Improving the reliability of machine learned potentials for modeling inhomogenous liquids
The atomic-scale response of inhomogeneous fluids at interfaces and surrounding solute particles plays a critical role in governing chemical, electrochemical and biological processes at such interfaces. Classical molecular dynamics simulations have been applied extensively to simulate the response of inhomogeneous fluids directly, and as inputs to classical density functional theory, but are limited by the accuracy of the underlying empirical force fields. Here, we deploy neural network potentials (NNPs) trained to ab initio simulations to accurately predict the inhomogeneous response of two widely different fluids: liquid water and molten NaCl. Although NNPs can be readily trained to model complex bulk systems across a range of state points, in order to appropriately model a fluid's response at an interface, inhomogeneous configurations must be included in the training data. We establish protocols based on molecular dynamics simulations in external atomic potentials in order to sufficiently sample the correct configurations of inhomogeneous fluids. We show that NNPs trained to inhomogeneous fluid configurations can predict several properties such as the density response, surface tension and size-dependent cavitation free energies in water and molten NaCl corresponding to ab initio interactions more accurately than empirical force fields. This work therefore provides a first demonstration and framework for extracting the response of inhomogeneous fluids from first principles for classical density-functional treatment of fluids free from empirical potentials.