Matbench Discovery

[](https://arxiv.org/abs/2308.14920) [](https://github.com/janosh/matbench-discovery/actions/workflows/test.yml) [](https://github.com/janosh/matbench-discovery/actions/workflows/gh-pages.yml) [](https://python.org/downloads) [](https://pypi.org/project/matbench-discovery?logo=pypi&logoColor=white)

Disclaimer: We evaluate how accurately ML models predict solid-state thermodynamic stability. Although this is an important aspect of high-throughput materials discovery, the ranking cannot give a complete picture of a model's general applicability to materials. A high ranking does not constitute endorsement by the Materials Project.

Matbench Discovery is an interactive leaderboard and associated PyPI package which together make it easy to rank ML energy models on a task designed to simulate high-throughput discovery of new stable inorganic crystals.

We've tested models covering multiple methodologies including graph neural network (GNN) interatomic potentials, GNN one-shot predictors, iterative Bayesian optimizers and random forests with shallow-learning structure fingerprints.

Our results show that ML models have become robust enough to deploy them as triaging steps to more effectively allocate compute in high-throughput DFT relaxations. This work provides valuable insights for anyone looking to build large-scale materials databases.

If you'd like to refer to Matbench Discovery in a publication, please cite the preprint:

Janosh Riebesell, Rhys E. A. Goodall, Philipp Benner, Yuan Chiang, Bowen Deng, Alpha A. Lee, Anubhav Jain, and Kristin A. Persson. "Matbench Discovery -- A Framework to Evaluate Machine Learning Crystal Stability Predictions." arXiv, August 28, 2023. https://doi.org/10.48550/arXiv.2308.14920.

We welcome new models additions to the leaderboard through GitHub PRs. See the contributing guide for details and ask support questions via GitHub discussion.

For detailed results and analysis, check out the preprint.