Neural Network Interatomic Potentials for Water

Water is the most important liquid on Earth. And difficult to describe theoretically, due to a delicate balance of weak and strong interactions tuned by entropic effects. High level ab initio calculations, such as Coupled Cluster (CC), can do the job, but albeit highly accurate their application is limited to systems with a few molecules due to their computational cost, not being amenable to simulate liquid water. Recent developments in density functional theory (DFT), i.e. new functionals and better description of van der Waals interactions, have made it possible to describe water with reasonable accuracy, and a good cost/accuracy compromise. Yet, even with DFT it is difficult to perform simulations on large systems at long time scales.
Artificial Neural Networks (ANN) force fields have been shown to be able to yield accurate (on par with the method they were fitted to) results with low cost. In this work we employ ANNs to represent the water potential surface with DFT- and CC-quality, and compare ANNs trained at different levels of theory to discuss the accuracy of different methods in describing macroscopic properties of water under different conditions including nuclear quantum effects.