Predicting orientation-dependent plastic susceptibility from static structure in amorphous solids via deep learning

Abstract

It has been a long-standing materials science challenge to establish structure-property relations in amorphous solids. Here we introduce a rotation-variant local structure representation that enables different predictions for different loading orientations, which is found essential for high-fidelity prediction of the propensity for stress-driven shear transformations. This novel structure representation, when combined with convolutional neural network (CNN), a powerful deep learning algorithm, leads to unprecedented accuracy for identifying atoms with high propensity for shear transformations (i.e., plastic susceptibility), solely from the static structure - the spatial atomic positions - in both two- and three-dimensional model glasses. The data-driven models trained on samples at one composition and a given processing history are found transferrable to glass samples with different processing histories or at different compositions in the same alloy system. Our analysis of the new structure representation also provides valuable insight into key atomic packing features that influence the local mechanical response and its anisotropy in glasses.

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Irreversible reorganization in a supercooled liquid originates from localised soft modes
• Identifying structural flow defects in disordered solids using machine learning methods
• Strain localization and percolation of stable structure in amorphous solids
• Anisotropic Structural Predictor in Glassy Materials
• Shear Transformation Zones: State Determined or Protocol Dependent?

Cited by in corpus (14)

• Topology of vibrational modes predict plastic events in glasses
• Inverse design of glass structure with deep graph neural networks
• Predicting the failure of two-dimensional silica glasses
• Convolutional neural networks enable high-fidelity prediction of path-dependent diffusion barrier spectra in multi-principal element alloys
• Predicting the location of shear band initiation in a metallic glass
• Stress Predictions in Polycrystal Plasticity using Graph Neural Networks with Subgraph Training
• Fatigue behavior of Cu-Zr metallic glasses under cyclic loading
• Structural relaxation and delayed yielding in cyclically sheared Cu-Zr metallic glasses
• Hedgehog topological defects in 3D amorphous solids
• Correlation between plastic rearrangements and local structure in a cyclically driven glass
• Self-Supervised Learning for Glass Composition Screening
• Strength of 2D Glasses Explored by Machine-Learning Force Fields
• Exploring the Relationship Between Softness and Excess Entropy in Glass-forming Systems
• Distribution of atomic rearrangement vectors in a metallic glass