SNM Radiation Signature Classification Using Different Semi-Supervised Machine Learning Models

Stomps, Jordan R.; Wilson, Paul P. H.; Dayman, Kenneth J.; Willis, Michael J.; Ghawaly, James M.; Archer, Daniel E.

doi:10.3390/jne4030032

SNM Radiation Signature Classification Using Different Semi-Supervised Machine Learning Models

Journal Article · Tue Jul 04 00:00:00 EDT 2023 · Journal of Nuclear Engineering

DOI:https://doi.org/10.3390/jne4030032· OSTI ID:1988203

; ; ; ; ;

The timely detection of special nuclear material (SNM) transfers between nuclear facilities is an important monitoring objective in nuclear nonproliferation. Persistent monitoring enabled by successful detection and characterization of radiological material movements could greatly enhance the nuclear nonproliferation mission in a range of applications. Supervised machine learning can be used to signal detections when material is present if a model is trained on sufficient volumes of labeled measurements. However, the nuclear monitoring data needed to train robust machine learning models can be costly to label since radiation spectra may require strict scrutiny for characterization. Therefore, this work investigates the application of semi-supervised learning to utilize both labeled and unlabeled data. As a demonstration experiment, radiation measurements from sodium iodide (NaI) detectors are provided by the Multi-Informatics for Nuclear Operating Scenarios (MINOS) venture at Oak Ridge National Laboratory (ORNL) as sample data. Anomalous measurements are identified using a method of statistical hypothesis testing. After background estimation, an energy-dependent spectroscopic analysis is used to characterize an anomaly based on its radiation signatures. In the absence of ground-truth information, a labeling heuristic provides data necessary for training and testing machine learning models. Supervised logistic regression serves as a baseline to compare three semi-supervised machine learning models: co-training, label propagation, and a convolutional neural network (CNN). In each case, the semi-supervised models outperform logistic regression, suggesting that unlabeled data can be valuable when training and demonstrating value in semi-supervised nonproliferation implementations.

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA)

Grant/Contract Number:: NA0003921

OSTI ID:: 1988203

Alternate ID(s):: OSTI ID: 2203878
OSTI ID: 2234360

Journal Information:: Journal of Nuclear Engineering, Journal Name: Journal of Nuclear Engineering Journal Issue: 3 Vol. 4; ISSN 2673-4362

Publisher:: MDPI AGCopyright Statement

Country of Publication:: Switzerland

Language:: English

References (12)

A Probabilistic Theory of Pattern Recognition Devroye, Luc; Györfi, László; Lugosi, Gábor Stochastic Modelling and Applied Probability, Vol. 31 https://doi.org/10.1007/978-1-4612-0711-5	book	April 1996
Characterization of gamma-ray background outside of the High Flux Isotope Reactor Nicholson, Andrew D.; Archer, Daniel E.; Garishvili, Irakli Journal of Radioanalytical and Nuclear Chemistry, Vol. 318, Issue 1 https://doi.org/10.1007/s10967-018-6097-5	journal	August 2018
A survey on semi-supervised learning van Engelen, Jesper E.; Hoos, Holger H. Machine Learning, Vol. 109, Issue 2 https://doi.org/10.1007/s10994-019-05855-6	journal	November 2019
Semisupervised classification for fault diagnosis in nuclear power plants Ma, Jianping; Jiang, Jin Nuclear Engineering and Technology, Vol. 47, Issue 2 https://doi.org/10.1016/j.net.2014.12.005	journal	March 2015
Classification of NPPs transients using change of representation technique: A hybrid of unsupervised MSOM and supervised SVM Moshkbar-Bakhshayesh, Khalil; Mohtashami, Soroush Progress in Nuclear Energy, Vol. 117 https://doi.org/10.1016/j.pnucene.2019.103100	journal	November 2019
A semi-supervised method for the characterization of degradation of nuclear power plants steam generators Pinciroli, Luca; Baraldi, Piero; Shokry, Ahmed Progress in Nuclear Energy, Vol. 131 https://doi.org/10.1016/j.pnucene.2020.103580	journal	January 2021
Understanding Machine Learning Shalev-Shwartz, Shai; Ben-David, Shai https://doi.org/10.1017/CBO9781107298019	book	July 2014
A Novel Weakly-Supervised Approach for RGB-D-Based Nuclear Waste Object Detection Sun, Li; Zhao, Cheng; Yan, Zhi IEEE Sensors Journal, Vol. 19, Issue 9 https://doi.org/10.1109/JSEN.2018.2888815	journal	May 2019
Combining Supervised and Semi-Supervised Learning in the Design of a New Identifier for NPPs Transients Moshkbar-Bakhshayesh, Khalil; Ghofrani, Mohammad B. IEEE Transactions on Nuclear Science, Vol. 63, Issue 3 https://doi.org/10.1109/TNS.2016.2547866	journal	June 2016
Combining labeled and unlabeled data with co-training Blum, Avrim; Mitchell, Tom Proceedings of the eleventh annual conference on Computational learning theory - COLT' 98 https://doi.org/10.1145/279943.279962	conference	January 1998
Semisupervised Learning for Seismic Monitoring Applications Linville, Lisa; Anderson, Dylan; Michalenko, Joshua Seismological Research Letters, Vol. 92, Issue 1 https://doi.org/10.1785/0220200195	journal	October 2020
Semi-Supervised Learning Chapelle, Olivier; Schölkopf, Bernhard; Zien, Alexander https://doi.org/10.7551/mitpress/9780262033589.001.0001	book	September 2006

SNM Radiation Signature Classification Using Different Semi-Supervised Machine Learning Models

References (12)

Similar Records

Related Subjects

SNM Radiation Signature Classification Using Different Semi-Supervised Machine Learning Models

Citation Formats

References (12)

Similar Records

Related Subjects