Expanding the Extrapolation Limits of Neural Network Force Fields using Physics-Based Data Augmentation

Yuliia Orlova, Gavin Keith Ridley, Frederick Zhao, Rafael Gomez-Bombarelli

Keywords: neural network force fields, data augmentation

TL;DR: The extrapolation capabilities of neural network force fields were improved by utilizing physics informed data augmentation

Abstract: Even though machine learning force fields are quite accurate in the prediction of forces and energies in the sampled region, they fail to extrapolate, which results in the unphysical behavior of the system during molecular dynamics simulations. We propose to overcome this problem by performing data augmentation. To expand the original dataset random perturbations of atoms were performed. The corresponding increase in the energy of the system was calculated under the assumption of harmonicity. The required spring constants were obtained from the original dataset by fitting a gaussian mixture model to the bond lengths distribution. The resulting force field performance was improved in the regions far from training data.