AI Insights
AI vs Supercomputers round 1: galaxy simulation goes to AI
Jul. 10, 2025
Press Release
Physics / Astronomy
Computing / Math
In the first study of its kind, researchers led by Keiya Hirashima at the RIKEN Center for Interdisciplinary Theoretical and Mathematical Sciences (iTHEMS) in Japan, along with colleagues from the Max Planck Institute for Astrophysics (MPA) and the Flatiron Institute, have used machine learning, a type of artificial intelligence, to dramatically speed up the processing time when simulating galaxy evolution coupled with supernova explosion. This approach could help us understand the origins of our own galaxy, particularly the elements essential for life in the Milky Way.
Understanding how galaxies form is a central problem for astrophysicists. Although we know that powerful events like supernovae can drive galaxy evolution, we cannot simply look to the night sky and see it happen. Scientists rely on numerical simulations that are based on large amounts of data collected from telescopes and other devices that measure aspects of interstellar space. Simulations must account for gravity and hydrodynamics, as well as other complex aspects of astrophysical thermo-chemistry.
On top of this, they must have a high temporal resolution, meaning that the time between each 3D snapshot of the evolving galaxy must be small enough so that critical events are not missed. For example, capturing the initial phase of supernova shell expansion requires a timescale of mere hundreds of years, which is 1000 times smaller than typical simulations of interstellar space can achieve. In fact, a typical supercomputer takes 1-2 years to carry out a simulation of a relatively small galaxy at the proper temporal resolution.
Getting over this timestep bottleneck was the main goal of the new study. By incorporating AI into their data-driven model, the research group was able to match the output of a previously modeled dwarf galaxy but got the result much more quickly. “When we use our AI model, the simulation is about four times faster than a standard numerical simulation,” says Hirashima. “This corresponds to a reduction of several months to half a year’s worth of computation time. Critically, our AI-assisted simulation was able to reproduce the dynamics important for capturing galaxy evolution and matter cycles, including star formation and galaxy outflows.”
Like most machine learning models, the researchers’ new model is trained using one set of data and then becomes able to predict outcomes based on a new set of data. In this case, the model incorporated a programmed neural network and was trained on 300 simulations of an isolated supernova in a molecular cloud that massed one million of our suns. After training, the model could predict the density, temperature, and 3D velocities of gas 100,000 years after a supernova explosion. Compared with direct numerical simulations such as those performed by supercomputers, the new model yielded similar structures and star formation history but took four times less time to compute.
According to Hirashima, “our AI-assisted framework will allow high-resolution star-by-star simulations of heavy galaxies, such as the Milky Way, with the goal of predicting the origin of the solar system and the elements essential for the birth of life.”
Currently, the lab is using the new framework to run a Milky Way-sized galaxy simulation.
Rate this article
Reference
Contact
Keiya Hirashima, Special Postdoctoral Researcher
Division of Fundamental Mathematical Science, RIKEN Center for Interdisciplinary Theoretical and Mathematical Sciences (iTHEMS)
Adam Phillips
RIKEN Communications Division
Email: adam.phillips [at] riken.jp
The simulated galaxy after 200 million years. While the simulations look very similar with and without the machine learning AI model, the AI model performed 4 times as fast, completing large scale simulation in a matter of months rather than years.
AI Insights
Technology and Artificial Intelligence in the Garden
First disclosure – a real person (me) wrote this article, not Artificial Intelligence (AI). Second disclosure – I am not a technology expert. In fact, I often say that I was dragged, kicking and screaming, into the computer age, but… It started at a public park. I was in Albuquerque visiting my daughter and her […]
Originally Published:
AI Insights
4 Artificial Intelligence (AI) Stocks That Could Make You a Millionaire
You’re reading a free article with opinions that may differ
from The Motley Fool’s Premium Investing Services. Become a Motley Fool member today to
get instant access to our top analyst recommendations, in-depth research, investing resources,
and more. Learn More
AI Insights
1 Artificial Intelligence (AI) Stock to Buy Before It Soars to $10 Trillion, According to a Wall Street Analyst (Hint: Not Apple)
If this Wall Street analyst is correct, Nvidia shareholders will see monster returns through the end of the decade.
Beth Kindig, lead technology analyst at the I/O Fund, has an impressive track record where chipmaker Nvidia (NVDA) is concerned. In 2021, she correctly predicted the company would surpass Apple‘s market value within five years. Nvidia checked that box in three years.
Earlier this year, Kindig correctly called it a buying opportunity when Nvidia stock crashed after Chinese startup DeepSeek introduced low-cost large language models. The stock price has increased 28% since she made that recommendation, and it currently trades at a record high.
However, Kindig’s boldest prediction is that Nvidia will be a $10 trillion company by 2030. That implies 156% upside from its present market value of $3.9 trillion, which equates to annual returns of nearly 19% through the end of the decade for shareholders.
Image source: Getty Images.
Nvidia dominates the markets for data center GPUs and AI networking gear
Nvidia is best known for developing graphics processing units (GPUs), chips commonly used to accelerate time-consuming data center workloads like training machine learning models and running artificial intelligence (AI) applications. Nvidia dominates the space with more than 90% market share, according to Beth Kindig.
Mike Gualtieri at Forrester Research in a recent report commented, “Nvidia sets the pace for AI infrastructure worldwide. Without Nvidia’s GPUs, modern AI wouldn’t be possible.”
Importantly, the company also complements its GPUs with CPUs and interconnects, as well as Ethernet and InfiniBand networking platforms. In fact, Nvidia is the market leader in generative AI networking and it recently added Alphabet‘s Google and Meta Platforms to its growing list of customers.
Going forward, Grand View Research estimates the data center GPU market will expand at 36% annually through 2033. And Morningstar expects generative AI networking market will grow at 34% annually through 2028. That gives Nvidia good shot at annual revenue growth exceeding 30% for many years to come.
Nvidia is likely to maintain its leadership as the physical AI revolution unfolds
ChatGPT popularized generative AI, which uses large language models to turn prompts into novel media like text, images, and video. That technology created tremendous demand for Nvidia AI infrastructure, and the company is well positioned to maintain its leadership as the physical AI boom unfolds.
Physical AI lets autonomous machines understand and navigate the real world, and Nvidia addresses the technology at three layers of the computing stack: Its data center GPUs and networking platforms train AI models, its Omniverse simulation engine generates synthetic training data and tests AI models, and its embedded processors offer on-board computing power to autonomous robots and self-driving cars.
Beyond that, Nvidia’s CUDA platform includes code libraries, application frameworks, and pretrained models that accelerate the development of robotics and automotive software. That vertical integration makes Nvidia the go-to option for engineers and developers as it eliminates the complexity of integrating products from multiple vendors, which ultimately lowers the total cost of ownership.
Indeed, Beth Kindig says Nvidia has a “near-monopoly in building supercomputers” because of the “impenetrable moat” created by its CUDA software platform. She also cites vertical integration — the fact that the company provides data center components well beyond GPUs — as a major reason Nvidia can achieve a market value of $10 trillion no later than 2030.
Nvidia stock trades at a reasonable valuation compared to forward earnings estimates
Nvidia reported strong first-quarter financial results that exceeded expectations on the top and bottom lines. Revenue rose 69% to $44 billion because of robust demand for AI infrastructure, and non-GAAP net income rose 33% to $0.81 per diluted share. Earnings would have increased more quickly had it not been for new chip export restrictions related to China.
Wall Street estimates Nvidia’s adjusted earnings will increase at 41% annually through the fiscal year ending in January 2027. That makes the current valuation of 50 times adjusted earnings look reasonable, especially because the company topped the consensus earnings estimate by an average of 5% in the last six quarters. Long-term investors should feel comfortable owning the stock at its current price.
Suzanne Frey, an executive at Alphabet, is a member of The Motley Fool’s board of directors. Randi Zuckerberg, a former director of market development and spokeswoman for Facebook and sister to Meta Platforms CEO Mark Zuckerberg, is a member of The Motley Fool’s board of directors. Trevor Jennewine has positions in Nvidia. The Motley Fool has positions in and recommends Alphabet, Apple, Meta Platforms, and Nvidia. The Motley Fool has a disclosure policy.
-
Funding & Business1 week ago
Kayak and Expedia race to build AI travel agents that turn social posts into itineraries
-
Jobs & Careers1 week ago
Mumbai-based Perplexity Alternative Has 60k+ Users Without Funding
-
Mergers & Acquisitions1 week ago
Donald Trump suggests US government review subsidies to Elon Musk’s companies
-
Funding & Business1 week ago
Rethinking Venture Capital’s Talent Pipeline
-
Jobs & Careers1 week ago
Why Agentic AI Isn’t Pure Hype (And What Skeptics Aren’t Seeing Yet)
-
Education2 days ago
9 AI Ethics Scenarios (and What School Librarians Would Do)
-
Education3 days ago
Teachers see online learning as critical for workforce readiness in 2025
-
Education3 days ago
Nursery teachers to get £4,500 to work in disadvantaged areas
-
Education5 days ago
How ChatGPT is breaking higher education, explained
-
Education3 days ago
Labour vows to protect Sure Start-type system from any future Reform assault | Children