Identifying structural flow defects in disordered solids using machine learning methods

Abstract

We use machine learning methods on local structure to identify flow defects - or regions susceptible to rearrangement - in jammed and glassy systems. We apply this method successfully to two disparate systems: a two dimensional experimental realization of a granular pillar under compression, and a Lennard-Jones glass in both two and three dimensions above and below its glass transition temperature. We also identify characteristics of flow defects that differentiate them from the rest of the sample. Our results show it is possible to discern subtle structural features responsible for heterogeneous dynamics observed across a broad range of disordered materials.

4 pages, 4 figures

References in corpus (20)

• Dynamics of Viscoplastic Deformation in Amorphous Solids
• Irreversible reorganization in a supercooled liquid originates from localised soft modes
• Vibrational modes identify soft spots in a sheared disordered packing
• A kinetic theory of plastic flow in soft glassy materials
• Deformation and Failure of Amorphous Solidlike Materials
• Nucleation mechanism for the direct graphite-to-diamond phase transition
• Understanding fragility in supercooled Lennard-Jones mixtures. I. Locally preferred structures
• Avalanches and Dynamical Correlations in supercooled liquids
• Excitations are localized and relaxation is hierarchical in glass-forming liquids
• On the density of shear transformation zones in amorphous solids
• Measurement of correlations between low-frequency vibrational modes and particle rearrangements in quasi-two-dimensional colloidal glasses
• On the Study of Collective Dynamics in Supercooled Liquids through the Statistics of the Iso-Configurational Ensemble
• Heterogeneous Dynamics, Marginal Stability and Soft Modes in Hard Sphere Glasses
• Localised soft modes and the supercooled liquid's irreversible passage through its configuration space
• Information-theoretic measurements of coupling between structure and dynamics in glass-formers
• Predicting plasticity with soft vibrational modes: from dislocations to glasses
• Lifetimes and Lengthscales of Structural Motifs in a Model Glassformer
• Phonons in two-dimensional soft colloidal crystals
• Are there localized saddles behind the heterogeneous dynamics of supercooled liquids?
• A small subset of normal modes mimics the properties of dynamical heterogeneity in a model supercooled liquid

Cited by in corpus (126)

• Machine learning and the physical sciences
• Unified Representation of Molecules and Crystals for Machine Learning
• Predicting plasticity in disordered solids from structural indicators
• Autonomously revealing hidden local structures in supercooled liquids
• Machine learning in nuclear materials research
• The Relationship Between Local Structure and Relaxation in Out-of-Equilibrium Glassy Systems
• Local yield stress statistics in model amorphous solids
• Modern computational studies of the glass transition
• Machine learning plastic deformation of crystals
• Machine learning determination of atomic dynamics at grain boundaries
• A transferable machine-learning framework linking interstice distribution and plastic heterogeneity in metallic glasses
• Disconnecting structure and dynamics in glassy thin films
• Widom delta of supercritical gas-liquid coexistence
• Local thermal energy as a structural indicator in glasses
• Averaging local structure to predict the dynamic propensity in supercooled liquids
• Predicting orientation-dependent plastic susceptibility from static structure in amorphous solids via deep learning
• Anomalous glassy dynamics in simple models of dense biological tissue
• Uncovering the effects of interface-induced ordering of liquid on crystal growth using machine learning
• Absence of Marginal Stability in a Structural Glass
• Machine Learning in a data-limited regime: Augmenting experiments with synthetic data uncovers order in crumpled sheets
• A characteristic energy scale in glasses
• Assessing the structural heterogeneity of supercooled liquids through community inference
• Structures of local rearrangements in soft colloidal glasses
• Predicting dynamic heterogeneity in glass-forming liquids by physics-inspired machine learning
• Estimating physical properties from liquid crystal textures via machine learning and complexity-entropy methods
• Non-Equilibrium Phase Transition in an Atomistic Glassformer: the Connection to Thermodynamics
• Inverse design of glass structure with deep graph neural networks
• Divergence of Voronoi cell anisotropy vector: A threshold-free characterization of local structure in amorphous materials
• Attractive versus truncated repulsive supercooled liquids: The dynamics is encoded in the pair correlation function
• From glass formation to icosahedral ordering by curving three-dimensional space
• Predicting the failure of two-dimensional silica glasses
• Electronic structure calculations of twisted multi-layer graphene superlattices
• Locally favoured structures and dynamic length scales in a simple glass-former
• Robust Prediction of Force Chains in Jammed Solids using Graph Neural Networks
• Comparing machine learning techniques for predicting glassy dynamics
• A machine-learning solver for modified diffusion equations
• BOTAN: BOnd TArgeting Network for prediction of slow glassy dynamics by machine learning relative motion
• Roadmap on machine learning glassy dynamics
• Machine Learning of Implicit Combinatorial Rules in Mechanical Metamaterials
• Dimensionality reduction of local structure in glassy binary mixtures
• Glass-like behavior of a hard-disk fluid confined to a narrow channel
• Direct evidence of void induced structural relaxations in colloidal glass formers
• Deformation and flow of amorphous solids: An updated review of mesoscale elastoplastic models
• Anisotropic Structural Predictor in Glassy Materials
• Machine learning based localization and classification with atomic magnetometers
• Machine Learning Characterization of Structural Defects in Amorphous Packings of Dimers and Ellipses
• Deformation-Driven Diffusion and Plastic Flow in Two-Dimensional Amorphous Granular Pillars
• A Microscopic Theory of Softness in Supercooled Liquids
• Low-temperature anomalies of a vapor deposited glass
• Improving the prediction of glassy dynamics by pinpointing the local cage
• Fragility in Glassy Liquids: A Structural Approach Based on Machine Learning
• Atomic nonaffinity as a predictor of plasticity in amorphous solids
• Predicting the location of shear band initiation in a metallic glass
• Universality, scaling and collapse in supercritical fluids
• Machine learning electron correlation in a disordered medium
• Instabilities of jammed packings of frictionless spheres under compression
• A model for the fragmentation kinetics of crumpled thin sheets
• Learning a Local Symmetry with Neural-Networks
• Combining Machine Learning and Physics to Understand Glassy Systems
• Role of disorder in determining the vibrational properties of mass-spring networks
• Understanding the fragile-to-strong transition in silica from microscopic dynamics
• Dynamic heterogeneity at the experimental glass transition predicted by transferable machine learning
• Quantifying the link between local structure and cellular rearrangements using information in models of biological tissues
• Identifying structural signature of dynamical heterogeneity via the local softness parameter
• Correlation of plastic events with local structure in jammed packings across spatial dimensions
• Discovering dynamic laws from observations: the case of self-propelled, interacting colloids
• Multi-component generalized mode-coupling theory: Predicting dynamics from structure in glassy mixtures
• Strain localization and failure of disordered particle rafts with tunable ductility during tensile deformation
• Geometry-enhanced graph neural network for learning the smoothness of glassy dynamics from static structure
• Role of structure in the alpha and beta dynamics of a simple glass-forming liquid
• Collective drifts in vibrated granular packings: the interplay of friction and structure
• Detection of Islands and Droplets on Smectic Films Using Machine Learning
• Rotation-equivariant Graph Neural Networks for Learning Glassy Liquids Representations
• Exploring glassy dynamics with Markov state models from graph dynamical neural networks
• Anisotropic Particles Strengthen Granular Pillars under Compression
• Local Plastic Response and Slow Heterogeneous Dynamics of Supercooled Liquids
• The Role of Local Structure in the Enhanced Dynamics of Deformed Glasses
• Machine learning and predicting the time dependent dynamics of local yielding in dry foams
• 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
• Internally-stressed and positionally-disordered minimal complexes yield glasslike nonphononic excitations
• Stagnant Zone Formation in a 2D Bed of Circular and Elongated Grains under Penetration
• The Spectrum of Structure for Jammed and Unjammed Soft Disks
• Dead or alive: Distinguishing active from passive particles using supervised learning
• Machine learning glass caging order parameters with an artificial nested neural network
• Selecting Relevant Structural Features for Glassy Dynamics by Information Imbalance
• Shear induced ordering in systems with competing interactions: A machine learning study
• Condensed-phase molecular representation to link structure and thermodynamics in molecular dynamics
• Strain fluctuations and elastic moduli in disordered solids
• 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 rearrangements and soft modes in polymer glasses during deformation and recovery
• Emerging contact force heterogeneity in ordered soft granular media
• Direct detection of plasticity onset through total-strain profile evolution
• Structure in Sheared Supercooled Liquids: Dynamical Rearrangements of an Effective System of Icosahedra
• Decoding Non-Linearity and Complexity: Deep Tabular Learning Approaches for Materials Science
• Beyond Quality and Quantity: Contact Distribution Encodes Frictional Strength
• Gauge invariance and hyperforce correlation theory for equilibrium fluid mixtures
• Correlation between plastic rearrangements and local structure in a cyclically driven glass
• Interplay of rearrangements, strain, and local structure during avalanche propagation
• Inferring the particle-wise dynamics of amorphous solids from the local structure at the jamming point
• Automated characterization of spatial and dynamical heterogeneity in supercooled liquids via implementation of Machine Learning
• Persistent Homology for Structural Characterization in Disordered Systems
• Rearrangements during slow compression of a jammed two-dimensional emulsion
• Effects of Polydispersity on the Plastic Behaviors of Dense 2D Granular Systems Under Shear
• Strength of 2D Glasses Explored by Machine-Learning Force Fields
• Towards interpreting the thermally activated $\beta$ dynamics in metallic glass with the structural constraint neural network
• Distribution of atomic rearrangement vectors in a metallic glass
• On the geometry of topological defects in glasses
• Slow Spin Dynamics and Self-Sustained Clusters in Sparsely Connected Systems
• Shape matters: Inferring the motility of confluent cells from static images
• Understanding Flow Behaviors of Supercooled Liquids by Embodying Solid-Liquid Duality at Particle Level
• Does mesoscopic elasticity control viscous slowing down in glassforming liquids?
• Unearthing the anticrystal: criticality in the linear response of disordered solids
• Machine learning that predicts well may not learn the correct physical descriptions of glassy systems
• A2I Transformer: Permutation-equivariant attention network for pairwise and many-body interactions with minimal featurization
• On-lattice voxelated convolutional neural networks for prediction of phase diagrams and diffusion barriers in cubic alloys
• Nonaffine motion in flowing highly polydisperse granular media
• Unsupervised classification of disordered patterns in an oppositely charged colloidal system
• Interpretability of linear regression models of glassy dynamics
• Preserving elastic anisotropy with tessellations of granular packings
• A machine learning assessment of the two states model for lipid bilayer phase transitions
• Identifying structural signatures of shear banding in model polymer nanopillars
• Learning-based approach to plasticity in athermal sheared amorphous packings: Improving softness
• Adaptive Latent Space Tuning for Non-Stationary Distributions
• Spotting structural defects in crystals from the topology of vibrational modes