BOTAN: BOnd TArgeting Network for prediction of slow glassy dynamics by machine learning relative motion

TL;DR

BOTAN is a graph neural network that predicts slow glassy dynamics by learning both particle self-motion and relative motion, enabling detailed understanding of structural relaxation in glass-forming systems.

Contribution

The paper introduces BOTAN, a novel graph neural network that simultaneously learns particle self-motion and relative motion, improving predictions of glassy dynamics.

Findings

High-precision predictions of slow structural relaxation.

Ability to distinguish effects of strain and rearrangements.

Enhanced understanding of glassy dynamics mechanisms.

Abstract

Recent developments in machine learning have enabled accurate predictions of the dynamics of slow structural relaxation in glass-forming systems. However, existing machine-learning models for these tasks are mostly designed such that they learn a single dynamic quantity and relate it to the structural features of glassy liquids. In this study, we propose a graph neural network model, ``BOnd TArgeting Network (BOTAN)'', that learns relative motion between neighboring pairs of particles, in addition to the self-motion of particles. By relating the structural features to these two different dynamical variables, the model autonomously acquires the ability to discern how different dynamical processes, strain fluctuations and particle rearrangements, affect the self-motion of particles undergoing slow relaxation, and thus can predict with high precision how slow structural relaxation develops in space and time.