Toward Learning Latent-Variable Representations of Microstructures by Optimizing in Spatial Statistics Space
Keywords: spatial statistics, autoencoder, material science
TL;DR: we train a VAE to obtain a low-dimensional latent representation of microstructures by minimizing the loss in spatial statistics space
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 microstructure.
In this work, we train Variational Autoencoders (VAE) ti 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.
Submission Number: 243
Loading