Help Privacy Policy Disclaimer
  Advanced SearchBrowse




Journal Article

Efficient Gaussian Process Regression for prediction of molecular crystals harmonic free energies


Krynski,  Marcin
NOMAD, Fritz Haber Institute, Max Planck Society;
Faculty of Physics, Warsaw University of Technology;


Rossi,  Mariana
NOMAD, Fritz Haber Institute, Max Planck Society;
Max Planck Institute for the Structure and Dynamics of Matter, Max Planck Society;

External Resource
No external resources are shared
Fulltext (public)

(Preprint), 5MB

(Publisher version), 2MB

Supplementary Material (public)
There is no public supplementary material available

Krynski, M., & Rossi, M. (2021). Efficient Gaussian Process Regression for prediction of molecular crystals harmonic free energies. npj Computational Materials, 169. doi:10.1038/s41524-021-00638-x.

Cite as: http://hdl.handle.net/21.11116/0000-0008-BC7A-C
We present a method to accurately predict the Helmholtz harmonic free energies of molecular crystals in high-throughput settings. This is achieved by devising a computationally efficient framework that employs a Gaussian Process Regression model based on local atomic environments. The cost to train the model with ab initio potentials is reduced by starting the optimisation of the framework parameters, as well as the training and validation sets, with an empirical potential. This is then transferred to train the model based on density-functional theory potentials, including dispersion-corrections. We benchmarked our framework on a set of 444 hydrocarbon crystal structures, comprising 38 polymorphs, and 406 crystal structures either measured in different conditions or derived from them. Superior performance and high prediction accuracy, with mean absolute deviation below 0.04 kJ/mol/atom at 300 K is achieved by training on as little as 60 crystal structures. Furthermore, we demonstrate the predictive efficiency and accuracy of the developed framework by successfully calculating the thermal lattice expansion of aromatic hydrocarbon crystals within the quasi-harmonic approximation, and predict how lattice expansion affects the polymorph stability ranking.