Abstract
Clandestine nuclear testing can be detected at a standoff distance using radioxenon beta-gamma analysis. International treaty monitoring organizations depend, in part, upon the activity ratios of various radioxenon types to determine if collected samples are the result of a weapons test or a peaceful purpose such as energy or medical isotope production. However, the currently deployed radioxenon analysis method makes assumptions about the location of energy coincidence counts on a beta-gamma spectrum, such that this method is particularly sensitive to measurement or calibration errors. We propose a machine learning method instead. By exposing a computer algorithm to many representative examples, the resultant computer model detects patterns in the data without making additional assumptions. Both a classification model predicting which radioisotopes are present and a regression model predicting concentrations of the radioisotopes are tested. This work is a proof-of-concept that machine learning can be effectively applied to radioxenon beta-gamma analysis.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Nuclear test ban treaty. JFK Library. https://www.jfklibrary.org/learn/about-jfk/jfk-in-history/nuclear-test-bantreaty
Maceira M, Blom PS, MacCarthy JK, Marcillo OE, Euler GG, Begnaud ML, Ford SR, Pasyanos ME, Orris GJ, Foxe MP, et al. (2017) Trends in nuclear explosion monitoring research & development-a physics perspective. Technical report, Los Alamos National Lab.(LANL), Los Alamos, NM (United States)
Bowyer TW , Abel KH, Hensley WK (1996)Automatic radioxenon analyzer for ctbt monitoring. Technical report, Pacific Northwest National Lab., Richland, WA (United States)
Bowyer T, Abel K, Hubbard C, Panisko M, Reeder P, Thompson R, Warner R (1999) Field testing of collection and measurement of radioxenon for the comprehensive test ban treaty. J Radioanal Nuclear Chem 240(1):109–122
Bowyer TW, Schlosser C, Abel KH, Auer M, Hayes JC, Heimbigner TR, McIntyre JI, Panisko ME, Reeder PL, Satorius H et al (2002) Detection and analysis of xenon isotopes for the comprehensive nuclear-test-ban treaty international monitoring system. J Environ Radioact 59(2):139–151
Cooper MW, Auer M, Bowyer TW, Casey LA, Elmgren K, Ely JH, Foxe MP, Gheddou A, Gohla H, Hayes JC et al (2019) Radioxenon net count calculations revisited. J Radioanal Nuclear Chem 321(2):369–382
Cooper MW, McIntyre JI, Bowyer TW, Carman AJ, Hayes JC, Heimbigner TR, Hubbard CW, Lidey L, Litke KE, Morris SJ et al (2007) Redesigned \(\beta\)-\(\gamma\) radioxenon detector. Nuclear Instrum Methods Phys Res Sect A: Accel Spectrom Detect Assoc Equip 579(1):426–430
Cooper MW, Bowyer TW, Hayes JC, Heimbigner TR, Hubbard CW , McIntyre JI, Schrom BT (2008) Spectral analysis of radioxenon. Technical report, Pacific Northwest National Lab Richland WA
Lowrey JD, Biegalski SR, Osborne AG, Deinert MR (2013) Subsurface mass transport affects the radioxenon signatures that are used to identify clandestine nuclear tests. Geophys Res Lett 40(1):111–115
Kalinowski MB, Axelsson A, Bean M, Blanchard X, Bowyer TW, Brachet G , McIntyre JI , Pistner C , Raith M , Ringbom A, et al. (2005) Discrimination of nuclear explosions against civilian sources based on xenon isotopic activity ratios. Pure and Applied Geophysics, in press, 10
Chien C (2020) Physical and Theoretical Chemistry. Chem Libretexts. https://chem.libretexts.org/Bookshelves/Physical_and_Theoretical_Chemistry_Textbook_Maps
Biegalski SRF, Foltz Biegalski KM, Haas DA (2009) Sdat: analysis of 131m xe with 133 xe interference. J Radioanal Nuclear Chem 282(3):715
Cooper MW , Hayes JC, Schrom BT, McIntyre JI, Ely JH (2016) Minimum detectable concentration and concentration calculations. Technical report, Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Deshmukh N, Prinke A, Miller B, McIntyre J (2017) Comparison of new and existing algorithms for the analysis of 2d radioxenon beta gamma spectra. J Radioanal Nuclear Chem 311(3):1849–1857
Foltz Biegalski KM, Biegalski SR (2005) Deconvolution of three-dimensional beta-gamma coincidence spectra from xenon sampling and measurement units. J Radioanal Nuclear Chem 263(1):259–265
Foltz Biegalski K, Biegalski S, Haas D (2008) Performance evaluation of spectral deconvolution analysis tool (sdat) software used for nuclear explosion radionuclide measurements. J Radioanal Nuclear Chem 276(2):407–413
Biegalski S, Flory A, Haas D, Ely J, Cooper M (2013) Sdat implementation for the analysis of radioxenon \(\beta\)-\(\gamma\) coincidence spectra. J Radioanal Nuclear Chem 296(1):471–476
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V et al (2011) Scikit-learn: Machine learning in python. J Mach Learn Res 12:2825–2830
Maini V, Sabri S (2017) Machine Learning for Humans
Aurélien G (2017) Hands-on machine learning with Scikit-Learn and TensorFlow: concepts, tools, and techniques to build intelligent systems. OReilly Media, USA
McIntyre JI, Schrom BT, Cooper MW, Prinke AM, Suckow TJ, Ringbom A, Warren GA (2016) A program to generate simulated radioxenon beta-gamma data for concentration verification and validation and training exercises. J Radioanal Nuclear Chem 307(3):2381–2387
Singh D, Singh B (2019)Investigating the impact of data normalization on classification performance. Applied Soft Computing, 97(Part B):105524
Bishop CM (2006) Pattern recognition and machine learning. Springer, Berlin
Sammut C, Webb GI (eds) (2010) Leave-One-Out Cross-Validation, pp 600–601. Springer US, Boston, MA
Deng L (2012) The mnist database of handwritten digit images for machine learning research [best of the web]. IEEE Signal Process Magaz 29(6):141–142
Acknowledgements
We gratefully acknowledge funding by by the Air Force Technical Applications Center. We also thank members of the Pacific Northwest National Laboratory for their extensive help and encouragement in this study. In particular, we thank Matthew Cooper and Michael Mayer for their many very thoughtful discussions concerning radioxenon, the beta-gamma detectors used to measure the isomers of interest, and the algorithms used to analyze the detector data. We also thank Justin McIntyre for his help in obtaining the extensive simulated data set used in this study. This work would not have been possible without their efforts; these individuals are true experts in their field and we very much hope to work more extensively with them in the future.
Funding
This study was funded by the Air Force Technical Applications Center.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
None
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
Armstrong, J., Carpency, T., Scoville, J. et al. Machine learning for the analysis of 2D radioxenon beta gamma spectra. J Radioanal Nucl Chem 327, 857–867 (2021). https://doi.org/10.1007/s10967-020-07533-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10967-020-07533-7