Machine learning surrogate models for prediction of point defect vibrational entropy

Clovis Lapointe, Thomas D. Swinburne, Louis Thiry, Stéphane Mallat, Laurent Proville, Charlotte Becquart, Mihai‐Cosmin Marinica

Physical Review Materials · 2020 · 19 citations · 72 references

DOIFull text

Open access

Concepts

Abstract

The temperature variation of the defect densities in a crystal depends on vibrational entropy. This contribution to the system thermodynamics remains computationally challenging as it requires a diagonalization of the system's Hessian which scales as $O({N}^{3})$ for a crystal made of $N$ atoms. Here, to circumvent such a heavy computational task and make it feasible even for systems containing millions of atoms, the harmonic vibrational entropy of point defects is estimated directly from the relaxed atomic positions through a linear-in-descriptor machine learning approach of order $O(N)$. With a size-independent descriptor dimension and fixed model parameters, an excellent predictive power is demonstrated on a wide range of defect configurations, supercell sizes, and external deformations well outside the training database. In particular, formation entropies in a range of $250{k}_{B}$ are predicted with less than $1.6{k}_{B}$ error from a training database whose formation entropies span only $25{k}_{B}$ (training error less than $1.0{k}_{B}$). This exceptional transferability is found to hold even when the training is limited to a low-energy superbasin in the phase space while the tests are performed for a different liquid-like superbasin at higher energies.

References

72