Bayesian SegNet for Semantic Segmentation with Improved Interpretation of Microstructural Evolution During Irradiation of Materials

TL;DR

This paper presents a Bayesian SegNet model for semantic segmentation of microstructural images of irradiated materials, enhancing interpretation of microstructural evolution and improving predictions related to tritium behavior.

Contribution

It introduces a Bayesian neural network approach with uncertainty quantification for microstructure segmentation, incorporating meta-data to improve sensitivity and interpretability.

Findings

Segmentation accuracy comparable to expert labels

Incorporation of meta-data improves model sensitivity

Uncertainty quantification aids microstructural analysis

Abstract

Understanding the relationship between the evolution of microstructures of irradiated LiAlO2 pellets and tritium diffusion, retention and release could improve predictions of tritium-producing burnable absorber rod performance. Given expert-labeled segmented images of irradiated and unirradiated pellets, we trained Deep Convolutional Neural Networks to segment images into defect, grain, and boundary classes. Qualitative microstructural information was calculated from these segmented images to facilitate the comparison of unirradiated and irradiated pellets. We tested modifications to improve the sensitivity of the model, including incorporating meta-data into the model and utilizing uncertainty quantification. The predicted segmentation was similar to the expert-labeled segmentation for most methods of microstructural qualification, including pixel proportion, defect area, and defect density. Overall, the high performance metrics for the best models for both irradiated and unirradiated images shows that utilizing neural network models is a viable alternative to expert-labeled images.