AI could uncover new physics faster but there’s a surprising catch

Science News from research organizations AI could uncover new physics faster but there’s a surprising catch AI may help uncover new laws of the universe faster—but sometimes it’s so confident in what it already knows that it misses the surprise. Date: June 11, 2026 Source: Sissa Medialab Summary: Scientists found that transfer learning can make the search for new physics in the universe much faster, slashing the need for expensive simulations. Yet the approach can backfire when AI relies too heavily on familiar patterns, potentially missing evidence of something truly new. Share: Facebook Twitter Pinterest LinkedIN Email FULL STORY Two images from the Quijote simulations used in this study. The panels show the same region of the Universe, but in different cosmological models. The top image corresponds to the standard ΛCDM model, while the bottom image shows a universe with massive neutrinos and modified gravity. The differences are subtle, but they reveal how changes in the underlying physics can affect the formation and distribution of cosmic structures. Credit: Francisco Villaescusa-Navarro Artificial intelligence is already playing a major role in helping cosmologists study the universe. Now, new research suggests a machine learning technique called transfer learning could make the search for new physics much faster and less expensive. However, the study also uncovered a surprising downside: AI can sometimes become so dependent on what it has already learned that it struggles to recognize something truly new. The study, published in the Journal of Cosmology and Astroparticle Physics (JCAP), examined how transfer learning might help researchers investigate theories that go beyond the standard cosmological model. AI and the Search for New Physics The current standard model of cosmology, known as ΛCDM, successfully explains many large-scale features of the universe, including its expansion and the distribution of galaxies. Yet scientists believe the model is not the final answer. Recent observations have raised questions that could point toward new physics, including the effects of massive neutrinos, modified gravity, and evolving dark energy. Exploring these possibilities requires researchers to generate enormous numbers of detailed computer simulations, each representing a virtual universe built using different physical assumptions. Producing these simulations is computationally expensive and often demands substantial computing power.

Using Transfer Learning to Reduce Simulation Costs The researchers investigated whether transfer learning could make this process more efficient. Transfer learning allows an AI system to apply knowledge gained from one task to another related task. Instead of training a neural network entirely on the most complex and computationally costly simulations, the team first trained it on simpler simulations based on ΛCDM. This initial phase, known as pretraining, was then followed by additional training using more sophisticated models that include potential new physics. "It's basically a shortcut," explains Adrian Bayer a cosmologist at the Flatiron Institute and Princeton University, co-author of the study. "Usually people train the AI directly on the most computationally expensive simulations. What we do instead is first use simpler and less expensive ΛCDM simulations to give the AI an idea of what's happening, and only afterward move to the more complex models." Bayer compares the approach to learning from textbooks. "You first read a basic book to get an idea of the knowledge," says Bayer, "and then move to the really complicated book." According to first author Veena Krishnaraj, an undergraduate student at Princeton University, this strategy prevents the AI from having to "digest everything at once." The results were striking. In some cases, transfer learning reduced the number of expensive simulations required by more than a factor of ten.

When Prior Knowledge Becomes a Problem The study also revealed a less obvious challenge known as negative transfer. Using Bayer's textbook comparison, imagine learning medicine from an introductory text and then encountering a rare disease that closely resembles a common condition. Existing knowledge is usually helpful, but it can sometimes encourage the wrong conclusion. The same issue can arise in AI systems. In some cases, the signatures of new physics resemble patterns that the AI has already associated with the standard cosmological model. When that happens, the pretrained network may interpret unfamiliar information through the lens of what it already knows, making it harder to recognize genuinely new effects. The researchers saw this effect while studying simulations that included massive neutrinos. Some of the observational signatures linked to neutrino mass closely resemble changes associated with an existing ΛCDM parameter called σ8, which measures how strongly matter clusters throughout the universe. Because of this similarity, the pretrained neural network initially had difficulty telling the two effects apart. "The negative transfer is not random. It is driven by underlying physical degeneracies in the model," says Krishnaraj. In other words, different physical processes can produce very similar observable signatures, making it challenging for the AI to correctly identify which parameter is responsible. "So this is something we need to be aware of and try to mitigate," she concludes. Promise and Risks for Future Cosmology The findings highlight both the potential benefits and limitations of applying foundation model concepts to physics. These approaches are broadly similar in spirit to the techniques behind modern generative AI systems and large language models. As the researchers note in the paper, pretraining can speed up inference, "but may also hinder learning new physics." So far, the approach has only been tested using simulations. The next step will be applying it to real astronomical observations.

The team believes transfer learning could become an important tool for upcoming cosmological surveys, which are expected to collect unprecedented amounts of high-precision data about the universe in the years ahead. The paper, "Transfer Learning Beyond the Standard Model" by Veena Krishnaraj, Adrian E. Bayer, Christian Kragh Jespersen, and Peter Melchior, is now available in JSTAT. RELATED TOPICS Space & Time Dark Matter Astrophysics Cosmology Matter & Energy Physics Energy and Resources Quantum Physics Computers & Math Computers and Internet Computer Modeling Neural Interfaces RELATED TERMS Big Bang Dark matter Physics Search engine Search engine optimization Cosmic microwave background radiation Edwin Hubble Science Story Source: Materials provided by Sissa Medialab. Note: Content may be edited for style and length.

Cite This Page: MLA APA Chicago Sissa Medialab. "AI could uncover new physics faster but there’s a surprising catch." ScienceDaily. ScienceDaily, 11 June 2026. . Sissa Medialab. (2026, June 11). AI could uncover new physics faster but there’s a surprising catch. ScienceDaily. Retrieved June 11, 2026 from www.sciencedaily.com/releases/2026/06/260611024557.htm Sissa Medialab. "AI could uncover new physics faster but there’s a surprising catch." ScienceDaily. www.sciencedaily.com/releases/2026/06/260611024557.htm (accessed June 11, 2026). Explore More from ScienceDaily RELATED STORIES AI May Not Need Massive Training Data After All Jan. 4, 2026 — New research shows that AI doesn’t need endless training data to start acting more like a human brain. When researchers redesigned AI systems to better resemble biological brains, some models ...

The Universe Is Expanding Too Fast to Fit Theories: Hubble Tension in Crisis Jan. 17, 2025 — The Universe really seems to be expanding fast. Too fast, even. A new measurement confirms what previous -- and highly debated -- results had shown: The Universe is expanding faster than predicted by ...

Making Quantum Physics Easier to Digest in Schools Nov. 27, 2024 — A team of physics educators is focusing on a new approach to teaching quantum physics in schools. Traditional classroom teaching has tended to focus on presenting the history of the origins of ...

In Odd Galaxy, NASA's Webb Finds Potential Missing Link to First Stars Oct. 3, 2024 — Looking deep into the early universe with NASA's James Webb Space Telescope, astronomers have found something unprecedented: a galaxy with an odd light signature, which they attribute to its gas ... New 'Forever Chemical' Cleanup Strategy Discovered May 9, 2024 — A method has been discovered to treat water heavily contaminated with unhealthful forever chemicals, known by chemists as PFAS or poly- and per-fluoroalkyl substances. It involves treating heavily ... Screen-Printing Method Can Make Wearable Electronics Less Expensive Jan. 12, 2023 — A new study demonstrates that electrodes can be made using just screen printing, creating a stretchable, durable circuit pattern that can be transferred to fabric and worn directly on human skin. ... TRENDING AT SCITECHDAILY.com Mysterious Cosmic Signal Could Be First Real Evidence of Primordial Black Holes Yale Discovery Overturns Long-Held “Evolutionary Dead End” Theory A Universe Without Dark Energy?

Mathematicians Challenge Standard Cosmology The Kombucha Surprise: One Ingredient Dramatically Changes Its Chemistry and Health Potential