Molecular Hessian matrices from a machine learning random forest regression algorithm

Abstract

In this article we present a machine learning model to obtain fast and accurate estimates of the molecular Hessian matrix. In this model, based on a random forest, the second derivatives of the energy with respect to redundant internal coordinates are learned individually. The internal coordinates together with their specific representation guarantee rotational and translational invariance. The model is trained on a subset of the QM7 data set, but is shown to be applicable to larger molecules picked from the QM9 data set. From the predicted Hessian it is also possible to obtain reasonable estimates of the vibrational frequencies, normal modes and zero point energies of the molecules.