Machine-learning screen predicts two new kagome superconductors, confirmed in the lab
Päivi Törmä's group at Aalto combined ML pre-screening with quantum-geometry calculations to predict superconductivity in YRu3B2 and LuRu3B2. Rice University synthesised both and confirmed superconductivity at 0.81 K and 0.95 K (Physical Review Research).
Key facts
- Tc: 0.81 K (YRu3B2), 0.95 K (LuRu3B2), far from room temperature
- Törmä: 'This approach will greatly speed up superconductor discovery.'
- Press headlines about a 'race to room-temperature superconductors' overstate the result
Science result
- Field
- materials / superconductivity
- Problem
- Predicting new superconductors
- Result
- Two superconductors predicted computationally with ML screening and confirmed experimentally.
- AI system
- ML pre-screening + quantum geometry theory
- Human role
- Human-led with AI tools
- Verification
- Peer-reviewed in Physical Review Research; lab-validated
- Status
- confirmed
What happened
A theory-plus-ML pipeline picked candidates, and experimental partners confirmed them.
Why it matters
It is a modest but clean prediction-then-confirmation loop in superconductor research, a field full of hype.
Changelog
- 2026-09-29: created
Related events
- GNoME predicts 2.2 million new crystals, 380,000 stable, but novelty and usefulness are disputed ★★★★
Sources (2)
- pressScienceDaily: Aalto/Rice ML-screened kagome superconductors (Jul 2026)
- pressFutura Sciences: AI unveils two materials
id: 2026-06-29-ml-screened-kagome-superconductors · updated 2026-09-29 · open in the interactive timeline