This study presents a deep learning-based approach for the automated segmentation of corrosion damage in scanning electron microscopy (SEM) images. The proposed method enables rapid and accurate segmentation of corrosion features in these SEM images, making it highly suitable for real-time applications such as automated microscopy. Specifically, a dedicated corrosion segmentation database tailored for this task is constructed. The newly constructed dataset, alongside data from two public databases, are employed to jointly train a deep learning-based model modified with a texture refinement module. Compared to the same model without the texture refinement module, the refined model substantially enhances the efficacy and efficiency of corrosion segmentation. Furthermore, the methodology developed here is extendable to segmentation tasks for other materials with similar resolution, texture, and contrast characteristics, thereby paving the way for accelerated and automated analysis in corrosion science and beyond.

The use of nuclear energy inevitably generates nuclear waste as the byproduct of fission reactions. Depending on the initial composition of the fuel that goes into the reactor and the subsequent burn-up level, the chemistry of the resulting nuclear waste can vary substantially. This waste typically exhibits a broad spectrum of radioactivity and half-lives, making effective management one of the most critical challenges for global nuclear energy. This chapter provides a comprehensive overview of the origin and classification of nuclear waste and various strategies for its safe immobilization and disposal. The short- and long-term storage of waste with varying radioactivity is addressed. The significant technical and political complexities involving primarily long-term disposal are also discussed. To ensure the safe and permanent disposal of hazardous waste with extremely long half-lives, future efforts should focus on both technical innovation and public engagement.

This study presents a deep learning-based approach for the automated segmentation of corrosion damage in scanning electron microscopy (SEM) images. The proposed method enables rapid and accurate segmentation of corrosion features in these SEM images, making it highly suitable for real-time applications such as automated microscopy. Specifically, a dedicated corrosion segmentation database tailored for this task is constructed. The newly constructed dataset, alongside data from two public databases, are employed to jointly train a deep learning-based model modified with a texture refinement module. Compared to the same model without the texture refinement module, the refined model substantially enhances the efficacy and efficiency of corrosion segmentation. Furthermore, the methodology developed here is extendable to segmentation tasks for other materials with similar resolution, texture, and contrast characteristics, thereby paving the way for accelerated and automated analysis in corrosion science and beyond.