Averaging local structure to predict the dynamic propensity in supercooled liquids

Abstract

Predicting the local dynamics of supercooled liquids based purely on local structure is a key challenge in our quest for understanding glassy materials. Recent years have seen an explosion of methods for making such a prediction, often via the application of increasingly complex machine learning techniques. The best predictions so far have involved so-called Graph Neural Networks (GNN) whose accuracy comes at a cost of models that involve on the order of 10${}^5$ fit parameters. In this Letter, we propose that the key structural ingredient to the GNN method is its ability to consider not only the local structure around a central particle, but also averaged structural features centered around nearby particles. We demonstrate that this insight can be exploited to design a significantly more efficient model that provides essentially the same predictive power at a fraction of the computational complexity (approximately 1000 fit parameters), and demonstrate its success by fitting the dynamic propensity of Kob-Andersen and binary hard-sphere mixtures. We then use this to make predictions regarding the importance of radial and angular descriptors in the dynamics of both models.

arXiv commentSI is included as an ancillary file

References in corpus (22)

• Scikit-learn: Machine Learning in Python
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Testing Mode-Coupling Theory for a Supercooled Binary Lennard-Jones Mixture I: The van Hove Correlation Function
• Irreversible reorganization in a supercooled liquid originates from localised soft modes
• The role of local structure in dynamical arrest
• Identifying structural flow defects in disordered solids using machine learning methods
• Predicting the long time dynamic heterogeneity in a supercooled liquid on the basis of short time heterogeneities
• Roles of icosahedral and crystal-like order in hard spheres glass transition
• Global Attention based Graph Convolutional Neural Networks for Improved Materials Property Prediction
• Predicting plasticity in disordered solids from structural indicators
• Autonomously revealing hidden local structures in supercooled liquids
• The Relationship Between Local Structure and Relaxation in Out-of-Equilibrium Glassy Systems
• Structure and dynamics in glass-formers: predictability at large length scales
• Identification of long-lived clusters and their link to slow dynamics in a model glass former
• What does the potential energy landscape tell us about the dynamics of supercooled liquids and glasses?
• Correlation of Local Order with Particle Mobility in Supercooled Liquids is Highly System Dependent
• Learning to fail: Predicting fracture evolution in brittle material models using recurrent graph convolutional neural networks
• Assessing the structural heterogeneity of supercooled liquids through community inference
• Revealing the three-dimensional structure of liquids using four-point correlation functions
• Attractive versus truncated repulsive supercooled liquids: The dynamics is encoded in the pair correlation function
• Tetrahedrality dictates dynamics in hard spheres
• Modeling of many-body interactions between elastic spheres through symmetry functions

Cited by in corpus (36)

• Colloidal Hard Spheres: Triumphs, Challenges and Mysteries
• Predicting dynamic heterogeneity in glass-forming liquids by physics-inspired machine learning
• Relevance of Shear Transformations in the Relaxation of Supercooled Liquids
• Comparing machine learning techniques for predicting glassy dynamics
• Roadmap on machine learning glassy dynamics
• BOTAN: BOnd TArgeting Network for prediction of slow glassy dynamics by machine learning relative motion
• Dimensionality reduction of local structure in glassy binary mixtures
• Finding defects in glasses through machine learning
• Improving the prediction of glassy dynamics by pinpointing the local cage
• Data-driven identification and analysis of the glass transition in polymer melts
• Dynamic heterogeneity at the experimental glass transition predicted by transferable machine learning
• Correlation of plastic events with local structure in jammed packings across spatial dimensions
• 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
• Controlling crystallization: What liquid structure and dynamics reveal about crystal nucleation mechanisms
• Noether invariance theory for the equilibrium force structure of soft matter
• Classifying the age of a glass based on structural properties: A machine learning approach
• Unraveling the dynamic slowdown in supercooled water: The role of dynamic disorder in jump motions
• Machine learning glass caging order parameters with an artificial nested neural network
• Dead or alive: Distinguishing active from passive particles using supervised learning
• Selecting Relevant Structural Features for Glassy Dynamics by Information Imbalance
• Condensed-phase molecular representation to link structure and thermodynamics in molecular dynamics
• Graph neural network-based structural classification of glass-forming liquids and its interpretation via self-attention mechanism
• Building a "trap model" of glassy dynamics from a local structural predictor of rearrangements
• Correlation between plastic rearrangements and local structure in a cyclically driven glass
• Revisiting the single-saddle model for the $\beta$-relaxation of supercooled liquids
• Towards interpreting the thermally activated $\beta$ dynamics in metallic glass with the structural constraint neural network
• Effects of Polydispersity on the Plastic Behaviors of Dense 2D Granular Systems Under Shear
• Rearrangements during slow compression of a jammed two-dimensional emulsion
• Shape matters: Inferring the motility of confluent cells from static images
• On the geometry of topological defects in glasses
• Understanding Flow Behaviors of Supercooled Liquids by Embodying Solid-Liquid Duality at Particle Level
• Machine learning that predicts well may not learn the correct physical descriptions of glassy systems
• Active Matter as a framework for living systems-inspired Robophysics
• Irregular Metamaterial Networks
• Interpretability of linear regression models of glassy dynamics