Matbench Discovery:benchmarking machine learning energy models for materials discovery.

Matbench Discovery is a platform for benchmarking machine learning energy models for materials discovery. It provides a comprehensive test set and metrics to evaluate model performance, including metrics like CPS (Composite Performance Score), Accuracy, F1-score, MAE, R^2, and RMSE. The platform aims to foster the development of more accurate and reliable models for accelerating materials research.


Citation: Riebesell, Janosh, Rhys EA 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 preprint arXiv:2308.14920 (2023).

Acknowledgement: Riebesell, Janosh, Rhys E. A. Goodall, Philipp Benner, Yuan Chiang, Bowen Deng, Alpha A. Lee, Anubhav Jain, and Kristin A. Persson