BASC: Applying Bayesian Optimization to the Search for Global Minima on Potential Energy Surfaces

Abstract

We present a novel application of Bayesian optimization to the field of surface science: rapidly and accurately searching for the global minimum on potential energy surfaces. Controlling molecule-surface interactions is key for applications ranging from environmental catalysis to gas sensing. We present pragmatic techniques, including exploration/exploitation scheduling and a custom covariance kernel that encodes the properties of our objective function. Our method, the Bayesian Active Site Calculator (BASC), outperforms differential evolution and constrained minima hopping – two state-of-the-art approaches – in trial examples of carbon monoxide adsorption on a hematite substrate, both with and without a defect.

Cite

Text

Carr et al. "BASC: Applying Bayesian Optimization to the Search for Global Minima on Potential Energy Surfaces." International Conference on Machine Learning, 2016.

Markdown

[Carr et al. "BASC: Applying Bayesian Optimization to the Search for Global Minima on Potential Energy Surfaces." International Conference on Machine Learning, 2016.](https://mlanthology.org/icml/2016/carr2016icml-basc/)

BibTeX

@inproceedings{carr2016icml-basc,
  title     = {{BASC: Applying Bayesian Optimization to the Search for Global Minima on Potential Energy Surfaces}},
  author    = {Carr, Shane and Garnett, Roman and Lo, Cynthia},
  booktitle = {International Conference on Machine Learning},
  year      = {2016},
  pages     = {898-907},
  volume    = {48},
  url       = {https://mlanthology.org/icml/2016/carr2016icml-basc/}
}