Researchers Use AI to Accelerate Superconductor Discovery

An Aalto-led SuperC team reported on June 29, 2026 that machine-learning-guided screening helped identify and experimentally confirm two kagome superconductors, YRu3B2 and LuRu3B2. The Physical Review Research paper reports superconducting critical temperatures of 0.81 K and 0.95 K, so this is not a room-temperature result; the practitioner value is the workflow. The team used ML to narrow a large chemical search space, then applied first-principles calculations before Rice University collaborators synthesized and tested the candidates. For data-science and materials teams, the useful lesson is that physics-informed features, high-precision candidate ranking, and experiment-ready validation loops can matter more than broad benchmark accuracy when ML systems must produce lab-verifiable discoveries.