Describe, Transform, Machine Learning: Feature Engineering for Grain Boundaries and Other Variable-Sized Atom Clusters

Abstract

Obtaining microscopic structure-property relationships for grain boundaries are challenging because of the complex atomic structures that underlie their behavior. This has led to recent efforts to obtain these relationships with machine learning, but representing a grain boundary structure in a manner suitable for machine learning is not a trivial task. There are three key steps common to property prediction in grain boundaries and other variable-sized atom clustered structures. These are: (1) describe the atomic structure as a feature matrix, (2) transform the variable-sized feature matrices of different structures to a fixed length common to all structures, and (3) apply machine learning to predict properties from the transformed feature matrices. We examine these feature engineering steps to understand how they impact the accuracy of grain boundary energy predictions. A database of over 7000 grain boundaries serves to evaluate the different feature engineering combinations. We also examine how these combination of engineered features provide interpretability, or the ability to extract insightful physics from the obtained structure-property relationships.

18 pages, 8 figures

References in corpus (20)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• On representing chemical environments
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions
• Physics-inspired structural representations for molecules and materials
• Structural phase transformations in metallic grain boundaries
• Entropy based fingerprint for local crystalline order
• Predicting phase behavior of grain boundaries with evolutionary search and machine learning
• Metrics for measuring distances in configuration spaces
• Chemomechanical Origin of Hydrogen Trapping at Grain Boundaries in FCC Metals
• A fingerprint based metric for measuring similarities of crystalline structures
• Discovering the Building Blocks of Atomic Systems using Machine Learning
• Machine learning determination of atomic dynamics at grain boundaries
• Prediction of grain boundary structure and energy by machine learning
• Examination of computed aluminum grain boundary structures and interface energies that span the 5D space of crystallographic character
• Application of machine learning potentials to predict grain boundary properties in fcc elemental metals
• Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting failure to machine learn four-body interactions
• Five Degree-of-Freedom Property Interpolation of Arbitrary Grain Boundaries via Voronoi Fundamental Zone Octonion Framework
• Maximum volume simplex method for automatic selection and classification of atomic environments and environment descriptor compression