High bias machine learning for antineutrino-based safeguards for small reactors. (May 2022)

• Record Type: Journal Article
• Authors: Dunbrack, Matthew; Stewart, Christopher; Erickson, Anna
• Is Part Of: Annals of nuclear energy. Volume 169(2022)
• Publication Date: 2022-05
• Subjects: Antineutrino -- Safeguards -- Machine learning -- Small reactor; Nuclear energy -- Periodicals; Nuclear engineering -- Periodicals; 621.4805
• DOI: 10.1016/j.anucene.2021.108897
• Languages: English
• ISSNs: 0306-4549

Abstract

Highlights: Antineutrino source term generation through high-fidelity reactor modeling Antineutrino spectra processing through safeguards power quantification. Statistical limitations for near-zero small reactor safeguards power. Antineutrino spectra training dataset selection for machine learning model robustness. Abstract: The statistical methods used for antineutrino detection will need to be improved to effectively monitor the inventory of next-generation nuclear reactors. In this sensitivity study, we evaluate machine learning models compared to previously used statistical approaches to identify diversion scenarios in a simulated Advanced Fast Reactor (AFR)-100. A chi-square goodness-of-fit technique, which individually compares the simulated antineutrino yields to the expected antineutrino yield, resulted in precise but low diversion detection probability. Various support vector machine (SVM) models were applied with diverse training datasets to evaluate the robustness of the method towards unexpected or "unseen" diversion scenarios. Our results indicate that while the SVM models significantly improved the detection probability of near-field antineutrino-based safeguards, up to a probability of ~0.04, for the simulated small reactor, the detection system still needs improvements to reach the 0.2 detection limit established by the International Atomic Energy Agency.