Machine learning is giving scientists a strong latest solution to seek for superconductors, materials that conduct electricity with zero resistance. A world team has demonstrated that AI can rapidly narrow an almost limitless variety of possible material combos to discover probably the most promising candidates. Based on Aalto University Professor Päivi Törmä, who leads the SuperC consortium, the approach could dramatically speed the invention of latest superconductors.
Superconductors allow electric current to flow without losing energy, but only when cooled to extremely low temperatures where quantum effects emerge. These remarkable materials are already utilized in technologies starting from quantum computers and medical neuroimaging systems to fusion reactors and maglev trains.
Despite their enormous potential, superconductors remain exceptionally difficult to find. There are virtually limitless combos of chemical elements that might form latest materials, yet only a tiny fraction develop into superconductors. Those who have already been identified generally require costly cooling systems that bring them near absolute zero before they exhibit their unique properties.
Scientists around the globe are looking for a practical superconductor that may operate at room temperature.
“Superconductive materials that may operate at room temperature would perpetually change the way in which we devour energy,” explains Törmä. “If such a cloth could replace regular conductors in applications like computers and data centers, global energy consumption might be slashed and the warmth footprint of the ICT sector vastly reduced.”
AI and Quantum Physics Join Forces
The SuperC consortium was established in 2023 by Professor Törmä and a world group of leading physicists who share the goal of using quantum physics to assist address climate change. It’s the primary coordinated global collaboration dedicated to discovering latest superconductors, with the ambitious objective of finding a room temperature superconductor by 2033.
Based on Törmä, combining quantum geometry with machine learning provides a strong foundation for that search. Within the team’s latest work, the newly identified superconductors, YRu3B2 and LuRu3B2, owe their properties to electrons forming flat bands inside a kagome lattice, a geometrical arrangement inspired by traditional Japanese basket weaving patterns.
To discover these materials, researchers first used machine learning to rapidly screen enormous numbers of possible elemental combos. A specialized algorithm chosen probably the most promising candidates, which were then analyzed using detailed quantum calculations to find out whether or not they could develop into superconductors.
Once the predictions were confirmed theoretically, collaborators at Rice University synthesized the materials by chemically combining their constituent elements into latest compounds. Led by Professor Emilia Morosan, the Rice team then experimentally verified that each materials are indeed superconductors.
The proof of concept study was recently published in Physical Review Research.
A Faster Path to Recent Superconductors
Developing an entire quantum mechanical understanding of superconductivity is very difficult, making the search for brand spanking new superconducting materials slow and computationally demanding.
“Over the many years researchers have recognized over 7,000 superconductors, but mostly serendipitously,” explains Törmä. “The means of identifying possible materials is so computationally heavy that, actually, researchers have only been in a position to theoretically predict the viability of about 20 of those.”
Even when a cloth appears promising on paper, it should prove impractical since it is simply too difficult to synthesize or unimaginable to provide at scale, Törmä notes. Traditionally, evaluating huge numbers of potential materials has required enormous computing resources. The SuperC team’s AI driven approach changes that process by focusing detailed calculations only on the strongest candidates.
“Our method uses machine-learning-based pre-screening followed by targeted calculations on the promising candidates. This approach will greatly speed up superconductor discovery in the longer term. With machine learning, we may find a way to push the variety of materials we will process into the billions,” says Törmä. “This can take us a critical step closer to finding a room-temperature superconductor.”
Looking Ahead
SuperC’s research will likely be featured in Aalto University’s Designs for a Cooler Planet exhibition from September 1 to October 30, 2026, in Greater Helsinki, Finland.
The SuperC consortium receives funding from The Kavli Foundation, Klaus Tschira Stiftung, Kevin Wells, the Jane and Aatos Erkko Foundation, the Keele Foundation, the Magnus Ehrnrooth Foundation, and the Neste and Fortum Foundation.