{"slug": "fusion-dreams-drive-high-temperature-superconductor-quest", "title": "Fusion Dreams Drive High-Temperature Superconductor Quest", "summary": "Two startups, San Francisco-based Periodic Labs and Cambridge, Mass.-based Quantum Formatics, are using AI and robots to discover new superconductors that can operate at temperatures above 10 kelvins, the transition temperature of niobium-titanium (NbTi), the most common superconductor. Quantum Formatics founder Jason Gibson says the company is about a year away from making a prototype wire for qualification tests, targeting operating temperatures of 10 to 20 K. Periodic Labs cofounder Ekin Doğuş Çubuk says its AI-powered robot-arm system can test 1,000 candidate superconductors per day using X-ray diffraction and machine learning.", "body_md": "Dozens of materials today outperform the world’s most common superconductor—[niobium-titanium](https://en.wikipedia.org/wiki/Niobium%E2%80%93titanium) (NbTi). But no competing material can beat niobium-titanium’s capacity to be manufactured at scale and rolled out into usable wire.\n\nTwo startups say that AI and robots could help close that gap.\n\nThe San Francisco–based [Periodic Labs](https://periodic.com/) and Cambridge, Mass.–based [Quantum Formatics](https://quantumformatics.com/) are searching for materials that work at temperatures higher than 10 kelvins (−264 °C), the transition temperature of NbTi, below which it loses all electrical resistance.\n\nQuantum Formatics has several candidate materials for a new generation of [superconductors](https://spectrum.ieee.org/tag/superconductors). Company founder [Jason Gibson](https://quantumformatics.com/team) says the company is about a year away from making a prototype wire that can be used in qualification tests to demonstrate [superconductor performance](https://spectrum.ieee.org/high-temperature-superconductor-current-capacity).\n\n“We’re trying to get operating temperatures of 10 to 20 K,” says Gibson. “We focus on moderate-temperature superconductors with excellent mechanical properties that lead to good manufacturability. This approach means we can adopt a standard wire-manufacturing process.”\n\nPeriodic Labs cofounder [Ekin Doğuş Çubuk](https://scholar.google.com/citations?user=Mu_8iOEAAAAJ&hl=en) says his company, established in September 2025, has developed a technique based on [X-ray diffraction](https://www.physics.upenn.edu/~heiney/datasqueeze/basics.html). XRD, as it’s called, is a method of mapping the atomic structure of a material by bouncing X-ray beams off it.\n\nPeriodic Labs’ XRD procedures help the company to study candidate superconductors and automate its [superconductor](https://spectrum.ieee.org/tag/superconductor) discovery process, says Çubuk.\n\nPeriodic Labs cofounder Ekin Doğuş Çubuk says the company has pioneered an AI-powered robot-arm system that can test 1,000 candidate superconductors per day. Richard Morgenstein/Periodic Labs\n\n### How Can Robots and AI Help Discover New Superconductors?\n\nBecause no human can sift through thousands of XRD patterns a day, the company is developing [machine learning](https://spectrum.ieee.org/tag/machine-learning) [algorithms](https://spectrum.ieee.org/tag/algorithms) to use XRD and measure the magnetic properties of materials to speed detection of new superconductors.\n\n“We have built robots that can physically use X-ray diffraction machines,” Çubuk says. “Robotic arms load samples, and then the measurement gets done, sent to an LLM. The robot takes a sample out, puts in a new sample, and then the LLM analyzes all the X-ray diffraction patterns to determine if the experiment worked—and if it didn’t work, what to do next.”\n\nÇubuk adds that developing and creating new materials from scratch hasn’t been easy to automate.\n\n“Our biggest bottleneck is being able to make these different materials for the first time,” says Çubuk, who was previously a research scientist at [Google DeepMind](https://spectrum.ieee.org/how-deepmind-is-reinventing-the-robot).\n\nMeanwhile, according to competing teams also using AI to make progress in the field, new superconductor discoveries are hotly anticipated today.\n\n“Magnets could come very fast if we are very lucky and find something very easily,” says Päivi Törmä, the leading physicist of the [Super C consortium](https://superc2033.com/) of European and American universities aiming to make the first room-temperature superconductors by 2033.\n\nNew superconductors can boost [energy efficiency](https://spectrum.ieee.org/tag/energy-efficiency) in [data centers](https://spectrum.ieee.org/tag/data-centers) and hospital magnetic-resonance-imaging equipment by an order of magnitude, she says.\n\n“I made estimates based on the best data that I could get,” Törmä says. “For sure, it’s 10 times more, but it can easily be 100 or 1,000 times more energy efficient.”\n\nPeriodic Labs has been conducting 100 experiments a day, according to Çubuk. The company is also opening a second lab to accelerate testing.\n\n“That’s going to ramp up to 1,000 attempts a day,” Çubuk says. “I think that will be by far the highest-throughput [superconductivity research](https://www.nature.com/articles/s41524-024-01475-4) ever done. We want to see by doing 1,000 good attempts a day if we can [discover really exciting superconductors](https://www.nature.com/articles/s41524-026-01964-8).”\n\nQuantum Formatics is using what it calls the System, its proprietary AI-accelerated superconductor-discovery algorithm. The company has published three articles in * Nature Computational Materials *describing\n\n[how its automated discovery system works](https://www.nature.com/articles/s41524-026-02117-7).\n\nQuantum Formatics founder Jason Gibson says AI can assist in the discovery of hardened superconductors for powering strong magnets for [nuclear fusion](https://spectrum.ieee.org/tag/nuclear-fusion), since existing magnets turn brittle in a reactor’s high-radiation environment.Minks Media\n\n“We realized there was a critical gap between where the research of superconductor discovery was and what actually gets implemented in a device,” says Gibson, the company’s founder. “Dozens of superconductors have been discovered that vastly exceed the superconducting properties of NbTi. However, nearly all have failed to reach large market penetration due to the challenge of manufacturing.”\n\nGibson points to the importance of [ductility](https://en.wikipedia.org/wiki/Ductility)—a material’s capacity to be reshaped and, in the case of Quantum Formatics, made into wires flexible enough to be wound into superconducting magnets.\n\n### What Technologies Could Benefit From New Superconductor Discoveries?\n\nFor comparison, [rare-earth barium copper oxides](https://en.wikipedia.org/wiki/Rare-earth_barium_copper_oxide) (ReBCO) are a [popular superconductor](https://arxiv.org/pdf/2203.08736), with transition temperatures in excess of liquid nitrogen’s 77 K boiling point. (A superconductor that’s coolable with inexpensive [liquid nitrogen](https://en.wikipedia.org/wiki/High-temperature_superconductivity), as opposed to the more costly [liquid hydrogen](https://en.wikipedia.org/wiki/Hydrogen_cryomagnetics) or [liquid helium](https://www.energy.gov/science/doe-explainssuperconductivity), is an attractive prospect for superconductor researchers.)\n\nThe Cambridge, Mass.–based [Commonwealth Fusion Systems](https://cfs.energy/) uses ReBCO tape in two experimental-fusion reactors the company is building in Massachusetts and Virginia.\n\nHowever, superconducting [magnetic tape](https://spectrum.ieee.org/tag/magnetic-tape) in a [fusion reactor](https://spectrum.ieee.org/tag/fusion-reactor) also is exposed to a substantial amount of radiation, which can degrade the tape.\n\n“Radiation is a very challenging thing,” says Dan Brunner, former chief technology officer at Commonwealth. “That’s one of the challenges with the ReBCO class of superconductors. It’s a very fine crystal structure. Because it’s crystalline, it’s brittle, and that makes it hard to engineer into systems.”\n\nQuantum Formatics is working with companies like Commonwealth Fusion and [Realta Fusion](https://realtafusion.com/), based in Madison, Wis. Superconducting magnets account for up to half of the $3 billion cost of a fusion reactor, Gibson says.\n\n“The one challenge we’re really trying to address in terms of ReBCO is its radiation tolerance,” Gibson adds. “It does not perform well under radiation, but it is essentially the only option that produces high enough [magnetic fields](https://spectrum.ieee.org/tag/magnetic-fields) to allow you to have a compact fusion plant.”\n\nÇubuk says that Periodic Labs is also investigating commercial applications like [power transmission](https://spectrum.ieee.org/tag/power-transmission) for data centers.\n\n“Data centers are getting more power hungry, and they have to use these extremely thick copper wires to bring power into the racks,” Çubuk said. “If somebody could make superconductor tapes work with liquid nitrogen, those tapes could be much thinner and much smaller and could carry much more power without the resistance loss.”\n\nFor the foreseeable future, Çubuk says, old-fashioned trial and error will remain an important part of the discovery process.\n\n“From that perspective,” he says, “it’s very interesting to think about how superconductors get discovered—and how they might get discovered in the future.”\n\n[This Fusion Reactor Is Held Together With Tape ›](https://spectrum.ieee.org/fusion-2662267312)[Electron Map May Show the Way Toward High-Temp Superconductivity ›](https://spectrum.ieee.org/electron-map-may-show-the-way-toward-hightemp-superconductivity)[5 Big Ideas for High-Temperature Superconductors ›](https://spectrum.ieee.org/high-temperature-superconductors)\n\n[Alan Patterson](https://spectrum.ieee.org/u/alan-patterson)\n\n[Alan Patterson](https://www.linkedin.com/in/zachary-patterson-a67905101/) has worked most of his career in Taiwan and Hong Kong, where he covered chipmakers like Taiwan Semiconductor Manufacturing Corp. (TSMC) and Semiconductor Manufacturing International Corp. (SMIC). More recently, he's returned to the U.S. to track reshoring of the industry.", "url": "https://wpnews.pro/news/fusion-dreams-drive-high-temperature-superconductor-quest", "canonical_source": "https://spectrum.ieee.org/high-temperature-superconductor-ai-research", "published_at": "2026-09-04 09:52:54+00:00", "updated_at": "2026-09-04 10:23:52.794529+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "ai-research", "ai-tools", "robotics"], "entities": ["Periodic Labs", "Quantum Formatics", "Jason Gibson", "Ekin Doğuş Çubuk", "Google DeepMind", "Super C consortium", "Päivi Törmä"], "alternates": {"html": "https://wpnews.pro/news/fusion-dreams-drive-high-temperature-superconductor-quest", "markdown": "https://wpnews.pro/news/fusion-dreams-drive-high-temperature-superconductor-quest.md", "text": "https://wpnews.pro/news/fusion-dreams-drive-high-temperature-superconductor-quest.txt", "jsonld": "https://wpnews.pro/news/fusion-dreams-drive-high-temperature-superconductor-quest.jsonld"}}