Abstract
The detection of missing radioactive material is an important capability for safeguards measurements. Gamma ray signatures provide sample information, but interpretation is complicated by measurement environments. To determine if machine learning is a viable analysis option, three algorithms are applied to gamma ray detection data to assess their success at identifying missing sources. Preliminary results demonstrate that these algorithms can predict the number and location of missing sources on simple models of spent fuel assemblies. In addition to simulated experiments, a study to investigate if the algorithms can be trained with simulated data and tested on measured data is presented.
Similar content being viewed by others
References
International Atomic Energy Agency (2019) Establishing a system for control of nuclear material for nuclear security purposes at a facility during use, storage and movement. IAEA
International Atomic Energy Agency (2015) Use of nuclear material accounting and control for nuclear security purposes at facilities. IAEA
Sarnoski S, Fast J, Fulsom B et al (2017) Measurement of the 235 U induced fission gamma-ray spectrum as an active non-destructive assay of fresh nuclear fuel. In: Institute of Nuclear Materials Management: annual meeting proceedings. Institute of Nuclear Materials Management, pp 1–10
Nawaz S, Hussain M, Watson S, et al (2013) An underwater robotic network for monitoring nuclear waste storage pools. In: Lecture notes of the institute for computer sciences, social-informatics and telecommunications engineering
International Atomic Energy Agency (2011) Safegaurds techniques and equipment, 2011 edition. IAEA
International Atomic Energy Agency Department of Safeguards (2018) Research and development plan: enhancing capabilities for nuclear verification. IAEA
Carchon R, Moeslinger M, Bourva L et al (2007) Gamma radiation detectors for safeguards applications. Nucl Instrum Methods Phys Res Sect A Accel Spectrom Detect Assoc Equip 579:380–383. https://doi.org/10.1016/j.nima.2007.04.086
Chichester DL, Seabury EH (2009) Addressing different active neutron interrogation signatures from fissionable material. In: IEEE nuclear science symposium, conference record, pp 956–960. https://doi.org/10.1109/NSSMIC.2009.5402466
Shoman N, Cipiti BB (2018) Unsupervised machine learning for nuclear safeguards. In: Institute of Nuclear Materials Management: annual meeting proceedings
Goorley T, James M, Booth T et al (2012) Initial MCNP6 release overview. Nucl Technol 180:298–315. https://doi.org/10.13182/NT11-135
Lamarsh J, Baratta A (2001) Introduction to nuclear engineering, 3rd edn. Prentice Hall, Upper Saddle River
Vaccaro S, Tobin SJ, Favalli A et al (2016) PWR and BWR spent fuel assembly gamma spectra measurements. Nucl Instrum Methods Phys Res Sect A Accel Spectrom Detect Assoc Equip. https://doi.org/10.1016/j.nima.2016.07.032
Favalli A, Vo D, Grogan B et al (2016) Determining initial enrichment, burnup, and cooling time of pressurized-water-reactor spent fuel assemblies by analyzing passive gamma spectra measured at the Clab interim-fuel storage facility in Sweden. Nucl Instrum Methods Phys Res Sect A Accel Spectrom Detect Assoc Equip. https://doi.org/10.1016/j.nima.2016.02.072
Pedregosa F, Gael V, Gramfort A et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825–2830. https://doi.org/10.1007/s13398-014-0173-7.2
Goldberger J, Roweis S, Hinton G, Salakhutdinov R (2005) Neighbourhood components analysis. Adv Neural Inf Process Syst 17:513–520. https://doi.org/10.1109/TCSVT.2013.2242640
Breiman L (2001) Random forests. Mach Learn 45:5–32. https://doi.org/10.1017/CBO9781107415324.004
Quinlan JR (1986) Induction of decision trees. Mach Learn 1:81–106. https://doi.org/10.1007/bf00116251
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297. https://doi.org/10.1007/s40031-014-0099-7
Shi R, Tuo X, Zheng H et al (2018) Step-approximation SNIP background-elimination algorithm for HPGe gamma spectra. Nucl Instrum Methods Phys Res Sect A Accel Spectrom Detect Assoc Equip 885:60–66. https://doi.org/10.1016/j.nima.2017.12.064
Acknowledgements
This work was supported in part by the U.S. Nuclear Regulatory Commission’s Nuclear Education Program Fellowship Grant Program.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Durbin, M., Lintereur, A. Implementation of machine learning algorithms for detecting missing radioactive material. J Radioanal Nucl Chem 324, 1455–1461 (2020). https://doi.org/10.1007/s10967-020-07188-4
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10967-020-07188-4