Efficient Surrogate Models for Materials Science Simulations: Machine Learning-based Prediction of Microstructure Properties

TL;DR

This paper develops and compares six machine learning surrogate models to predict microstructure properties in materials science, demonstrating their accuracy, robustness, and the influence of domain knowledge on performance.

Contribution

The study introduces and evaluates multiple machine learning surrogate models for materials microstructure prediction, highlighting the effects of feature engineering and data quality.

Findings

Machine learning models achieve high accuracy in predicting microstructure evolution.

Including domain-specific features improves model robustness and performance.

Model performance varies with data quality and quantity, guiding future data collection.

Abstract

Determining, understanding, and predicting the so-called structure-property relation is an important task in many scientific disciplines, such as chemistry, biology, meteorology, physics, engineering, and materials science. Structure refers to the spatial distribution of, e.g., substances, material, or matter in general, while property is a resulting characteristic that usually depends in a non-trivial way on spatial details of the structure. Traditionally, forward simulations models have been used for such tasks. Recently, several machine learning algorithms have been applied in these scientific fields to enhance and accelerate simulation models or as surrogate models. In this work, we develop and investigate the applications of six machine learning techniques based on two different datasets from the domain of materials science: data from a two-dimensional Ising model for predicting the formation of magnetic domains and data representing the evolution of dual-phase microstructures from the Cahn-Hilliard model. We analyze the accuracy and robustness of all models and elucidate the reasons for the differences in their performances. The impact of including domain knowledge through tailored features is studied, and general recommendations based on the availability and quality of training data are derived from this.