Machine Learning Characterization of Structural Defects in Amorphous Packings of Dimers and Ellipses

Abstract

Structural defects within amorphous packings of symmetric particles can be characterized using a machine learning approach that incorporates structure functions of radial distances and angular arrangement. This yields a scalar field, \emph{softness}, that correlates with the probability that a particle is about to rearrange. However, when particle shapes are elongated, as in the case of dimers and ellipses, we find the standard structure functions produce imprecise softness measurements. Moreover, ellipses exhibit deformation profiles in stark contrast to circular particles. In order to account for effects of orientation and alignment, we introduce new structure functions to recover predictive performance of softness, as well as provide physical insight to local and extended dynamics. We study a model disordered solid, a bidisperse two-dimensional granular pillar, driven by uniaxial compression and composed entirely of monomers, dimers, or ellipses. We demonstrate how the computation of softness via support vector machine extends to dimers and ellipses with the introduction of new orientational structure functions. Then, we highlight the spatial extent of rearrangements and defects, as well as their cross-correlation, for each particle shape. Finally, we demonstrate how an additional machine learning algorithm, recursive feature elimination, provides an avenue to better understand how softness arises from particular structural aspects. We identify the most crucial structure functions in determining softness and discuss their physical implications.

arXiv comment16 pages, 12 figures

References in corpus (29)

• Scikit-learn: Machine Learning in Python
• On representing chemical environments
• Dynamics of Viscoplastic Deformation in Amorphous Solids
• Identifying structural flow defects in disordered solids using machine learning methods
• Vibrational modes identify soft spots in a sheared disordered packing
• Deformation and Failure of Amorphous Solidlike Materials
• Particle Shape Effects on the Stress Response of Granular Packings
• Network Analysis of Particles and Grains
• Granular materials composed of shape-anisotropic grains
• Jamming in Systems Composed of Frictionless Ellipse-Shaped Particles
• Minkowski Tensors of Anisotropic Spatial Structure
• The Relationship Between Local Structure and Relaxation in Out-of-Equilibrium Glassy Systems
• Local yield stress statistics in model amorphous solids
• A parameter-free, solid-angle based, nearest-neighbor algorithm
• Heterogeneous Dynamics, Marginal Stability and Soft Modes in Hard Sphere Glasses
• Machine learning determination of atomic dynamics at grain boundaries
• Disconnecting structure and dynamics in glassy thin films
• Particle motion during the compaction of granular matter
• Local thermal energy as a structural indicator in glasses
• Hypostatic jammed packings of frictionless nonspherical particles
• Transforming mesoscale granular plasticity through particle shape
• Constraints and vibrations in static packings of ellipsoidal particles
• Non-universal Voronoi cell shapes in amorphous ellipsoid packings
• Divergence of Voronoi cell anisotropy vector: A threshold-free characterization of local structure in amorphous materials
• Focus on Imaging Methods in Granular Physics
• Deformation-Driven Diffusion and Plastic Flow in Two-Dimensional Amorphous Granular Pillars
• Compression Driven Jamming of Athermal Frictionless Spherocylinders in Two Dimensions
• Rods are less fragile than spheres: Structural relaxation in dense liquids composed of anisotropic particles
• Anisotropic Particles Strengthen Granular Pillars under Compression

Cited by in corpus (10)

• Roadmap on machine learning glassy dynamics
• Machine Learning of Implicit Combinatorial Rules in Mechanical Metamaterials
• Fragility in Glassy Liquids: A Structural Approach Based on Machine Learning
• Machine-learning effective many-body potentials for anisotropic particles using orientation-dependent symmetry functions
• Quantifying the link between local structure and cellular rearrangements using information in models of biological tissues
• Strain localization and failure of disordered particle rafts with tunable ductility during tensile deformation
• Stress propagation in locally loaded packings of disks and pentagons
• Building a "trap model" of glassy dynamics from a local structural predictor of rearrangements
• Interplay of rearrangements, strain, and local structure during avalanche propagation
• Machine learning that predicts well may not learn the correct physical descriptions of glassy systems