Bayesian SegNet for Semantic Segmentation with Improved Interpretation of Microstructural Evolution During Irradiation of Materials
This work addresses the need for improved predictions of tritium-producing burnable absorber rod performance in materials science, though it is incremental as it applies existing neural network methods to a new dataset with modifications.
The study tackled the problem of predicting tritium diffusion, retention, and release in irradiated LiAlO2 pellets by training Deep Convolutional Neural Networks to segment microstructural images into defect, grain, and boundary classes, achieving high performance metrics similar to expert-labeled segmentations.
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.