasn’t the AI that conceived the method. Rather it was the AI that executed method that discovered the new materials.
AI is another year or more away from being able to conceive its own methods to test and then testing them.
But already the initial stages of that are underway. What’s his name from chatgpt say’s they’re about 20 percent there.
If I HAD money to invest, it would definitely be in battery tech. We have them in everything, we simply can’t live without them.
I can use it when we have a power outage as well. Not to power an entire house, but for charging cell phones, radios, and computers. 12V DC, as well as 110 V AC. It’s great battery technology.
Great so now instead of lithium fires, we’ll have magnesium fires.....
I have no doubt that batteries will power a small part of our civilization for years to come but it will not be as is imagined by the green fanatics of today. The Toyota hybrid model that uses a small ICE powering a generator that powers electric motor driven wheels is good. The ICE can also power the car if the electrics fail. No plug-in station needed.
But there are many places in the USA where the ICE is far better suited for all transportation needs.
…electric is by far the most efficient, controllable and reliable means of mechanical movement…
…diesel electric trains will be around for years to come…
…but they just don’t quite have the sex appeal for current generations…
…so hybrid with “fuel” storage for both are what is being pushed…
…the main point of contention currently is the inefficiency of electric storage…
…but it seems no thought has been given to the inherent loss of the efficiency in transferring energy through multiple means…
…having the cake and eating it too needs to be removed from the equation…
The DOD and DARPA are already getting Al+Graphene cells they have 3+ election charges per atom, can charge at 66C rates and have cycle lives in the 20,000 range. For drones of course. It’s only a matter of time before those cells make it to commercial use. Currently only the Gov can afford the Gucci expensive graphene part of the cell. When you have uncle suger money graphene at gold prices per gram don’t matter performance does. The university of Queensland has a process to bulk make graphene from methane they patented and are commercializing it should open the market for Al Gr cells right up.
These guys
https://graphenemg.com/graphene-products/graphene-aluminium-ion-battery/
Aluminum is the third most abundant element in the earth’s crust. Carbon is in the air and every living thing can be heated in a closed system and turned to carbon and ash with that ash loaded with calcium,phosphorus and magnesium too.
Virtually every rock in the crust other than carbonates are (aluminium,calcium,magnesium)-silicates, basalt of the oceans crust is Fe,Mg,Ca,Al silicates with 10-14% Al even in basalts.
Top ten by mass in the crust.
oxygen (~46.6%)
silicon (~27.7%)
aluminum (~8.1%)
iron (~5.0%)
calcium (~3.6%)
sodium (~2.6%)
potassium (~2.8%)
magnesium (~2.1%)
hydrogen (~0.14%)
titanium (~0.56%)
With silicate leaching process you can break any of the SiO4 really all of them with sulfuric acid and a halide catalyst like fluorine or chlorine where (M)=metals,[Al,Fe,Mg,Ca,T
I]..(M)SiO4 into (M)SOx aquas then precipitate out the corresponding solid sulfate.. This means you can solution mine every rock type on earth for any and all of its metal elements at will every where. Supercritical CO2 plus hot water also does a bang up job of breaking silicates apart bringing the metals up with it. You can participate metallic carbonates like sulfates it’s how some nuclear fuel reprocessing works they use carbonates not nitrates. Most of the metals form solid carbonates.
Point is with modern chemistry and human knowledge we will never be short on any element in the above list ever. The supply is limitless when you start solution mining the crust. We do this for uranium today, and we get phosphates and titanium as by products. Lithium is also solution mined and it is the origin of the Sileach process to begin with lithium silicates are clays easier to find than lithium brines.
You will never be allowed to have this car but if you were it would take you 1300 miles on a tank at 100+ mpg it returned 2.2L/100km that’s 108 freedom units per gallon.
Notice they ran the pack to zero something you would not normally do the ICE would kick on at 20% or so but they forced a zero run so all of the energy was coming from the generator and it still ran 1300 Fing miles. Impressive tech to say the least.
https://www.adamasintel.com/1300-mile-range-14000-chinese-ev-you-wont-get-in-us/
Modern power electronics are simply more efficient than automatic hydro mechanical transmissions. Especially when you only run your generator at it’s peak brake specific fuel efficiency point. This one does 45% to the pack no ICE anywhere is touching that via a hydro mechanical transmission to the wheels. The physics makes fudds big mad but it is physics after all and could careless about feelings.
I dont see why it’s so hard to grasp other than scientific ignorance. Spinning a mass of fluid around and mashing gears , clutches and bearings is lose lose and lose losses. Vs spinning a single moving part inside a magnetic field and sending those electrons to another single spinning rotor inside another magnetic field driving at most one set of reduction gears to the wheels.
The proof is in the pudding, the Camry 24 ICE gets 28 mpg city the identically sized hybrid Camry does 51 mpg game set match..boom drops Mike he is dead Jim.
So much so Toyota won’t sell you a Camry that is not driven by a EDU anymore.
Mexico is getting those BYD hybrids once the factory undone building.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.