Large-scale prediction of new stable crystalline materials (GNoME)
Large-scale prediction of new stable crystalline materials (GNoME) is graded disputed on whataifound.org, with the AI's role graded search scaffold.
GNoME predicted about 2.2 million new inorganic crystal structures, roughly 380,000 of them flagged as thermodynamically stable, presented as an order-of-magnitude expansion of known stable materials.
- Verification
- Disputed
- Autonomy
- Search scaffold
- Lab
- Google DeepMind
- Model
- GNoME (graph neural network)
- Field
- Materials science
- Date
- 2023-11-29
What was found
Graph Networks for Materials Exploration (GNoME) is a graph neural network trained in an active-learning loop against density-functional-theory calculations to predict formation energies and filter candidates by stability. DeepMind released the predicted structures as a public dataset. Published in Nature.
Novelty check
Stable-material prediction builds on the Materials Project and OQMD convex-hull databases. The dispute below is precisely about how much of GNoME's set is genuinely new relative to those existing catalogues.
Caveats
Substantive objections were raised and remain unresolved. Cheetham and Seshadri, reviewing the release, found 'scant evidence for compounds that fulfil the trifecta of novelty, credibility and utility,' noting that many entries are minor substitutional variants, radioactive, or otherwise unlikely to be useful. Stability here means a DFT convex-hull prediction, not experimental synthesis; the headline counts are predicted, not made.
Independent checks
Cheetham & Seshadri (critical review): disputed the novelty and utility of most predicted compounds · link ↗
Sources
Community discussion
How this is graded
whataifound.org grades every entry on two axes: verification (how solid the result is, from a machine-checked proof down to refuted) and autonomy (how much the AI did versus its human collaborators). This finding is disputed and search scaffold. Full definitions are in the methodology.
Cite this entry
whataifound.org (2023). Large-scale prediction of new stable crystalline materials (GNoME). whataifound.org: A Registry of AI Scientific and Mathematical Discoveries. https://whataifound.org/finding/2023-11-29-gnome