A Transfer Learning Approach for Microstructure Reconstruction and Structure-property Predictions

TL;DR

This paper introduces a transfer learning method using deep convolutional networks for microstructure reconstruction and property prediction, offering a versatile, off-the-shelf solution applicable across various material systems to accelerate materials discovery.

Contribution

The paper presents a novel transfer learning framework that generalizes microstructure reconstruction and structure-property prediction across diverse materials, reducing the need for system-specific tuning.

Findings

Successfully reconstructed diverse microstructures with varying complexity

Demonstrated accurate structure-property predictions across multiple materials

Provided an off-the-shelf approach reducing modeling effort

Abstract

Stochastic microstructure reconstruction has become an indispensable part of computational materials science, but ongoing developments are specific to particular material systems. In this paper, we address this generality problem by presenting a transfer learning-based approach for microstructure reconstruction and structure-property predictions that is applicable to a wide range of material systems. The proposed approach incorporates an encoder-decoder process and feature-matching optimization using a deep convolutional network. For microstructure reconstruction, model pruning is implemented in order to study the correlation between the microstructural features and hierarchical layers within the deep convolutional network. Knowledge obtained in model pruning is then leveraged in the development of a structure-property predictive model to determine the network architecture and initialization conditions. The generality of the approach is demonstrated numerically for a wide range of material microstructures with geometrical characteristics of varying complexity. Unlike previous approaches that only apply to specific material systems or require a significant amount of prior knowledge in model selection and hyper-parameter tuning, the present approach provides an off-the-shelf solution to handle complex microstructures, and has the potential of expediting the discovery of new materials.