|About this Abstract
||MS&T21: Materials Science & Technology
||Ceramics and Glasses Modeling by Simulations and Machine Learning
||P1-3: Molecular Dynamic Characteristic Temperatures for Predicting Metallic Glass Forming Ability
||Lane Enrique Schultz, Dane Morgan, Izabela Szlufarska, Benjamin Afflerbach
|On-Site Speaker (Planned)
||Lane Enrique Schultz
We explore the use of characteristics temperatures derived from molecular dynamics to predict aspects of metallic Glass Forming Ability (GFA). We use temperatures derived from cooling curves of self-diffusion, viscosity, and energy as features for machine learning models of GFA. The GFA of alloys was quantified by melt-spinning or suction casting amorphization behavior, with alloys that showed crystalline phases after synthesis classified as Poor GFA and those with pure amorphous phases as Good GFA. This binary GFA classification was then modeled using decision tree-based methods and were assessed with nested-cross validation. The maximum F1 score for the precision-recall with Good Glass Forming Ability as the positive class was 0.82 ± 0.01 for the best model type. Although the predictive ability of the models developed here are modest, this work demonstrates clearly that one can use molecular dynamics simulations and machine learning to predict metal glass forming ability.