Bridging Multimodal Microscopy for Advanced Characterization on Nuclear Fuel Using Machine Learning

Haarika Manda^1,2Liang Zhao³Yalei Tang³Rahul Reddy Kancharla³Peng Xu³Tiankai Yao³Fei Xu^3*

• ¹Idaho National Laboratory, Idaho Falls, United States
• ²University of California Santa Barbara, Santa Barbara, United States
• ³Idaho National Laboratory (DOE), Idaho Falls, United States

Uranium dioxide (UO2), widely used as driver fuel in light water reactors, experiences microstructure and property change by nuclear fission reactions. This paper bridges the characterization of fresh UO2 fuel at different length scales, serving as a baseline for future post irradiation examination of irradiated UO2 fuel. To characterize the microstructural change of nuclear fuel, modern approaches cover a wide range of length scales through different characterization techniques, such as mm scale for Synchrotron-based X-ray computed tomography and microscale for focused ion beam (FIB) and scanning electron microscopy (SEM). It is challenging to bridge the data and knowledge of the same sample in different length scales. This paper proposed a deep learning framework leveraging transfer learning to detect microstructural defects, trained from a sparse FIB, SEM, and SXCT images. The proposed model achieved superior performance in defect segmentation on multiscale microscopic data compared to four of the latest deep learning models.