A new radionuclide identification method for low-count energy spectra with multiple radionuclides. (July 2022)

• Record Type: Journal Article
• Authors: Li, Chunmiao; Liu, Shuangquan; Wang, Chao; Jiang, Xiaopan; Sun, Xiaoli; Li, Mohan; Wei, Long
• Is Part Of: Applied radiation and isotopes. Volume 185(2022)
• Publication Date: 2022-07
• Subjects: Radionuclide identification -- Feature enhancer -- One-dimensional neural network -- Low-count spectra -- Multiple radionuclides; Radiology -- Periodicals; Radiation -- Industrial applications -- Periodicals; Nuclear chemistry -- Periodicals; Internet resource; Periodical; 660.298
• DOI: 10.1016/j.apradiso.2022.110219
• Languages: English
• ISSNs: 0969-8043

Abstract

Abstract: Radionuclide identification is to recognize the radionuclides in the environment by analyzing the energy spectrum. Rapid and accurate identification is important for nuclear security. Current radionuclide identification methods based on traditional peak search require background subtraction. As a result, they have difficulties to deal with complex situations in practical applications such as low-count energy spectrum and mixed nuclides. In this paper, we propose a new radionuclide identification method with a feature enhancer and a one-dimensional neural network. The training dataset in this method is from simulated data generated by Geant4. By preprocessing the input energy spectrum data through the feature enhancer and extracting the nonlinear information through the neural network, this approach performs well on experimental energy spectra even at low count. The method also shows a high recognition accuracy and little misjudgments when dealing with mixed radionuclides spectra. Due to its good performance in identifying mixed nuclides and low-count spectra, the method has been deployed in portable instrument for radionuclide identification in real-time measurement. Highlights: A new nuclide identification method for low-count energy spectra with multiple radionuclides is developed. The method combines a feature enhancer based on the prior energy information and a neural network to classify the nuclides. With the good universality of this method, the types of nuclides in database can be further increased. The method has been deployed in portable instrument for radionuclide identification in real-time measurement.