Finding defects in glasses through machine learning

Abstract

Structural defects control the kinetic, thermodynamic and mechanical properties of glasses. For instance, rare quantum tunneling two-level systems (TLS) govern the physics of glasses at very low temperature. Because of their extremely low density, it is very hard to directly identify them in computer simulations. We introduce a machine learning approach to efficiently explore the potential energy landscape of glass models and identify desired classes of defects. We focus in particular on TLS and we design an algorithm that is able to rapidly predict the quantum splitting between any two amorphous configurations produced by classical simulations. This in turn allows us to shift the computational effort towards the collection and identification of a larger number of TLS, rather than the useless characterization of non-tunneling defects which are much more abundant. Finally, we interpret our machine learning model to understand how TLS are identified and characterized, thus giving direct physical insight into their microscopic nature.

References in corpus (13)

• Accurate determination of crystal structures based on averaged local bond order parameters
• Suppression of tunneling two-level systems in ultrastable glasses of indomethacin
• Two-Level Systems and Boson Peak Remain Stable in 110-Million-Year-Old Amber Glass
• Low-energy quasilocalized excitations in structural glasses
• Averaging local structure to predict the dynamic propensity in supercooled liquids
• Controlling Structure and Properties of Vapor-Deposited Glasses of Organic Semiconductors: Recent Advances and Challenges
• Predicting dynamic heterogeneity in glass-forming liquids by physics-inspired machine learning
• Fragility in Glassy Liquids: A Structural Approach Based on Machine Learning
• Barrier height prediction by machine learning correction of semiempirical calculations
• Correlation of plastic events with local structure in jammed packings across spatial dimensions
• Microscopic observation of two-level systems in a metallic glass model
• Relationship between two-level systems and quasi-localized normal modes in glasses
• Signatures of Many-Body Localization in the Dynamics of Two-Level Systems in Glasses

Cited by in corpus (9)

• Roadmap on machine learning glassy dynamics
• Classifying the age of a glass based on structural properties: A machine learning approach
• Selecting Relevant Structural Features for Glassy Dynamics by Information Imbalance
• Graph neural network-based structural classification of glass-forming liquids and its interpretation via self-attention mechanism
• Hedgehog topological defects in 3D amorphous solids
• Two-level systems and harmonic excitations in a mean-field anharmonic quantum glass
• Shape matters: Inferring the motility of confluent cells from static images
• Nearest-Neighbours Neural Network architecture for efficient sampling of statistical physics models
• Interpretability of linear regression models of glassy dynamics