Predicting the Young's Modulus of Silicate Glasses using High-Throughput Molecular Dynamics Simulations and Machine Learning
K Yang and XY Xu and B Yang and B Cook and H Ramos and NMA Krishnan and MM Smedskjaer and C Hoover and M Bauchy, SCIENTIFIC REPORTS, 9, 8739 (2019).
The application of machine learning to predict materials' properties usually requires a large number of consistent data for training. However, experimental datasets of high quality are not always available or self-consistent. Here, as an alternative route, we combine machine learning with high-throughput molecular dynamics simulations to predict theYoung's modulus of silicate glasses. We demonstrate that this combined approach offers good and reliable predictions over the entire compositional domain. By comparing the performances of select machine learning algorithms, we discuss the nature of the balance between accuracy, simplicity, and interpretability in machine learning.
Return to Publications page