Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

A counting-time optimization method for artificial neural network (ANN) based gamma-ray spectroscopy

  • Moonhyung Cho (Department of Nuclear & Quantum Engineering, Korea Advanced Institute of Science and Technology) ;
  • Jisung Hwang (Department of Nuclear & Quantum Engineering, Korea Advanced Institute of Science and Technology) ;
  • Sangho Lee (Department of Nuclear & Quantum Engineering, Korea Advanced Institute of Science and Technology) ;
  • Kilyoung Ko (Department of Nuclear & Quantum Engineering, Korea Advanced Institute of Science and Technology) ;
  • Wonku Kim (Department of Nuclear & Quantum Engineering, Korea Advanced Institute of Science and Technology) ;
  • Gyuseong Cho (Department of Nuclear & Quantum Engineering, Korea Advanced Institute of Science and Technology)
  • Received : 2023.09.17
  • Accepted : 2024.02.15
  • Published : 2024.07.25
Download PDF
⟨ Previous Next ⟩

Abstract

With advancements in machine learning technologies, artificial neural networks (ANNs) are being widely used to improve the performance of gamma-ray spectroscopy based on NaI(Tl) scintillation detectors. Typically, the performance of ANNs is evaluated using test datasets composed of actual spectra. However, the generation of such test datasets encompassing a wide range of actual spectra representing various scenarios often proves inefficient and time-consuming. Thus, instead of measuring actual spectra, we generated virtual spectra with diverse spectral features by sampling from categorical distribution functions derived from the base spectra of six radioactive isotopes: 54Mn, 57Co, 60Co, 134Cs, 137Cs, and 241Am. For practical applications, we determined the optimum counting time (OCT) as the point at which the change in the Kullback-Leibler divergence (ΔKLDV) values between the synthetic spectra used for training the ANN and the virtual spectra approaches zero. The accuracies of the actual spectra were significantly improved when measured up to their respective OCTs. The outcomes demonstrated that the proposed method can effectively determine the OCTs for gamma-ray spectroscopy based on ANNs without the need to measure actual spectra.

Keywords

References

  1. S. Anilkumar, K. Narayani, A.K. Verma, R. Singh, K.S. Pradeepkumar, Application of simulated standard spectra for the analysis of complex sample spectra from NaI (Tl) detectors, J. Radioanal. Nucl. Chem. 302 (2014) 1449-1454, https://doi.org/10.1007/s10967-014-3659-z. 
  2. J. Kim, K.T. Lim, J. Kim, C. jong Kim, B. Jeon, K. Park, G. Kim, H. Kim, G. Cho, Quantitative analysis of NaI(Tl) gamma-ray spectrometry using an artificial neural network, Nucl. Instruments Methods Phys. Res. Sect. A Accel. Spectrometers, Detect. Assoc. Equip. 944 (2019) 162549, https://doi.org/10.1016/j.nima.2019.162549. 
  3. T. Report, Use of Portable Gamma Detector Systems during Decommissioning, 2019. www.epri.com. 
  4. R. Zhao, N. Liu, Low-resolution gamma-ray spectrum analysis using comprehensive training set and deep ResNet architecture, Nucl. Instruments Methods Phys. Res. Sect. A Accel. Spectrometers, Detect. Assoc. Equip. 1050 (2023) 168135, https://doi.org/10.1016/j.nima.2023.168135. 
  5. M. Kamuda, J. Zhao, K. Huff, A comparison of machine learning methods for automated gamma-ray spectroscopy, Nucl. Instruments Methods Phys. Res. Sect. A Accel. Spectrometers, Detect. Assoc. Equip. 954 (2020), https://doi.org/10.1016/j.nima.2018.10.063. 
  6. M. Kamuda, C.J. Sullivan, An automated isotope identification and quantification algorithm for isotope mixtures in low-resolution gamma-ray spectra, Radiat. Phys. Chem. 155 (2019) 281-286, https://doi.org/10.1016/j.radphyschem.2018.06.017. 
  7. M. Kamuda, J. Stinnett, C.J. Sullivan, Automated isotope identification algorithm using artificial neural networks, IEEE Trans. Nucl. Sci. 64 (2017) 1858-1864, https://doi.org/10.1109/TNS.2017.2693152. 
  8. P. Olmos, J.C. Diaz, J.M. Perez, P. Aguayo, A. Bru, G. Garcia-Belmonte, J.L. de Pablos, P. Gomez, V. Rodellar, A new approach to automatic radiation spectrum analysis, IEEE Trans. Nucl. Sci. 38 (1991) 971-975, https://doi.org/10.1109/23.83860. 
  9. C. Bobin, O. Bichler, V. Lourenco, C. Thiam, M. Thevenin, Real-time radionuclide identification in γ-emitter mixtures based on spiking neural network, Appl. Radiat. Isot. 109 (2016) 405-409, https://doi.org/10.1016/j.apradiso.2015.12.029. 
  10. J. Hwang, B. Jeon, J. Kim, H. Kim, G. Cho, Deep learning-based spectrum-dose prediction for a plastic scintillation detector, Radiat. Phys. Chem. 201 (2022) 110444, https://doi.org/10.1016/j.radphyschem.2022.110444. 
  11. G. Gilmore, Practical Gamma-Ray Spectroscopy, John Wiley & Sons, 2008, pp. 144-145. 
  12. N. Charles, B. Meinhold, Biological Effects and Exposure for Hot Particles, 1999. 
  13. C.M. Bishop, Pattern Recognition and Machine Learning, 2006, https://doi.org/10.1007/BF00746534. 
  14. C. gregorich, Technical Report, In-Plant Gamma Spectrometry: Isotopic Data Collection Experiences, Electric Power Research Institute, 2015 3002005481.