Geometry Optimization in Internal Coordinates Based on Gaussian Process Regression: Comparison of Two Approaches
- Daniel BornDaniel BornInstitute for Theoretical Chemistry, University of Stuttgart, Pfaffenwaldring 55, 70569 Stuttgart, GermanyMore by Daniel Born
- and
- Johannes Kästner*Johannes Kästner*Email: [email protected]Institute for Theoretical Chemistry, University of Stuttgart, Pfaffenwaldring 55, 70569 Stuttgart, GermanyMore by Johannes Kästner
Abstract
Geometry optimization based on Gaussian process regression (GPR) was extended to internal coordinates. We used delocalized internal coordinates composed of distances and several types of angles and compared two methods of including them. In both cases, the GPR surrogate surface is trained on geometries in internal coordinates. In one case, it predicts the gradient in Cartesian coordinates and in the other, in internal coordinates. We tested both methods on a set of 30 small molecules and one larger Rh complex taken from the study of a catalytic mechanism. The former method is slightly more efficient, while the latter method is somewhat more robust. Both methods reduce the number of required optimization steps compared to GPR in Cartesian coordinates or the standard L-BFGS optimizer. We found it advantageous to use automatically adjusted hyperparameters to optimize them.
Cited By
This article is cited by 7 publications.
- Chong Teng, Yang Wang, Daniel Huang, Katherine Martin, Jean-Baptiste Tristan, Junwei Lucas Bao. Dual-Level Training of Gaussian Processes with Physically Inspired Priors for Geometry Optimizations. Journal of Chemical Theory and Computation 2022, 18 (9) , 5739-5754. https://doi.org/10.1021/acs.jctc.2c00546
- Chong Teng, Daniel Huang, Junwei Lucas Bao. A spur to molecular geometry optimization: Gradient-enhanced universal kriging with on-the-fly adaptive ab initio prior mean functions in curvilinear coordinates. The Journal of Chemical Physics 2023, 158 (2) , 024112. https://doi.org/10.1063/5.0133675
- Roland Lindh, Ignacio Fdez. Galván. Molecular structure optimizations with Gaussian process regression. 2023, 391-428. https://doi.org/10.1016/B978-0-323-90049-2.00017-2
- Stefan Heinen, Guido Falk von Rudorff, O. Anatole von Lilienfeld. Transition state search and geometry relaxation throughout chemical compound space with quantum machine learning. The Journal of Chemical Physics 2022, 157 (22) , 221102. https://doi.org/10.1063/5.0112856
- Haoyan Huo, Matthias Rupp. Unified representation of molecules and crystals for machine learning. Machine Learning: Science and Technology 2022, 3 (4) , 045017. https://doi.org/10.1088/2632-2153/aca005
- Ryan Snyder, Bryant Kim, Xiaoliang Pan, Yihan Shao, Jingzhi Pu. Facilitating ab initio QM/MM free energy simulations by Gaussian process regression with derivative observations. Physical Chemistry Chemical Physics 2022, 24 (41) , 25134-25143. https://doi.org/10.1039/D2CP02820D
- Han Yan, Xiong Xu, Peng Li, Peijie He, Qing Peng, Can Ding. Aluminum Doping Effect on Surface Structure of Silver Ultrathin Films. Materials 2022, 15 (2) , 648. https://doi.org/10.3390/ma15020648