Quantitative analysis of energy-dispersive X-ray fluorescence spectroscopy based on machine learning and a generative data enhancement technique.

This paper proposes a data enhancement technique to generate expanded datasets for machine learning by developing an X-ray fluorescence spectra simulator based on the physical process. The simulator consists of several modules, including the excitation source, the interaction process, and the detection system. The spectra generated by the simulator are subject to dimension reduction through feature selection and feature extraction algorithms, and then serve as the input for the XGBoost (extreme gradient boosting) model. Six elements of metal samples with various content ranges were selected as the research target. The results showed that for simulated data, the R 2 value for elements with concentrations ranging from 0% to 100% is greater than 95%, and for elements with concentrations of <0.3%, the R 2 value is greater than 85%. The experimental data were predicted by the model trained by the simulated spectra. Therefore, this approach provides reliable results for practical application and can supply additional datasets to obtain reasonable prediction results for machine learning with inadequate reference materials.

A Portable Three-Layer Compton Camera for Wide-Energy-Range Gamma-ray Imaging: Design, Simulation and Preliminary Testing.

(1) Background: The imaging energy range of a typical Compton camera is limited due to the fact that scattered gamma photons are seldom fully absorbed when the incident energies are above 3 MeV. Further improving the upper energy limit of gamma-ray imaging has important application significance in the active interrogation of special nuclear materials and chemical warfare agents, as well as range verification of proton therapy. (2) Methods: To realize gamma-ray imaging in a wide energy range of 0.3~7 MeV, a principle prototype, named a portable three-layer Compton camera, is developed using the scintillation detector that consists of an silicon photomultiplier array coupled with a Gd3Al2Ga3O12:Ce pixelated scintillator array. Implemented in a list-mode maximum likelihood expectation maximization algorithm, a far-field energy-domain imaging method based on the two interaction events is applied to estimate the initial energy and spatial distribution of gamma-ray sources. The simulation model of the detectors is established based on the Monte Carlo simulation toolkit Geant4. The reconstructed images of a 133Ba, a 137Cs and a 60Co point-like sources have been successfully obtained with our prototype in laboratory tests and compared with simulation studies. (3) Results: The proportion of effective imaging events accounts for about 2%, which allows our prototype to realize the reconstruction of the distribution of a 0.05 µSv/h 137Cs source in 10 s. The angular resolution for resolving two 137Cs point-like sources is 15°. Additional simulated imaging of the 6.13 MeV gamma-rays from 14.1 MeV neutron scattering with water preliminarily demonstrates the imaging capability for high incident energy. (4) Conclusions: We conclude that the prototype has a good imaging performance in a wide energy range (0.3~7 MeV), which shows potential in several MeV gamma-ray imaging applications.

Ground Radioactivity Distribution Reconstruction and Dose Rate Estimation Based on Spectrum Deconvolution.

Estimating the gamma dose rate at one meter above ground level and determining the distribution of radioactive pollution from aerial radiation monitoring data are the core technical issues of unmanned aerial vehicle nuclear radiation monitoring. In this paper, a reconstruction algorithm of the ground radioactivity distribution based on spectral deconvolution was proposed for the problem of regional surface source radioactivity distribution reconstruction and dose rate estimation. The algorithm estimates unknown radioactive nuclide types and their distributions using spectrum deconvolution and introduces energy windows to improve the accuracy of the deconvolution results, achieving accurate reconstruction of multiple continuous distribution radioactive nuclides and their distributions, as well as dose rate estimation of one meter above ground level. The feasibility and effectiveness of the method were verified through cases of single-nuclide (137Cs) and multi-nuclide (137Cs and 60Co) surface sources by modeling and solving them. The results showed that the cosine similarities between the estimated ground radioactivity distribution and dose rate distribution with the true value were 0.9950 and 0.9965, respectively, which could prove that the proposed reconstruction algorithm would effectively distinguish multiple radioactive nuclides and accurately restore their radioactivity distribution. Finally, the influences of statistical fluctuation levels and the number of energy windows on the deconvolution results were analyzed, showing that the lower the statistical fluctuation level and the more energy window divisions, the better the deconvolution results.

Comparison of machine learning approaches for radioisotope identification using NaI(TI) gamma-ray spectrum.

This research aims at comparing the performance of different machine learning algorithms used for NaI(TI) gamma-ray detector based radioisotope identification. Six machine learning algorithms were implemented, including support vector machine (SVM), k-nearest neighbor (KNN), logistic regression (LR), naive Bayes (NB), decision tree (DT), and multilayer perceptron (MLP). The hyper-parameters of each model were elaborately optimized. The effects of data size, statistical fluctuation, and spectrum drift were considered. Results show that for smaller data size (5 types of radioisotopes and 6000 spectra), the support vector machine and the logistic regression classifier exhibit higher identification accuracy with less training/predicting time. Whereas for larger data size (14 types of radioisotopes corresponding to the standard IEC 62327-2017), the multilayer perceptron showed highest accuracy but required the longest time for model training. The naive Bayes classifier and the decision tree were prone to make mistakes when fluctuations and distortions were added to the spectra. The k-nearest neighbor classifier, though showing high accuracy for most data sets, consumed the longest time while making prediction.

Assessment of a compton-suppressed spectrometer for measurement of radioactive xenon isotopes.

Airborne radionuclide monitoring is considered to be the most certain way to detect a clandestine nuclear weapon test. The activity concentration of radioxenon samples collected by the radionuclide stations of the International Monitoring System (IMS) for the Comprehensive Nuclear-Test-Ban Treaty (CTBT) is generally performed at the low-level, hence it is necessary to improve the detection sensitivity of the radioactivity measuring apparatus for radionuclide monitoring. The Compton-suppressed spectrometer (CSS) has the advantage of reducing the background and improving the sensitivity in the environmental level measurement. Therefore, the measurement of the relevant radioxenon sample at the environmental level is feasible by using CSS. To assess the performance of CSS for radioxenon measurements, the Compton-suppressed and unsuppressed spectra of the 133Xe and 127Xe samples have been acquired, and subsequently, the information of the full energy peaks (FEP) in the spectra were compared. The assessment indicates that CSS can provide high sensitivity, simple operation, and straightforward activity determination, and it can be regarded as an appropriate apparatus in the radioxenon measurement.