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

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.

11 pages, 10 figures, a typo fixed in the title; accepted in J. Chem. Phys

References in corpus (11)

• Theoretical perspective on the glass transition and amorphous materials
• Fast Graph Representation Learning with PyTorch Geometric
• The role of local structure in dynamical arrest
• Irreversible reorganization in a supercooled liquid originates from localised soft modes
• Identifying structural flow defects in disordered solids using machine learning methods
• The Relationship Between Local Structure and Relaxation in Out-of-Equilibrium Glassy Systems
• Predicting dynamic heterogeneity in glass-forming liquids by physics-inspired machine learning
• Relationship between bond-breakage correlations and four-point correlations in heterogeneous glassy dynamics: Configuration changes and vibration modes
• Comparing machine learning techniques for predicting glassy dynamics
• Dimensionality reduction of local structure in glassy binary mixtures
• Connection between fragility, mean-squared displacement and shear modulus in two van der Waals bonded glass-forming liquids

Cited by in corpus (13)

• Predicting dynamic heterogeneity in glass-forming liquids by physics-inspired machine learning
• Roadmap on machine learning glassy dynamics
• Improving the prediction of glassy dynamics by pinpointing the local cage
• Dynamic heterogeneity at the experimental glass transition predicted by transferable machine learning
• Geometry-enhanced graph neural network for learning the smoothness of glassy dynamics from static structure
• Rotation-equivariant Graph Neural Networks for Learning Glassy Liquids Representations
• Unraveling the dynamic slowdown in supercooled water: The role of dynamic disorder in jump motions
• Selecting Relevant Structural Features for Glassy Dynamics by Information Imbalance
• A deep learning approach to the measurement of long-lived memory kernels from Generalised Langevin Dynamics
• Building a "trap model" of glassy dynamics from a local structural predictor of rearrangements
• Graph neural network-based structural classification of glass-forming liquids and its interpretation via self-attention mechanism
• Towards interpreting the thermally activated $\beta$ dynamics in metallic glass with the structural constraint neural network
• Interpretability of linear regression models of glassy dynamics