Application of Artificial Neural Networks to Elemental Assay Data for Nuclear Forensics Analysis
Date of Award
Master of Science in Nuclear Engineering
Department of Engineering Physics
Abigail Bickley, PhD
There is a need to quickly and accurately determine the likely physical origins of a collected sample for nuclear treaty verification purposes. The objective of this research is to prove there is a means to relate different samples (Q-values) to one another using a 'same versus not-same' artificial neural network called a Siamese network. This would provide the capability of comparing an unknown sample to a database of samples with known physical origins. Using moment transformations on current data has shown to increase the prediction capabilities of a Siamese network, and using a triplet loss function in connection with the Siamese network can further increase these capabilities
DTIC Accession Number
Seik, Jason G., "Application of Artificial Neural Networks to Elemental Assay Data for Nuclear Forensics Analysis" (2021). Theses and Dissertations. 5023.