Predicting Young's Modulus of Glasses with Sparse Datasets using Machine Learning

Abstract

Machine learning (ML) methods are becoming popular tools for the prediction and design of novel materials. In particular, neural network (NN) is a promising ML method, which can be used to identify hidden trends in the data. However, these methods rely on large datasets and often exhibit overfitting when used with sparse dataset. Further, assessing the uncertainty in predictions for a new dataset or an extrapolation of the present dataset is challenging. Herein, using Gaussian process regression (GPR), we predict Young's modulus for silicate glasses having sparse dataset. We show that GPR significantly outperforms NN for sparse dataset, while ensuring no overfitting. Further, thanks to the nonparametric nature, GPR provides quantitative bounds for the reliability of predictions while extrapolating. Overall, GPR presents an advanced ML methodology for accelerating the development of novel functional materials such as glasses.

17 pages, 5 figures

References in corpus (6)

• Achieving DFT accuracy with a machine-learning interatomic potential: thermomechanics and defects in bcc ferromagnetic iron
• A New Transferable Interatomic Potential for Molecular Dynamics Simulations of Borosilicate Glasses
• Structural, vibrational, and elastic properties of a calcium aluminosilicate glass from molecular dynamics simulations: the role of the potential
• Accurate Force Field for Molybdenum by Machine Learning Large Materials Data
• Predicting the dissolution kinetics of silicate glasses using machine learning
• Prediction of Silicate Glasses' Stiffness by High-Throughput Molecular Dynamics Simulations and Machine Learning

Cited by in corpus (11)

• ViscNet: Neural network for predicting the fragility index and the temperature-dependency of viscosity
• Designing optical glasses by machine learning coupled with a genetic algorithm
• Predicting and interpreting oxide glass properties by machine learning using large datasets
• GlassNet: a multitask deep neural network for predicting many glass properties
• Predicting Oxide Glass Properties with Low Complexity Neural Network and Physical and Chemical Descriptors
• Predicting densities and elastic moduli of SiO2-based glasses by machine learning
• Revealing the Compositional Control of Electrical, Mechanical, Optical, and Physical Properties of Inorganic Glasses
• Deep Learning Aided Rational Design of Oxide Glasses
• Unveiling the Glass Veil: Elucidating the Optical Properties in Glasses with Interpretable Machine Learning
• Learning from Sparse Datasets: Predicting Concrete's Strength by Machine Learning
• Scalable Gaussian Processes for Predicting the Properties of Inorganic Glasses with Large Datasets