# Graph Dynamical Networks for Unsupervised Learning of Atomic Scale Dynamics in Materials

## TL;DR

This paper introduces graph dynamical networks, an unsupervised learning method that captures atomic scale dynamics from molecular simulations, aiding materials design by analyzing complex local environments.

## Contribution

The work presents a novel unsupervised graph neural network approach for learning atomic dynamics across various phases and environments from molecular dynamics data.

## Key findings

- Successfully learned dynamical information for multi-component amorphous materials
- Applicable to diverse phases and environments in molecular simulations
- Provides an automated tool for analyzing atomic scale dynamics

## Abstract

Understanding the dynamical processes that govern the performance of functional materials is essential for the design of next generation materials to tackle global energy and environmental challenges. Many of these processes involve the dynamics of individual atoms or small molecules in condensed phases, e.g. lithium ions in electrolytes, water molecules in membranes, molten atoms at interfaces, etc., which are difficult to understand due to the complexity of local environments. In this work, we develop graph dynamical networks, an unsupervised learning approach for understanding atomic scale dynamics in arbitrary phases and environments from molecular dynamics simulations. We show that important dynamical information can be learned for various multi-component amorphous material systems, which is difficult to obtain otherwise. With the large amounts of molecular dynamics data generated everyday in nearly every aspect of materials design, this approach provides a broadly useful, automated tool to understand atomic scale dynamics in material systems.