Generative Adversarial Networks and Mixture Density Networks-Based Inverse Modeling for Microstructural Materials Design

Abstract

There are two broad modeling paradigms in scientific applications: forward and inverse. While forward modeling estimates the observations based on known causes, inverse modeling attempts to infer the causes given the observations. Inverse problems are usually more critical as well as difficult in scientific applications as they seek to explore the causes that cannot be directly observed. Inverse problems are used extensively in various scientific fields, such as geophysics, health care and materials science. Exploring the relationships from properties to microstructures is one of the inverse problems in material science. It is challenging to solve the microstructure discovery inverse problem, because it usually needs to learn a one-to-many nonlinear mapping. Given a target property, there are multiple different microstructures that exhibit the target property, and their discovery also requires significant computing time. Further, microstructure discovery becomes even more difficult because the dimension of properties (input) is much lower than that of microstructures (output). In this work, we propose a framework consisting of generative adversarial networks and mixture density networks for inverse modeling of structure–property linkages in materials, i.e., microstructure discovery for a given property. The results demonstrate that compared to baseline methods, the proposed framework can overcome the above-mentioned challenges and discover multiple promising solutions in an efficient manner.

Artificial Intelligence in Predicting Mechanical Properties of Composite Materials

“…The proposed models were able to generate microstructures closely resembling the original microstructure dataset in terms of Kernel inception distance, Frechet inception distance, inception scores, and morphometric parameters. Mao et al [174] combined GANs and mixture density networks (MDN) to perform inverse modeling of the low-dimensional design representations of the microstructure images.…”

Applications of generative adversarial networks in materials science

“…The applications of machine learning to materials science, boosted by continuous advances of algorithms, as well as computing resource and size of material data repository, have led to the fourth paradigm of data‐driven materials discovery. The approaches can be categorized into two main types, “forward” and “inverse” [3–7] . The former focuses on the prediction of target property for unknown materials and selection of candidates guided by the predictions [8] .…”