Data-Driven Learning of 3-Point Correlation Functions as Microstructure Representations
This addresses the problem of explainable microstructure analysis for materials science, offering a more interpretable alternative to deep generative models, though it appears incremental by building on existing correlation function concepts.
The paper tackles the challenge of finding complete, concise, and explainable microstructure representations for disordered materials by proposing a method based on three-point correlation functions, showing that a concise subset can characterize various microstructures and compute material properties.
This paper considers the open challenge of identifying complete, concise, and explainable quantitative microstructure representations for disordered heterogeneous material systems. Completeness and conciseness have been achieved through existing data-driven methods, e.g., deep generative models, which, however, do not provide mathematically explainable latent representations. This study investigates representations composed of three-point correlation functions, which are a special type of spatial convolutions. We show that a variety of microstructures can be characterized by a concise subset of three-point correlations, and the identification of such subsets can be achieved by Bayesian optimization. Lastly, we show that the proposed representation can directly be used to compute material properties based on the effective medium theory.