A Deep Adversarial Learning Methodology for Designing Microstructural Material Systems

Abstract

In Computational Materials Design (CMD), it is well recognized that identifying key microstructure characteristics is crucial for determining material design variables. However, existing microstructure characterization and reconstruction (MCR) techniques have limitations to be applied for materials design. Some MCR approaches are not applicable for material microstructural design because no parameters are available to serve as design variables, while others introduce significant information loss in either microstructure representation and/or dimensionality reduction. In this work, we present a deep adversarial learning methodology that overcomes the limitations of existing MCR techniques. In the proposed methodology, generative adversarial networks (GAN) are trained to learn the mapping between latent variables and microstructures. Thereafter, the low-dimensional latent variables serve as design variables, and a Bayesian optimization framework is applied to obtain microstructures with desired material property. Due to the special design of the network architecture, the proposed methodology is able to identify the latent (design) variables with desired dimensionality, as well as capturing complex material microstructural characteristics. The validity of the proposed methodology is tested numerically on a synthetic microstructure dataset and its effectiveness for materials design is evaluated through a case study of optimizing optical performance for energy absorption. Additional features, such as scalability and transferability, are also demonstrated in this work. In essence, the proposed methodology provides an end-to-end solution for microstructural design, in which GAN reduces information loss and preserves more microstructural characteristics, and the GP-Hedge optimization improves the efficiency of design exploration.

Recent advances and applications of machine learning in solid-state materials science

“…GANs have found great success in image processing 205,206 and have recently been introduced to other fields, such as astronomy, 207 particle physics, 208 genetics, 209 and also very recently to materials science. 29,210,211 More information about these algorithms can be found in the references provided or in refs. 1,[212][213][214][215][216] .…”

“…Lastly, we discuss two works that introduced modern neural network architectures to crystal structure prediction and generation. Both methods have also been used recently for microstructures by Li et al 210,282 Ryan et al 28 applied VAEs (see section "Basic principles of machine learning-Algorithms") to crystal structure prediction. The 42-layer VAEs develop a more efficient representation for the input (see section "Basic principles of machine learning-Features").…”

Machine learning and artificial neural network accelerated computational discoveries in materials science

“…GAN has the capability to generate realistic examples across different domains other than the mainstream AI fields. The GAN algorithm has been explored in several pioneer works in computational materials studies …”

Pores for thought: generative adversarial networks for stochastic reconstruction of 3D multi-phase electrode microstructures with periodic boundaries

“…The authors implement a type of generative model called Generative Adversarial Networks (GANs) 40 to reconstruct the three-dimensional microstructure of synthetic and natural granular microstructures. Li et al 41 extended this work to enable the generation of optimised sandstones, again using GANs. Compared to other common microstructure generation techniques, GANs are able to provide fast sampling of highdimensional and intractable density functions without the need for an a priori model of the probability distribution function to be specified 39 .…”