Vibrational Properties of Metastable Polymorph Structures by Machine Learning.

Despite vibrational properties being critical for the ab initio prediction of finite-temperature stability as well as thermal conductivity and other transport properties of solids, their inclusion in ab initio materials repositories has been hindered by expensive computational requirements. Here we tackle the challenge, by showing that a good estimation of force constants and vibrational properties can be quickly achieved from the knowledge of atomic equilibrium positions using machine learning. A random-forest algorithm trained on 121 different mechanically stable structures of KZnF3 reaches a mean absolute error of 0.17 eV/Å2 for the interatomic force constants, and it is less expensive than training the complete force field for such compounds. The predicted force constants are then used to estimate phonon spectral features, heat capacities, vibrational entropies, and vibrational free energies, which compare well with the ab initio ones. The approach can be used for the rapid estimation of stability at finite temperatures.