Building Data-driven Models with Microstructural Images: Generalization and Interpretability
This work addresses the need for more robust and understandable data-driven models in materials science to improve process-structure-property predictions, but it appears incremental as it builds on existing CNN approaches.
The paper tackles the problem of using convolutional neural networks to classify microstructural images by focusing on generalization across datasets, feature efficiency, and interpretability, rather than just accuracy on a single dataset.
As data-driven methods rise in popularity in materials science applications, a key question is how these machine learning models can be used to understand microstructure. Given the importance of process-structure-property relations throughout materials science, it seems logical that models that can leverage microstructural data would be more capable of predicting property information. While there have been some recent attempts to use convolutional neural networks to understand microstructural images, these early studies have focused only on which featurizations yield the highest machine learning model accuracy for a single data set. This paper explores the use of convolutional neural networks for classifying microstructure with a more holistic set of objectives in mind: generalization between data sets, number of features required, and interpretability.