Toward Learning Latent-Variable Representations of Microstructures by Optimizing in Spatial Statistics Space

TL;DR

This paper proposes a method using Variational Autoencoders to generate microstructure textures that preserve spatial statistical properties, aiming for low-dimensional representations useful in materials design.

Contribution

It introduces a novel training approach that minimizes spatial statistics distance in the latent space, enhancing microstructure representation without exact image reconstruction.

Findings

VAE can preserve spatial statistics in texture reconstructions

Method demonstrates potential for low-dimensional microstructure modeling

Future work will apply this to actual material microstructures

Abstract

In Materials Science, material development involves evaluating and optimizing the internal structures of the material, generically referred to as microstructures. Microstructures structure is stochastic, analogously to image textures. A particular microstructure can be well characterized by its spatial statistics, analogously to image texture being characterized by the response to a Fourier-like filter bank. Material design would benefit from low-dimensional representation of microstructures Paulson et al. (2017). In this work, we train a Variational Autoencoders (VAE) to produce reconstructions of textures that preserve the spatial statistics of the original texture, while not necessarily reconstructing the same image in data space. We accomplish this by adding a differentiable term to the cost function in order to minimize the distance between the original and the reconstruction in spatial statistics space. Our experiments indicate that it is possible to train a VAE that minimizes the distance in spatial statistics space between the original and the reconstruction of synthetic images. In future work, we will apply the same techniques to microstructures, with the goal of obtaining low-dimensional representations of material microstructures.