Download
Materials Discovery (GNoME) is a large-scale research initiative by Google DeepMind focused on applying graph neural networks to accelerate the discovery of stable inorganic crystal materials. The project centers on Graph Networks for Materials Exploration (GNoME), a message-passing neural network architecture trained on density functional theory (DFT) data to predict material stability and energy formation. Using GNoME, DeepMind identified 381,000 new stable materials, later expanding the dataset to include over 520,000 materials within 1 meV/atom of the convex hull as of August 2024. The repository provides datasets, model definitions, and interactive Colabs for exploring these materials, computing decomposition energies, and visualizing chemical families. Additionally, it includes JAX-based implementations of GNoME and Nequip—the latter being used to train interatomic potentials for dynamic simulations.
Features
- Dataset of 520,000+ inorganic crystal materials predicted via graph networks
- GNoME model achieving state-of-the-art energy accuracy (~21 meV/atom)
- Includes Nequip model for interatomic potential learning and dynamics
- Colab notebooks for data exploration, energy analysis, and visualization
- Results benchmarked against DFT (PBE and r²SCAN) functionals
- Released under Apache 2.0 (code) and CC BY-NC 4.0 (data) licenses
Project Samples
