Exploring glassy dynamics with Markov state models from graph dynamical neural networks

Abstract

Amorphous materials exhibit structural heterogeneities that relax only on long timescales. Using machine learning techniques, we construct a Markov state model (MSM) for model glass formers that coarse-grains the dynamics into a low-dimensional space, in which transitions occur with rates corresponding to the slowest modes of the system. The transition timescale between states is more than an order of magnitude larger than the conventional alpha-relaxation time, and reveals a fragile to strong crossover at the glass transition. The learned map of states assigned to the particles exhibits correlations of a few molecular diameters both at liquid and glassy temperatures. We show that the MSM effectively constructs a map of scaled excess Voronoi volume, and the free energy difference between the two states is given exactly by the entropy of the these distributions. These results resonate with classic free volume theories of the glass transition, singling out local packing fluctuations as the slowest relaxing features.

References in corpus (7)

• Theoretical perspective on the glass transition and amorphous materials
• Irreversible reorganization in a supercooled liquid originates from localised soft modes
• Identifying structural flow defects in disordered solids using machine learning methods
• Dynamic heterogeneity in amorphous materials
• Graph Dynamical Networks for Unsupervised Learning of Atomic Scale Dynamics in Materials
• The building blocks of dynamical heterogeneities in dense granular media
• The Relationship Between Local Structure and Relaxation in Out-of-Equilibrium Glassy Systems

Cited by in corpus (6)

• Predicting dynamic heterogeneity in glass-forming liquids by physics-inspired machine learning
• Roadmap on machine learning glassy dynamics
• Dynamic heterogeneity at the experimental glass transition predicted by transferable machine learning
• Graph neural network-based structural classification of glass-forming liquids and its interpretation via self-attention mechanism
• Compressing and forecasting atomic material simulations with descriptors
• Countering adversarial perturbations in graphs using error correcting codes