DeepMind’s GNoME predicts 2.2 million new crystals, 380,000 of them stable
See how this story connectsGoogle DeepMind reported in Nature that its GNoME deep-learning tool found 2.2 million new crystal structures, of which 380,000 are predicted to be stable, and contributed those to Berkeley Lab’s Materials Project. Outside labs had independently made 736 of the structures, and a second Nature paper with Berkeley Lab showed autonomous synthesis guided by the predictions.
Why it matters
Materials scientists working on batteries, chips and superconductors gained 380,000 predicted-stable candidates in the open Materials Project database.
- When
- 29 Nov 2023
- ID
WTA-N-2023-0183- Where
- United Kingdom, United States
- Who
- Google DeepMind, Lawrence Berkeley National Laboratory
- Topics
- Materials
Summary by wheresthe.ai, from Google DeepMind and the reporting credited above. Checked against the source on 9 Oct 2026.
Source copy: download the page as saved on 18 Oct 2026 (PDF). Also held by the Internet Archive.
Cite this story
WTA-N-2023-0183: “DeepMind’s GNoME predicts 2.2 million new crystals, 380,000 of them stable.” wheresthe.ai, 29 Nov 2023. https://wheresthe.ai/d/gb-deepmind-gnome-materials-2023-11/ (source: Google DeepMind).
Spotted an error? Email [email protected].