Machine learning metallic glass critical cooling rates through elemental and molecular simulation based featurization

Abstract

We have developed a machine learning model for critical cooling rates for metallic glasses based on computational properties. We compare results for features derived from easy-to-compute functions of elemental properties to more complex physically motivated properties using ab initio, machine-learning potentials, and empirical potential molecular dynamics methods. The established approach enables property acquisition across a diverse range of alloys. Analysis of various features for 34 alloys from 20 chemical systems shows that the best model for critical cooling rates was learned from one elemental property-based feature and three simulated features. The elemental property-based feature is an ideal entropy value based on alloy stoichiometry. The simulated features were acquired from estimates of energies above the convex hull, changes in heat capacity, and the fraction of icosahedra-like Voronoi polyhedra. Models were assessed through a demanding cross validation test based on repeatedly leaving out full chemical systems as test sets and had an $R^2$ of 0.78 and a mean average error of 0.76 in units of $[lo{g}_{10}(K/s)]$. We demonstrate with Shapley additive explanation analysis that the most impactful features have physically reasonable influence on model predictions. The established methodology can be applied to other high-throughput studies of material properties of diverse compositions.

References in corpus (14)

• Scikit-learn: Machine Learning in Python
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• A Universal Graph Deep Learning Interatomic Potential for the Periodic Table
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• Strengthening in multi-principal element alloys with local-chemical-order roughened dislocation pathways
• Extracting Accurate Materials Data from Research Papers with Conversational Language Models and Prompt Engineering
• Correlation between Fragility and the Arrhenius Crossover Phenomenon in Metallic, Molecular, and Network Liquids
• The Materials Simulation Toolkit for Machine Learning (MAST-ML): an automated open source toolkit to accelerate data-driven materials research
• On the role of Sm in solidification of Al-Sm metallic glasses
• Flexible, Model-Agnostic Method for Materials Data Extraction from Text Using General Purpose Language Models
• Machine Learning Prediction of Critical Cooling Rate for Metallic Glasses From Expanded Datasets and Elemental Features
• Dynamical, structural and chemical heterogeneities in a binary metallic glass-forming liquid
• Molecular simulation-derived features for machine learning predictions of metal glass forming ability
• Microalloying effect in ternary Al-Sm-X (X=Ag, Au, Cu) metallic glasses studied by ab initio molecular dynamics