How AI and high-performance computing are speeding up scientific discovery – Microsoft
Computing has already accelerated scientific discovery. Now scientists say a combination of advanced AI with next-generation cloud computing is turbocharging the pace of discovery to speeds unimaginable just a few years ago.
Microsoft and the Pacific Northwest National Laboratory (PNNL) in Richland, Washington, are collaborating to demonstrate how this acceleration can benefit chemistry and materials science two scientific fields pivotal to finding energy solutions that the world needs.
Scientists at PNNL are testing a new battery material that was found in a matter of weeks, not years, as part of the collaboration with Microsoft to use to advanced AI and high-performance computing (HPC), a type of cloud-based computing that combines large numbers of computers to solve complex scientific and mathematical tasks.
As part of this effort, the Microsoft Quantum team used AI to identify around 500,000 stable materials in the space of a few days.
The new battery material came out of a collaboration using Microsofts Azure Quantum Elements to winnow 32 million potential inorganic materials to 18 promising candidates that could be used in battery development in just 80 hours. Most importantly, this work breaks ground for a new way of speeding up solutions for urgent sustainability, pharmaceutical and other challenges while giving a glimpse of the advances that will become possible with quantum computing.
We think theres an opportunity to do this across a number of scientific fields, says Brian Abrahamson, the chief digital officer at PNNL. Recent technology advancements have opened up the opportunity to accelerate scientific discovery.
PNNL is a U.S. Department of Energy laboratory doing research in several areas, including chemistry and materials science, and its objectives include energy security and sustainability. That made it the ideal collaborator with Microsoft to leverage advanced AI models to discover new battery material candidates.
The development of novel batteries is an incredibly important global challenge, Abrahamson says. It has been a labor-intensive process. Synthesizing and testing materials at a human scale is fundamentally limiting.
The traditional first step of materials synthesis is to read all the published studies of other materials and hypothesize how different approaches might work out. But one of the main challenges is that people publish their success stories, not their failure stories, says Vijay Murugesan, materials sciences group lead at PNNL. That means scientists rarely benefit from learning from each others failures.
The next traditional scientific step is testing the hypotheses, typically a long, iterative process. If its a failure, we go back to the drawing board again, Murugesan says. One of his previous projects at PNNL, a vanadium redox flow battery technology, required several years to solve a problem and design a new material.
The traditional method requires looking at how to improve on what has been done in the past. Another approach would be to take all the possibilities and, through elimination, find something new. Designing new materials requires a lot of calculations, and chemistry is likely to be among the first applications of quantum computing. Azure Quantum Elements offers a cloud computing system designed for chemistry and materials science research with an eye toward eventual quantum computing, and is already working on these kinds of models, tools and workflows. These models will be improved for future quantum computers, but they are already proving useful for advancing scientific discovery using traditional computers.
To evaluate its progress in the real world, the Microsoft Quantum team focused on something ubiquitous in our lives materials for batteries.
Microsoft first trained different AI systems to do sophisticated evaluations of all the workable elements and to suggest combinations. The algorithm proposed 32 million candidates like finding a needle in a haystack. Next, the AI system found all the materials that were stable. Another AI tool filtered out candidate molecules based on their reactivity, and another based on their potential to conduct energy.
The idea isnt to find every single possible needle in the hypothetical haystack, but to find most of the good ones. Microsofts AI technology whittled the 32 million candidates down to about 500,000 mostly new stable materials, then down to 800.
At every step of the simulation where I had to run a quantum chemistry calculation, instead Im calling the machine learning model. So I still get the insight and the detailed observations that come from running the simulation, but the simulation can be up to half a million times faster, says Nathan Baker, Product Leader for Azure Quantum Elements.
AI may be fast, but it isnt perfectly accurate. The next set of filters used HPC, which provides high accuracy but uses a lot of computing power. That makes it a good tool for a smaller set of candidate materials. The first HPC verification used density functional theory to calculate the energy of each material relative to all the other states it could be in. Then came molecular dynamics simulations that combined AI and HPC to analyze the movements of atoms and molecules inside each material.
This process culled the list to 150 candidates. Finally, Microsoft scientists used HPC to evaluate the practicality of each material availability, cost and such to trim the list to 23 five of which were already known.
Thanks to this AI-HPC combination, discovering the most promising material candidates took just 80 hours.
The HPC portion accounted for 10 percent of the time spent computing and that was on an already-targeted set of molecules. This intense computing is the bottleneck, even at universities and research institutions that have supercomputers, which not only are not tailored to a specific domain but also are shared, so researchers may have to wait their turn. Microsofts cloud-based AI tools relieve this situation.
Microsoft scientists used AI to do the vast majority of the winnowing, accounting for about 90 percent of the computational time spent. PNNL materials scientists then vetted the short list down to half a dozen candidate materials. Because Microsofts AI tools are trained for chemistry, not just battery systems, they can be used for any kind of materials research, and the cloud is always accessible.
We think the cloud is a tremendous resource in improving the accessibility to research communities, Abrahamson says.
Today, Microsoft supports a chemistry-specific copilot and AI tools that together act like a magnet that pulls possible needles out of the haystack, trimming the number of candidates for further exploration so scientists know where to focus. The vision we are working toward is generative materials where I can ask for list of new battery compounds with my desired attributes, Baker says.
The hands-on stage is where the project stands now. The material has been successfully synthesized and turned into prototype batteries that are functional and will undergo multiple tests in the lab. Making the material at this point, before its commercialized, is artisanal. One of the first steps is to take solid precursors of the materials and to grind them by hand with a mortar and pestle, explains Shannon Lee, a PNNL materials scientist. She then uses a hydraulic press to compact the material into a dime-shaped pellet. It goes into a vacuum tube and is heated to 450 to 650 degrees Celsius (842 to 1202 degrees Fahrenheit), transferred to a box to keep it away from oxygen or water, and then ground into a powder for analysis.
For this material, the 10-or-more-hour process is relatively quick, Lee says. Sometimes it takes a week or two weeks to make a single material.
Then hundreds of working batteries must be tested, over thousands of different charging cycles and other conditions, and later different battery shapes and sizes to realize commercial use. Murugesan dreams of the development of a digital twin for chemistry or materials, so you dont need to go to a lab and put this material together and make a battery and test it. You can say, this is my anode and this is my cathode and thats the electrolyte and this is how much voltage Im going to apply, and then it can predict how everything will work together. Even details like, after 10,000 cycles and five years of usage, the material performance will be like this.
Microsoft is already working on digital tools to speed up the other parts of the scientific process.
The lengthy traditional process is illustrated by lithium-ion batteries. Lithium got attention as a battery component in the early 1900s, but rechargeable lithium-ion batteries didnt hit the market until the 1990s.
Today, lithium-ion batteries increasingly run our world, from phones to medical devices to electric vehicles to satellites. Lithium demand is expected to rise five to ten times by 2030, according to the U.S. Department of Energy. Lithium is already relatively scarce, and thus expensive. Mining it is environmentally and geopolitically problematic. Traditional lithium-ion batteries also pose safety issues, with the potential to catch fire or explode.
Many researchers are looking for alternatives, both for lithium and for the materials used as electrolytes. Solid-state electrolytes show promise for their stability and safety.
The newly discovered material PNNL scientists are currently testing uses both lithium and sodium, as well as some other elements, thus reducing the lithium content considerably possibly by as much as 70 percent. It is still early in the process the exact chemistry is subject to optimization and might not work out when tested at larger scale, Abrahamson cautions. He points out that the story here is not about this particular battery material, but rather the speed at which a material was identified. The scientists say the exercise itself is immensely valuable, and it has revealed some surprises.
The AI-derived material is a solid-state electrolyte. Ions shuttle back and forth through the electrolyte, between the cathode and the anode, ideally with minimal resistance.
Read more from the original source:
How AI and high-performance computing are speeding up scientific discovery - Microsoft
- Google rolls out Gemini Deep Think AI, a reasoning model that tests multiple ideas in parallel - TechCrunch - August 1st, 2025 [August 1st, 2025]
- Big Tech may be breaking the bank for AI, but investors love it - Reuters - August 1st, 2025 [August 1st, 2025]
- Is Amazon Losing Ground To Microsoft And Google in AI? - Investor's Business Daily - August 1st, 2025 [August 1st, 2025]
- Tim Cook Says Apple Is Investing Significantly in AI and Could Buy Another Company - Investopedia - August 1st, 2025 [August 1st, 2025]
- UBS took a sweeping look at the AI revolution and concluded the 'visible' impact is at least 3 years away for consumer firms - Fortune - August 1st, 2025 [August 1st, 2025]
- China has top-flight AI models. But it is struggling to run them - The Economist - August 1st, 2025 [August 1st, 2025]
- The 10 jobs least and most threatened by AI - Axios - August 1st, 2025 [August 1st, 2025]
- Startup Trunk Tools is using AI to reduce construction errors and waste - CNBC - August 1st, 2025 [August 1st, 2025]
- Metas superintelligence isnt here yet. But its AI bets are already paying off - CNN - August 1st, 2025 [August 1st, 2025]
- Ethan Thornton of Mach Industries takes the AI stage at Disrupt 2025 - TechCrunch - August 1st, 2025 [August 1st, 2025]
- 20 jobs and careers AI is unlikely to ever touch, according to Microsoft - Fortune - August 1st, 2025 [August 1st, 2025]
- Palantir Won a Big Army Pact. The AI Firm Is in the Sweet Spot, Says Analyst. - Barron's - August 1st, 2025 [August 1st, 2025]
- Etsy Turns From TV Ads Toward Search, With AI as the Wild Card - The Wall Street Journal - August 1st, 2025 [August 1st, 2025]
- Big Tech's AI and core businesses are blurring together - Yahoo Finance - August 1st, 2025 [August 1st, 2025]
- These 40 Jobs May Be Replaced by AI. These 40 Probably Won't Microsoft study identifies most AI affected jobs - Inc.com - August 1st, 2025 [August 1st, 2025]
- Why You Shouldnt Use AI To Write Your Executive (Legal) Resume Or LinkedIn Profile - Above the Law - August 1st, 2025 [August 1st, 2025]
- Prediction: This Artificial Intelligence (AI) Stock Could Hit a $10 Trillion Valuation by 2035 - The Motley Fool - August 1st, 2025 [August 1st, 2025]
- What is AI, how do apps like ChatGPT work and why are there concerns? - BBC - August 1st, 2025 [August 1st, 2025]
- BG3's Astarion voice actor is 'not interested' in AI: 'Where's the joy in it?' - Polygon - August 1st, 2025 [August 1st, 2025]
- TikTok took the world by storm. Now, Chinese companies are taking videos further with AI - CNBC - August 1st, 2025 [August 1st, 2025]
- 'What am I falling in love with?' Human-AI relationships are no longer just science fiction - CNBC - August 1st, 2025 [August 1st, 2025]
- I Watched AI Agents Try to Hack My Vibe-Coded Website - WIRED - August 1st, 2025 [August 1st, 2025]
- Personal Perspective: AI training is here. But what we need is human training. - Psychology Today - August 1st, 2025 [August 1st, 2025]
- Amazons overwhelming AI demand is just a bronze medal compared to its rivals - Sherwood News - August 1st, 2025 [August 1st, 2025]
- Bidens autopen controversy says more about AI than you might think - The Hill - August 1st, 2025 [August 1st, 2025]
- Enterprise AI is at a tipping Point, heres what comes next - The World Economic Forum - August 1st, 2025 [August 1st, 2025]
- Apple quietens Wall Streets fears of China struggles and slow AI progress - The Guardian - August 1st, 2025 [August 1st, 2025]
- The AI Company Capitalizing on Our Obsession With Excel - The Wall Street Journal - August 1st, 2025 [August 1st, 2025]
- Apple to Significantly Invest in AI, Warns of $1 Billion Tariff Hit - PYMNTS.com - August 1st, 2025 [August 1st, 2025]
- I'm a software engineer, and I've lost my job 4 times in the last 18 years. I don't think AI is the problem. - Business Insider - August 1st, 2025 [August 1st, 2025]
- Exclusive | AI Finance App Ramp Is Valued at $22.5 Billion in Funding Round - The Wall Street Journal - July 30th, 2025 [July 30th, 2025]
- How spy agencies are experimenting with the newest AI models - The Economist - July 30th, 2025 [July 30th, 2025]
- Metas AI Recruiting Campaign Finds a New Target - WIRED - July 30th, 2025 [July 30th, 2025]
- SOCOM adds new advanced AI capabilities to tech wish list - DefenseScoop - July 30th, 2025 [July 30th, 2025]
- We will sign the EU AI Code of Practice. - The Keyword - July 30th, 2025 [July 30th, 2025]
- Why the man behind The Haters Guide to the AI Bubble thinks Wall Streets hottest trade will go bust - MarketWatch - July 30th, 2025 [July 30th, 2025]
- How Do You Think AI Will Impact Jobs In The Next 5-10 Years? - The Seattle Medium - July 30th, 2025 [July 30th, 2025]
- The Trumpification of AI: What Could Go Wrong? - Mother Jones - July 30th, 2025 [July 30th, 2025]
- YouTube to roll out new AI-powered technology aimed at identifying teen users - CBS News - July 30th, 2025 [July 30th, 2025]
- Google says it will sign EUs AI code of practice - TechCrunch - July 30th, 2025 [July 30th, 2025]
- Millions are watching these bizarre AI Bible videos on TikTok. Should you be worried or encouraged? - Premier Christianity Magazine - July 30th, 2025 [July 30th, 2025]
- Silicon Valley's billions of dollars on AI haven't actually generated a return yet. Here's why most companies should embrace 'small AI' instead -... - July 30th, 2025 [July 30th, 2025]
- Alibabas AI coding tool raises security concerns in the West - AI News - July 30th, 2025 [July 30th, 2025]
- How Zuckerbergs Prometheus AI project could change the world as we know it - The Independent - July 30th, 2025 [July 30th, 2025]
- Nvidia AI chip challenger Groq said to be nearing new fundraising at $6B valuation - TechCrunch - July 30th, 2025 [July 30th, 2025]
- How US adults are using AI, according to AP-NORC polling - AP News - July 30th, 2025 [July 30th, 2025]
- Gen AI apps doubled their revenue, grew to 1.7B downloads in first half of 2025 - TechCrunch - July 30th, 2025 [July 30th, 2025]
- The AI browser war is underway. Compare the top browsers from Perplexity, Opera, and more. - Mashable - July 30th, 2025 [July 30th, 2025]
- Aetna Launches New AI and Digital Tools to Improve Access and Care - CVS Health - July 30th, 2025 [July 30th, 2025]
- YouTube is turning over age verification to AI - Engadget - July 30th, 2025 [July 30th, 2025]
- Apple is facing pressure from Wall Street to figure out its AI strategy - CNBC - July 30th, 2025 [July 30th, 2025]
- Google was once the most exciting place on the internet. AI mode will ruin it - The Independent - July 30th, 2025 [July 30th, 2025]
- Microsoft research: Which jobs overlap most with AI tasks? - theregister.com - July 30th, 2025 [July 30th, 2025]
- Amazons AI Coding Revealed a Dirty Little Secret - Bloomberg.com - July 30th, 2025 [July 30th, 2025]
- Apple Loses Fourth AI Researcher in a Month to Metas Superintelligence Team - Bloomberg.com - July 30th, 2025 [July 30th, 2025]
- Could This Once-Hot AI Stock Get Another Shot At Stardom? - Barchart.com - July 30th, 2025 [July 30th, 2025]
- The race to provide AI agents for tedious tasks is on, but should we trust them with our data? - CBC - July 30th, 2025 [July 30th, 2025]
- The Shortcut AI Excel agent could 'one-shot' spreadsheet jobs. Here's how to try it. - Mashable - July 30th, 2025 [July 30th, 2025]
- With Ambiences new mega-round, AI scribes have announced nearly $1 billion in funding this year - statnews.com - July 30th, 2025 [July 30th, 2025]
- Microsoft study identifies 40 jobs AI chatbots are likely to help automate and those where the tech is barely being used - Business Insider - July 30th, 2025 [July 30th, 2025]
- AMD Raises AI Chip Price, Confident It Can Compete With Nvidia - Investor's Business Daily - July 28th, 2025 [July 28th, 2025]
- Opinion | How AI is impacting 700 professions and might impact yours - The Washington Post - July 28th, 2025 [July 28th, 2025]
- AMD Stock Is Rising. Its AI Chip Business Is Improving, Says Analyst. - Barron's - July 28th, 2025 [July 28th, 2025]
- NFL record predictions 2025: AI makes win-loss picks for all 32 teams - USA Today - July 28th, 2025 [July 28th, 2025]
- China's latest AI model claims to be even cheaper to use than DeepSeek - CNBC - July 28th, 2025 [July 28th, 2025]
- Auterion says it will provide Ukraine with 33,000 AI drone guidance kits - Reuters - July 28th, 2025 [July 28th, 2025]
- How Microsofts customers and partners accelerated AI Transformation in FY25 to innovate with purpose and shape their future success - The Official... - July 28th, 2025 [July 28th, 2025]
- Hawleys bill would let people sue AI firms using their content without permission - STLPR - July 28th, 2025 [July 28th, 2025]
- Western Union to Tap Stablecoins and AI for Greater Efficiencies - PYMNTS.com - July 28th, 2025 [July 28th, 2025]
- Microsoft Edge transforms into an AI browser with new Copilot Mode - The Verge - July 28th, 2025 [July 28th, 2025]
- Forget the Turing Test, AIs real challenge is communication - AI News - July 28th, 2025 [July 28th, 2025]
- Trumps order to remove woke AI from government may have downstream impacts, experts worry - Nextgov/FCW - July 28th, 2025 [July 28th, 2025]
- Google Search: Introducing AI Mode in the UK - The Keyword - July 28th, 2025 [July 28th, 2025]
- AI is driving mass layoffs in tech, but it's boosting salaries by $18,000 a year everywhere else, study says - Fortune - July 28th, 2025 [July 28th, 2025]
- Warren Buffett Has 40% of Berkshire Hathaway's $293 Billion Portfolio Invested in 5 Artificial Intelligence (AI) Stocks - Yahoo Finance - July 28th, 2025 [July 28th, 2025]
- Meta Earnings On Deck. Zuckerberg's Big AI Bets Will Be In Focus. - Investor's Business Daily - July 28th, 2025 [July 28th, 2025]
- Everyone's a loser in Trump's AI Action Plan - Engadget - July 28th, 2025 [July 28th, 2025]
- On GPS: Bill Gates on navigating the future of AI - CNN - July 28th, 2025 [July 28th, 2025]
- AI Apps Are Undressing Women Without Consent And Its A Problem - Forbes - July 28th, 2025 [July 28th, 2025]
- AI's race in the dark with China - Axios - July 28th, 2025 [July 28th, 2025]