Self-Supervised Learning for Glass Composition Screening

Abstract

Glass composition screening is essential for advancing new glass materials, yet the inherent complexity of multicomponent systems presents significant challenges. Current supervised learning methods for this task rely heavily on large amounts of high-quality data and are prone to overfitting on noisy samples, which limits their generalization ability. In this work, we propose a novel self-supervised learning framework designed specifically for screening glass compositions within pre-defined glass transition temperature (Tg) ranges. We reformulate the screening task as a classification problem, aiming to predict whether the glass transition temperature of a given composition falls within a target interval. To improve the model's robustness to noise, we introduce an innovative data augmentation strategy grounded in asymptotic theory. Additionally, we present DeepGlassNet, a dedicated network architecture developed to capture and analyze the complex interactions among constituent elements in glass compositions. Experimental results demonstrate that DeepGlassNet achieves superior screening accuracy compared to traditional methods and exhibits strong adaptability to other composition-related screening tasks. This study not only provides an efficient methodology for designing multicomponent glasses but also establishes a foundation for applying self-supervised learning in material discovery. Code and data are available at: https://github.com/liubin06/DeepGlassNet

This work is accepted for publication in Acta Materialia

References in corpus (11)

• Subwavelength-thick Lenses with High Numerical Apertures and Large Efficiency Based on High Contrast Transmitarrays
• Biomimetic Omnidirectional Anti-reflective Glass via Direct Ultrafast Laser Nanostructuring
• Thermal expansion and the glass transition
• The Relationship Between Local Structure and Relaxation in Out-of-Equilibrium Glassy Systems
• Theories of Glass Formation and the Glass Transition
• Predicting orientation-dependent plastic susceptibility from static structure in amorphous solids via deep learning
• Predicting and interpreting oxide glass properties by machine learning using large datasets
• Multiple reentrant glass transitions in confined hard-sphere glasses
• Convolutional neural networks enable high-fidelity prediction of path-dependent diffusion barrier spectra in multi-principal element alloys
• Ionic Self-Diffusion and the Glass Transition Anomaly in Aluminosilicates
• Predicting the location of shear band initiation in a metallic glass