Hybrid machine learning/physics-based approach for predicting oxide glass-forming ability

Collin J. Wilkinson, Cory Trivelpiece, Rob Hust, Rebecca S. Welch, Steve A. Feller, John C. Mauro

Research output: Contribution to journalArticlepeer-review

6 Scopus citations


Predicting the liquid compositions that will vitrify at experimentally accessible quench rates remains one of the grand challenges in the field of condensed matter physics. This glass-forming ability can be quantified as the critical quench rate needed to suppress crystallization. Knowledge of this critical quench rate also informs which glass composition could be used for new applications. There have been several physical and empirical models presented in the literature to predict the critical quench rate/glass forming ability. These models range from those theoretically derived to those quantified only through experimental characterization. In this work, we instead propose a new method to calculate the critical quench rate using the recently developed toy landscape model combined with machine learning. The toy landscape model accesses the underlying physics that control the vitrification behavior by directly simulating the liquid thermodynamics and kinetics. The results are discussed in terms of industrial impact, physical insights, and how the glass science community can develop improved predictions of glass-forming ability.

Original languageEnglish (US)
Article number117432
JournalActa Materialia
StatePublished - Jan 1 2022

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Ceramics and Composites
  • Polymers and Plastics
  • Metals and Alloys


Dive into the research topics of 'Hybrid machine learning/physics-based approach for predicting oxide glass-forming ability'. Together they form a unique fingerprint.

Cite this