Physics-aware Deep Generative Models for Creating Synthetic Microstructures

TL;DR

This paper introduces three deep generative models, including a physics-aware GAN, for fast and physically consistent synthesis of microstructure images in materials science.

Contribution

The paper presents novel generative models that explicitly incorporate physical invariances into microstructure synthesis, improving over traditional stochastic optimization methods.

Findings

Models can synthesize microstructures respecting physical invariances.

Latent space interpolation reveals meaningful microstructure variations.

Models demonstrate potential for physics-constrained microstructure design.

Abstract

A key problem in computational material science deals with understanding the effect of material distribution (i.e., microstructure) on material performance. The challenge is to synthesize microstructures, given a finite number of microstructure images, and/or some physical invariances that the microstructure exhibits. Conventional approaches are based on stochastic optimization and are computationally intensive. We introduce three generative models for the fast synthesis of binary microstructure images. The first model is a WGAN model that uses a finite number of training images to synthesize new microstructures that weakly satisfy the physical invariances respected by the original data. The second model explicitly enforces known physical invariances by replacing the traditional discriminator in a GAN with an invariance checker. Our third model combines the first two models to reconstruct microstructures that respect both explicit physics invariances as well as implicit constraints learned from the image data. We illustrate these models by reconstructing two-phase microstructures that exhibit coarsening behavior. The trained models also exhibit interesting latent variable interpolation behavior, and the results indicate considerable promise for enforcing user-defined physics constraints during microstructure synthesis.