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

TL;DR

This paper investigates feature engineering methods for machine learning models to predict grain boundary properties from atomic structures, emphasizing the importance of structure representation, transformation, and interpretability.

Contribution

It systematically evaluates feature engineering steps for variable-sized atom clusters, improving prediction accuracy and interpretability of grain boundary properties.

Findings

Transforming variable-sized structures to fixed-length features enhances prediction accuracy.

Feature engineering choices significantly impact model interpretability.

A database of over 7000 grain boundaries supports comprehensive evaluation.

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.