Abstract

Data-driven approaches have been recognized as a new paradigm for establishing and exploring process-morphology-property relationships. However, typical exploration methods deliver high-dimensional morphologies that pose the challenge of extracting the key features and patterns that could guide the processing and materials design. The high dimensionality also hampers the organization of the data and the associated data analytics. As a solution, the currently available approaches either take a simplified view of the morphology, e.g., focusing on pixels in the morphology images, or apply transformations that average out structural descriptors of morphologies. To address these shortcomings, we propose a new computationally efficient and configurable distance operator that takes an intermediate approach. Our main idea is to represent the morphology as a graph where graph connectivity reflects the relative arrangement of components (e.g., grains, droplets) in the morphology, and the label of the graph vertices captures the domain-specific information of each characteristic domain. Next, given the graph abstraction, the distance between morphologies is computed using vectorized graph-based representation. Because both morphology graph structure and associated signature functions have clear interpretations, our distance measure can be easily tailored to specific applications. Our results demonstrate the superior performance of the proposed approach on data from simulation and synthetic data, including in real-world applications like morphologies clustering.

BibTex

@article{Desai2024,
title = {COMODO: Configurable morphology distance operator},
journal = {Computational Materials Science},
volume = {244},
pages = {113208},
year = {2024},
issn = {0927-0256},
doi = {https://doi.org/10.1016/j.commatsci.2024.113208},
url = {https://www.sciencedirect.com/science/article/pii/S0927025624004294},
author = {Parth Desai and Namit Juneja and Varun Chandola and Jaroslaw Zola and Olga Wodo},
keywords = {Morphology informatics, Distance operator, Graph, Configurable signature functions, Clustering},
}