Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Machine Learning technique for isotopic determination of radioisotopes using HPGe γ-ray spectra

Journal Article · · Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment

γ-ray spectroscopy is a quantitative, non-destructive technique that may be utilized for the identification and quantitative isotopic estimation of radionuclides. Traditional methods of isotopic determination have various challenges that contribute to statistical and systematic uncertainties in the estimated isotopics. Furthermore, these methods typically require numerous pre-processing steps, and have only been rigorously tested in laboratory settings with limited shielding. Here, in this work, we examine the application of a number of machine learning based regression algorithms as alternatives to conventional approaches for analyzing γ-ray spectroscopy data in the Emergency Response arena. This approach not only eliminates many steps in the analysis procedure, and therefore offers potential to reduce this source of systematic uncertainty, but is also shown to offer comparable performance to conventional approaches in the Emergency Response Application.

Research Organization:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA), Office of Defense Nuclear Nonproliferation
Grant/Contract Number:
89233218CNA000001
OSTI ID:
1992274
Report Number(s):
LA-UR-23-20010
Journal Information:
Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment, Journal Name: Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment Vol. 1054; ISSN 0168-9002
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (42)

Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position journal April 1980
A random forest guided tour journal April 2016
Connectionist learning procedures journal September 1989
Application of neural network techniques in gamma spectroscopy
  • Olmos, P.; Diaz, J. C.; Perez, J. M.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 312, Issue 1-2 https://doi.org/10.1016/0168-9002(92)90148-W
journal February 1992
Applicability and limits of the MGAU code for the determination of the enrichment of uranium samples
  • Abousahl, S.; Michiels, A.; Bickel, M.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 368, Issue 2 https://doi.org/10.1016/0168-9002(95)00663-X
journal January 1996
Application of neural networks for the analysis of gamma-ray spectra measured with a Ge spectrometer
  • Yoshida, Eiji; Shizuma, Kiyoshi; Endo, Satoru
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 484, Issue 1-3 https://doi.org/10.1016/S0168-9002(01)01962-3
journal May 2002
Statistical modelling of neural networks in γ-spectrometry
  • Vigneron, V.; Morel, J.; Lépy, M. C.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 369, Issue 2-3 https://doi.org/10.1016/S0168-9002(96)80068-4
journal February 1996
Background elimination methods for multidimensional coincidence γ-ray spectra
  • Morháč, Miroslav; Kliman, Ján; Matoušek, Vladislav
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 401, Issue 1 https://doi.org/10.1016/S0168-9002(97)01023-1
journal December 1997
Efficient one- and two-dimensional gold deconvolution and its application to γ-ray spectra decomposition
  • Morháč, Miroslav; Kliman, Ján; Matoušek, Vladislav
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 401, Issue 2-3 https://doi.org/10.1016/S0168-9002(97)01058-9
journal December 1997
Application of neural networks to quantitative spectrometry analysis
  • Pilato, V.; Tola, F.; Martinez, J. M.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 422, Issue 1-3 https://doi.org/10.1016/S0168-9002(98)01110-3
journal February 1999
Identification of peaks in multidimensional coincidence γ-ray spectra
  • Morháč, Miroslav; Kliman, Ján; Matoušek, Vladislav
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 443, Issue 1 https://doi.org/10.1016/S0168-9002(99)01005-0
journal March 2000
Low-resolution gamma-ray measurements of uranium enrichment journal October 1997
Results from the international evaluation exercise for uranium enrichment measurements journal March 2000
Rapid radionuclide identification algorithm based on the discrete cosine transform and BP neural network journal February 2018
Rapid nuclide identification algorithm based on convolutional neural network journal November 2019
A simple method for the absolute determination of uranium enrichment by high-resolution γ spectrometry journal May 2006
Application of support vector machine to rapid classification of uranium waste drums using low-resolution γ-ray spectra journal October 2015
Real-time radionuclide identification in γ-emitter mixtures based on spiking neural network journal March 2016
Determination of isotopes activity ratio using gamma ray spectroscopy based on neural network model journal June 2019
Study on the performance of different uranium isotopic codes used in nuclear safeguards activities journal April 2019
A tutorial on Bayesian nonparametric models journal February 2012
Deep learning in neural networks: An overview journal January 2015
Determination of the uranium enrichment with the NaIGEM code
  • Mortreau, Patricia; Berndt, Reinhard
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 530, Issue 3 https://doi.org/10.1016/j.nima.2004.04.229
journal September 2004
The use of artificial neural networks in PVT-based radiation portal monitors
  • Kangas, Lars J.; Keller, Paul E.; Siciliano, Edward R.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 587, Issue 2-3 https://doi.org/10.1016/j.nima.2008.01.065
journal March 2008
Nuclide identification algorithm based on K–L transform and neural networks
  • Chen, Liang; Wei, Yi-Xiang
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 598, Issue 2 https://doi.org/10.1016/j.nima.2008.09.035
journal January 2009
Applying Monte Carlo and artificial intelligence techniques for  235U mass prediction in samples with different enrichments
  • Shaban, Sameh E.; Hazzaa, M. H.; El-Tayebany, R. A.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 916 https://doi.org/10.1016/j.nima.2018.10.008
journal February 2019
Identification of SNM based on low-resolution gamma-ray characteristics and neural network
  • Zhang, Changfan; Hu, Gen; Luo, Fei
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 927 https://doi.org/10.1016/j.nima.2019.02.023
journal May 2019
Isotopic composition analysis and age dating of uranium samples by high resolution gamma ray spectrometry journal September 2016
Status of research and development of learning-based approaches in nuclear science and engineering: A review journal April 2020
Deep learning journal May 2015
Use of artificial neural networks in measuring characteristics of shielded plutonium for arms control journal January 2012
Airborne radiation mapping: overview and application of current and future aerial systems journal November 2016
Bayesian classification with Gaussian processes journal January 1998
Development of Neural Network Model With Explainable AI for Measuring Uranium Enrichment journal November 2021
Application Analysis of Radial Basis Function Neural Network Algorithm of Genetic Algorithm for Environmental Restoration and Treatment Effect Evaluation of Decommissioned Uranium Tailings Ponds journal November 2021
Subcritical Measurements of a Plutonium Sphere Reflected by Polyethylene and Acrylic journal March 2009
Measurements of UF 6 Cylinders with Portable Instruments journal February 1974
Determination of uranium and thorium concentrations in thorium ore sample using artificial neural network and comparison with net area peak method journal May 2018
Discriminatory Analysis. Nonparametric Discrimination: Consistency Properties journal December 1989
Gradient boosting machines, a tutorial journal January 2013
Neural Network Approaches for Mobile Spectroscopic Gamma-Ray Source Detection journal May 2021
Environmental Radiation Monitoring and External Dose Estimation in Aomori Prefecture after the Fukushima Daiichi Nuclear Power Plant Accident journal January 2016

Similar Records

Determination of γ-ray branching ratios for ⁹⁵Zr and ¹⁴⁷Nd
Technical Report · Mon Jun 08 00:00:00 EDT 2020 · OSTI ID:1633525

Detector-Response Correction of Two-Dimensional γ -Ray Spectra from Neutron Capture
Journal Article · Thu May 28 00:00:00 EDT 2015 · EPJ Web of Conferences · OSTI ID:1208914

New approach to precisely measure γ-ray intensities for long-lived fission products, with results for the decay of 95Zr
Journal Article · Thu Mar 18 00:00:00 EDT 2021 · Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment · OSTI ID:1778018