A machine learning model to classify dynamic processes in liquid water

TL;DR

This paper presents a deep learning approach using recurrent neural networks to classify hydrogen bond interchange and breakage processes in liquid water, revealing a consistent ratio across various temperatures and demonstrating the potential of AI in studying molecular dynamics.

Contribution

The study introduces a novel deep learning model for classifying dynamic hydrogen bond processes in water, combining ab initio simulations with a new bond operator.

Findings

The interchange to breakage ratio is approximately 1:4.

This ratio remains stable across temperatures from 280 to 360 K.

Deep learning effectively distinguishes complex hydrogen bond dynamics.

Abstract

The dynamics of water molecules plays a vital role in understanding water. We combined computer simulation and deep learning to study the dynamics of H-bonds between water molecules. Based on ab initio molecular dynamics simulations and a newly defined directed Hydrogen (H-) bond population operator, we studied a typical dynamic process in bulk water: interchange, in which the H-bond donor reverses roles with the acceptor. By designing a recurrent neural network-based model, we have successfully classified the interchange and breakage processes in water. We have found that the ratio between them is approximately 1:4, and it hardly depends on temperatures from 280 to 360 K. This work implies that deep learning has the great potential to help distinguish complex dynamic processes containing H-bonds in other systems.