PhD student develops brain-like technology that could solve dangerous issue with electric vehicles: 'Orders of magnitude faster'
In a new study published in npj Computational Materials, researchers, including a Ph.D. student from Skoltech and AIRI Institute, demonstrated how neural networks can significantly accelerate the discovery of solid electrolyte materials. This advancement could address one of the biggest hurdles in EV battery design: creating batteries that are safer, longer-lasting, and capable of holding more charge while reducing fire risks.
Data shows that traditional internal combustion engine vehicles already have a much higher fire hazard risk than EVs.
Solid-state batteries are a highly anticipated successor to traditional lithium-ion EV batteries. Instead of using flammable liquid electrolytes, solid-state batteries utilize ceramic or other solid materials to move lithium ions between electrodes. These materials offer greater stability, enabling faster charging, longer ranges, and improved safety.
However, most known solid electrolytes do not yet meet all the technical requirements for commercial EVs. Researchers are now using artificial intelligence neural networks to predict new materials with high ionic mobility at speeds far surpassing traditional trial-and-error methods.
"We demonstrated that graph neural networks can identify new solid-state battery materials with high ionic mobility and do it orders of magnitude faster than traditional quantum chemistry methods," explained Artem Dembitskiy, the lead author of the study and a Ph.D. student at Skoltech. "Machine learning lets us screen tens of thousands of materials in a fraction of the time."
This innovative approach has helped the team identify two promising new protective coatings that could stabilize next-generation batteries and prevent dangerous short circuits.
The potential of solid-state batteries is significant: Some automakers estimate they could offer up to 50% more range compared to today's EVs, along with reduced fire risk and longer battery life. This translates into lower long-term maintenance costs and fewer battery replacements.
This research builds on previous AI-assisted breakthroughs in EV battery technology, fueling solid-state battery innovations that could enable EVs to last a decade longer than current battery technology.
Pairing these high-efficiency EVs with home solar can drive savings even further. By charging at home using solar energy, drivers can lower their electricity bills and easily compare rates on sites like EnergySage.
If you were going to purchase an EV, which of these factors would be most important to you?
Cost
Battery range
Power and speed
The way it looks
Click your choice to see results and speak your mind.
Considering an EV as your next car? You could save over $1,500 a year on gas and maintenance as well as receive Inflation Reduction Act tax breaks and credits, up to $7,500 through Sept. 30, while reducing planet-warming pollution and avoiding high gas prices.
While these solid-state batteries are not yet ready for mass-market EVs, AI tools like these are helping us get there faster. This breakthrough could enable automakers to reduce their reliance on nonrenewable fuels and create a cleaner, more affordable future for drivers everywhere.
Join our free newsletter for weekly updates on the latest innovations improving our lives and shaping our future, and don't miss this cool list of easy ways to help yourself while helping the planet.
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Yahoo
6 hours ago
- Yahoo
GM wows with Corvette, Cadillac concepts at Monterey Car Week
CARMEL, Calif – GM brought some Detroit muscle to the rarified air of Monterey Car Week — with a twist. While the Corvette nameplate falls under the Chevrolet brand, more and more it stands out on its own. At The Quail event in Carmel Valley, where multi-million dollar Paganis are displayed alongside priceless gullwing Mercedes SL coupes (and the parking lot is a show in and of itself), Corvette showed off two concepts that showed where the sportscar is headed in the future. The CX and its racing-inspired twin the CX-R, evoke supercar looks that go beyond the current 'C8' Corvette. The two concepts feature fighter jet-style interiors, with a trick canopy opening to boot. The twist — the CX is all electric, which is becoming a rarity at the higher end, and the CX-R features hybrid power. The racy CX-R will also be a drivable car in the Gran Turismo 7 racing game on PlayStation. And the response, beyond the oohs and ahhs, was strong for vehicles that aren't going on sale. 'We've had a number of customers that have already said, 'Could we buy one of those vehicles today?,'' said Rory Harvey, EVP and President of Global Markets, from the Quail Event to Yahoo Finance. Harvey, who essentially leads on all GM brands globally, noted that customers were asking to buy a vehicle with no pricing info, and wouldn't even be released. It was a good opportunity though, to collect future client info from buyers who typically own multiple cars. 'Just listening to the customers, the enthusiasts that are on the stage, I mean, the feedback is outstanding,' Harvey said. The UK-born exec noted that Corvette, in his opinion, was already at supercar levels, with competitive lap times at places like the Nurburgring in Germany, and 38% market share in the luxury sports car segment, making it the leader. Harvey's purview extends to Cadillac, where the luxury brand showed off its 'Elevated Velocity' concept, a cross-over style EV SUV meant to evoke the high-desert landscape. The new design language may hint at more curves and swooping design, as opposed to Cadillac's traditional angular features and vertical light bars. Regardless, Cadillac as a brand has been on a winning streak with its combination of traditional gas powered cars like the Escalade and CT5 sedans, and EVs like the Lyriq and Optiq. 'Cadillac now has done 12 consecutive quarters of year-on-year growth, which is absolutely superb. But in quarter two, Cadillac is now the number one luxury brand for EVs. So again, that's really, really strong,' Harvey said. 'We've launched so many new products over the course of the last two years, and that momentum continues to build. So we're looking at, how do we keep our foot on the accelerator pedal and build even further?' Harvey said he wasn't terribly concerned over the upcoming loss of the EV tax credit, because the brand would be able 'flex' into its other gas-powered offerings like the XT crossovers if its EVs were not price competitive. While a nice game plan, it doesn't address the fact the company invested heavily in EVs, and might take a hit to sales. Another challenge is tariffs, where GM took a big hit in the second quarter and stands to feel more pain in the second half of the year. Harvey noted the trade deals in place are mostly preliminary, so when the details come out the company will have a hard look at its manufacturing footprint, product portfolio in terms of territory, and where the company can minimize its tariff exposure. 'We've publicly stated that we believe that we can mitigate approximately 30% of the impact of tariffs; so, we're in a strong position at the moment,' Harvey said of GM's ability to pivot around President Trump's tariff war. Harvey still believes GM is in a great spot regardless of tariffs, and it's because of products like the current Corvette and Cadillac portfolio — cars that are selling well in the marketplace. 'If you looked at just General Motors sales in the US, we are the fastest growing brand, full stop. And if you look to the nearest competitor, they're about half the level of growth that we've got. So customers love our products.' Pras Subramanian is the lead auto reporter for Yahoo Finance. You can follow him on X and on Instagram. Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
Forbes
6 hours ago
- Forbes
AI Agent Types
In the big conversation that companies and people are having about AI agents, one of the major points is around the various different types of agents that we classify into different categories. In other words, there are AI agents, and there are AI agents. Some are fairly rudimentary – while others are extremely sophisticated and skilled. Another way to think about this is that neural networks are not the same as human brains: they're much more heterogenous. They didn't evolve collectively over millions of years, so they may not look like each other in the same ways that human brains do. That said, one of the biggest differences between AI agents is their memory. Stateful systems have some sort of recollection of data – it provides ongoing context for their work. By contrast, stateless systems just start over every single time a user session begins. You'll see the difference in a chatbot or AI agent that either remembers your history, or sees you as a brand new person each time you interact. Seven Types of Agents It also helps to think about AI agent memory within the framework that has developed to distinguish agent types. Experts like to classify AI agents in these seven categories:In terms of memory, perhaps the best distinction is between the first two types – simple reflex agents, and model-based reflex agents. An author simply named Manika at ProjectPro describes an example of a simple reflex agent this way: 'An automatic door sensor is a simple reflex agent. When the sensor detects movement near the door, it triggers the mechanism to open. The rule is: if movement is detected near the door, then open the door. It does not consider any additional context, such as who is approaching or the time of day, and will always open whenever movement is sensed.' And a model-based reflex agent this way: 'A vacuum cleaner like the Roomba, one that maps a room and remembers obstacles like furniture (represents a model-based agent). It ensures cleaning without repeatedly bumping into the same spots.' (Manika actually cites input by Andrew Ng at Sequoia, someone we've had on Imagination in Action forums and interview panels). Essentially, the stateful AI agent relies on having that consistent memory for specific capabilities. Daffodil provides these characteristics of a stateful agent:You can see how having the framework and context drives things like perceiving a shift in user intent, or leveraging a task or purchase history to predict a future outcome or preference. Acting Like Humans In a recent TED talk on the subject, Aditi Garg began with the idea of reconnecting with an old middle school friend: 'That's the beauty of human relationships, the fact that we don't have to reintroduce ourselves,' she said. 'We don't have to explain our inside jokes or our favorite stories. We just pick up where we left off. It's effortless, it's personal. It's what makes friendships so meaningful.' Contrast this with the current capabilities of an AI system that doesn't have vibrant memory…AI today, it can unpack physics, it can summarize books,' Garg added. 'It can also … compose some symphonies, but the moment you open a new chat window, it resets. It's like talking to a brilliant mind, but with amnesia. Machines can reason, but they still cannot remember.' Reimagining Memory Garg went over some of the ways that we are used to thinking about memory, with a suggestion that changing the framework will be useful in adding memory to AI systems. 'On a very fundamental level, we think of data as like a vast digital library with bytes and bytes of information that you can access,' she said. That idea, she noted, may need to be worked on. The memory of AI will need to be accessible in real-time, flowing through the system in the same ways that our own memory is instantly recalled by our biological brains. Making the analogy to a Ferrari that need to be refueled every lap of a race, Garg talked about how AI operations will waste enormous amounts of time trying to access these parts of an AI agent's system. On the other hand, she said, new systems will have immediate, transformed statefulness. 'If an AI system can access any piece of information, it can literally never forget. If it can maintain context across conversations (and) projects … the same storage breakthrough that keeps GPUs fed is the breakthrough that will keep your AI memory alive.' That goal, Garg suggested, has to do with locating the memory and the compute in the same place. Data Centers and Colocation Design I've seen this played out in data center plans where engineers actually put the data and the operations in the same place, along with the energy or power source. You can think of a mini data center sitting next to a nuclear power plant, with the storage banks tied directly into a centralized LLM that will use that data to its advantage. What do you get with these systems? We stand at the threshold of AI that remembers,' Garg concluded. 'When the speed of remembering finally matches the speed of thinking, we enable AI that transforms from a brilliant mind with amnesia, (to) your digital twin.' That might be the next big innovation in machine learning and artificial intelligence – you'll see the same models that you interact with today, endowed with better memory, and they'll seem smarter and more 'with it', because they will know a lot of the things that you would expect them to know if they had the memory of a human brain. By the way, it's a really good idea to know those seven kinds of AI agents, since they're going to remain part of the conversation for a long time to come. What do you see as the next major advance in AI?
Yahoo
9 hours ago
- Yahoo
Why Aren't More People Talking About This Big News About an Nvidia Partner?
Key Points The electric vehicle market will eventually improve, and is the future of the auto industry. ON Semiconductor is seeing signs of stabilization in its end markets. Its Nvidia partnership in data centers is an example of growth opportunities outside of the auto market. 10 stocks we like better than ON Semiconductor › ON Semiconductor (NASDAQ: ON) and Navitas Semiconductor (NASDAQ: NVTS) were both named as companies Nvidia is partnering with to develop the next generation of data centers. Navitas is a loss-making company that isn't likely to be profitable until 2027, andng company trading at a very attractive valuation. Navitas' stock is up 89% so far this year as I write this, while ON Semiconductor's is down almost 19%. Go figure. Why isn't ON Semiconductor attracting more investor attention? The comparison made above isn't to be critical of Navitas. It's a company with a big future, and the Nvidia partnership will likely be a needle mover for a small loss-making company. Instead, the focus is on highlighting what a good long-term value ON Semiconductor looks like right now. There's little doubt as to the reason why ON Semiconductor's stock price has been so weak over the last year (down 28%). The company's core market is in silicon carbide (SiC) chips, an end market dominated by the auto industry and electric vehicles in particular. Consequently, when the EV market suffers a sustained downturn, with expectations lowered throughout the year, then ON Semi will also suffer downward revisions to expectations. That's precisely what's happened this year. As the chart below demonstrates, sales to its automotive-related end market continue to experience year-on-year declines. Unfortunately, there's little the company can do about relatively high interest rates, which make it more expensive to buy autos, or the automakers' response in cutting production plans. Three reasons why a turnaround could be coming soon However, investors are likely too pessimistic about the company's prospects, and ON Semiconductor's recent earnings report and some news items highlight that. First, CEO Hassane El-Khoury has consistently taken a cautious approach to guidance during the downturn. Still, he noted on the last earnings call, on Aug. 4, that "we are seeing signs of stabilization across our end markets." Indeed, if you look closely at the chart above, you can see that, while the year-over-year comparison remains negative, revenue grew on a sequential basis (quarter-to-quarter). That's a positive sign of a recovery building. Moreover, El-Khoury told investors that automotive revenue was better than expected in the second quarter and he expects it to grow "in the third quarter with continued EV ramps." Second, the Nvidia partnership highlights the potential in the company's industrial-based sales. As El-Khoury noted when discussing the need for AI infrastructure, notably power, "onsemi is the only broad-based U.S. power semiconductor supplier addressing this challenge with our intelligent power semiconductors, dramatically increasing power density and reducing energy loss." Third, despite the slowdown, ON Semiconductor remains a well-run business that's generating value for investors, and it trades on an excellent valuation. Focusing on free cash flow (FCF), management continues to expect to convert 25% of revenue into FCF in 2025. Based on analyst forecasts for revenue, this would produce about $1.44 billion in FCF, and, as noted above, it would mean the stock trades at just 14.5 times FCF in 2025 -- that's low for a company with such exciting long-term growth prospects, even if it faces near-term headwinds. A once-in-a-lifetime stock buy If you can tolerate the potential for bad news, then ON Semiconductor looks like a very attractive stock. The EV market is currently challenging, but automakers who fail to develop a viable EV business will struggle to become significant players in the future. Because of this, a new wave of investment will eventually come, and that will help ON Semiconductor's core market. At the same time, its Nvidia partnership is exciting and would likely hit the news more frequently if the stock's narrative weren't so heavily focused on its EV exposure. Following a trough year in 2025, Wall Street expects the company to grow earnings by 29% in 2026, and if that comes to fruition, then the stock will be markedly higher then. Do the experts think ON Semiconductor is a buy right now? The Motley Fool's expert analyst team, drawing on years of investing experience and deep analysis of thousands of stocks, leverages our proprietary Moneyball AI investing database to uncover top opportunities. They've just revealed their to buy now — did ON Semiconductor make the list? When our Stock Advisor analyst team has a stock recommendation, it can pay to listen. After all, Stock Advisor's total average return is up 1,071% vs. just 185% for the S&P — that is beating the market by 886.18%!* Imagine if you were a Stock Advisor member when Netflix made this list on December 17, 2004... if you invested $1,000 at the time of our recommendation, you'd have $663,630!* Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you'd have $1,115,695!* The 10 stocks that made the cut could produce monster returns in the coming years. Don't miss out on the latest top 10 list, available when you join Stock Advisor. See the 10 stocks » *Stock Advisor returns as of August 13, 2025 Lee Samaha has no position in any of the stocks mentioned. The Motley Fool has positions in and recommends Nvidia. The Motley Fool recommends ON Semiconductor. The Motley Fool has a disclosure policy. Why Aren't More People Talking About This Big News About an Nvidia Partner? was originally published by The Motley Fool Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
