An international team of researchers has demonstrated a powerful new way to discover superconductors by combining machine learning with advanced quantum physics. The approach, led by the SuperC consortium under Aalto University Professor Päivi Törmä, allows scientists to sift through an almost limitless number of possible material combinations and pinpoint the most promising candidates for superconductivity.
The breakthrough has already resulted in the discovery of two new superconducting materials: YRu3B2 and LuRu3B2. These materials gain their superconducting properties from electrons forming flat bands within a kagome lattice, a geometric arrangement inspired by traditional Japanese basket-weaving patterns.
"Superconductive materials that can operate at room temperature would forever change the way we consume energy," explains Törmä. "If such a material could replace regular conductors in applications like computers and data centers, global energy consumption could be slashed and the heat footprint of the ICT sector vastly reduced."
Superconductors carry electricity with zero resistance but currently require extreme cooling to near absolute zero. The SuperC consortium, established in 2023, is the first coordinated global collaboration dedicated to systematically discovering new superconductors with the ambitious goal of identifying a room-temperature superconductor by 2033.
To find these materials, the researchers first used machine learning to screen vast numbers of possible elemental combinations. A specialized algorithm identified the most promising candidates, which were then examined using detailed theoretical calculations. Collaborators at Rice University, led by Professor Emilia Morosan, synthesized the materials and laboratory testing confirmed their superconducting behavior.
"Over the decades researchers have recognized over 7,000 superconductors, but mostly serendipitously," says Törmä. "The process of identifying possible materials is so computationally heavy that researchers have only been able to theoretically predict the viability of about 20 of these."
The new approach changes this by using machine learning to eliminate unlikely candidates before performing the most demanding calculations. "With machine learning, we may be able to push the number of materials we can process into the billions," Törmä adds. "This will take us a critical step closer to finding a room-temperature superconductor."
The proof-of-concept study was published June 17, 2026 in Physical Review Research.
