• Journal of Radiation Protection and Research
• /
• v.46 no.4
• /
• pp.204-212
• /
• 2021

Background: Identification of radioisotopes for plastic scintillation detectors is challenging because their spectra have poor energy resolutions and lack photo peaks. To overcome this weakness, many researchers have conducted radioisotope identification studies using machine learning algorithms; however, the effect of data normalization on radioisotope identification has not been addressed yet. Furthermore, studies on machine learning-based radioisotope identifiers for plastic scintillation detectors are limited. Materials and Methods: In this study, machine learning-based radioisotope identifiers were implemented, and their performances according to data normalization methods were compared. Eight classes of radioisotopes consisting of combinations of ²²Na, ⁶⁰Co, and ¹³⁷Cs, and the background, were defined. The training set was generated by the random sampling technique based on probabilistic density functions acquired by experiments and simulations, and test set was acquired by experiments. Support vector machine (SVM), artificial neural network (ANN), and convolutional neural network (CNN) were implemented as radioisotope identifiers with six data normalization methods, and trained using the generated training set. Results and Discussion: The implemented identifiers were evaluated by test sets acquired by experiments with and without gain shifts to confirm the robustness of the identifiers against the gain shift effect. Among the three machine learning-based radioisotope identifiers, prediction accuracy followed the order SVM > ANN > CNN, while the training time followed the order SVM > ANN > CNN. Conclusion: The prediction accuracy for the combined test sets was highest with the SVM. The CNN exhibited a minimum variation in prediction accuracy for each class, even though it had the lowest prediction accuracy for the combined test sets among three identifiers. The SVM exhibited the highest prediction accuracy for the combined test sets, and its training time was the shortest among three identifiers.

• Nuclear Engineering and Technology
• /
• v.55 no.2
• /
• pp.707-716
• /
• 2023

The influence of waste technological waters of thermal and fast reactors of Beloyarsk NPP (Russia) on the accumulation of ⁶⁰Co, ⁹⁰Sr and ¹³⁷Cs in macrophytes and ichthyofauna of the cooling pond has been studied. Critical radionuclides, routes of their entry into the ecosystem and periods of maximum discharge of radioisotopes into the cooling pond have been determined. It is shown that the technology of electricity generation at the Beloyarsk NPP, based on fast reactors, has a much smaller effect on the release of artificial radionuclides into the environment. Therefore, during the entire period of monitoring studies (1976-2019), the decrease in the specific activity of radionuclides of NPP origin in macrophytes was 13-25800 times, in ichthyofauna 1.5-44.5 times. The maximum discharge of artificial radionuclides into the Beloyarsk reservoir was noted during the period of restoration and decontamination work aimed at eliminating the emergencies at the AMB reactors of NPP. The factors influencing the accumulation of artificial radionuclides in the components of the freshwater ecosystem of the Beloyarsk cooling pond have been determined, including: the physicochemical nature of radioisotopes, their concentration in surface water, the temperature of the aquatic environment, the trophicity of the reservoir, the species of hydrobionts.

• Nuclear Engineering and Technology
• /
• v.54 no.8
• /
• pp.3043-3050
• /
• 2022

In Korea, all nuclear power plants (NPPs) participate in annual performance tests including in vivo measurements using the FastScan, a stand type whole body counter (WBC), manufactured by Canberra. In 2018, all Korean NPPs satisfied the testing criterion, the root mean square error (RMSE) ≤ 0.25, for the whole body configuration, but three NPPs which participated in an additional lung configuration test in the fission and activation product category did not meet the criterion. Due to the low resolution of the FastScan NaI(Tl) detectors, the conventional peak analysis (PA) method of the FastScan did not show sufficient performance to meet the criterion in the presence of interfering radioisotopes (RIs), ¹³⁴Cs and ¹³⁷Cs. In this study, we developed an artificial neural network (ANN) to improve the performance of the FastScan in the lung configuration. All of the RMSE values derived by the ANN satisfied the criterion, even though the photopeaks of ¹³⁴Cs and ¹³⁷Cs interfered with those of the analytes or the analyte photopeaks were located in a low-energy region below 300 keV. Since the ANN performed better than the PA method, it would be expected to be a promising approach to improve the accuracy and precision of in vivo FastScan measurement for the lung configuration.

• Journal of Korean Society for Atmospheric Environment
• /
• v.11 no.4
• /
• pp.351-359
• /
• 1995

In order to investigate geochemical behaviors of artificial radionuclide($^{137}$ Cs), the fallout deposition of arificial radioisotope($^{137}$ Cs) was measured from May to October in 1994 at the Korea Ocean Research & Development Institute(KORDI), Ansan, Kyunggido, Korea. And to study radioisotopic behavior and cumulative action in soil, soil samples were collected from Kwang-Leung Forest, Kyunggidom and artificial radioisotope ($^{137}$ Cs) and natural radioisotope($^{210}$ Pb) were identified. The amount of $^{137}$ Cs in atmosphere collected by wet deposition process in May was found to be 4.95 to 11.96mBq m$^{-2}$ whereas the amounts of $^{137}$ Cs by dry deposition process in May and October were found to be 4.0mBq g$^{-1}$ and 3.0mBq g$^{-1}$ , respectively. The amount of $^{137}$ Cs accumulated in soil was measured to be 311mBq cm$^{-2}$ , which contained 83% of the total inputs from atmospheric fallout (374 mBq cm$^{-2}$ ) since 1960s. In addition, the accumulation rate and the annual flux of $^{210}$ Pb into soils were 0.32cm yr$^{-1}$ and 34 mBq cm$^{-2}$ yr$^{-1}$ , respectively. Conclusively, it was found that arificial radioisotopes were mainly from the stratosphere and soil resupension of continental China through the troposphere.

• Nuclear Engineering and Technology
• /
• v.53 no.4
• /
• pp.1277-1283
• /
• 2021

It is important for operators of poly-pipelines in petroleum industry to continuously monitor characteristics of transferred fluid such as its type and amount. To achieve this aim, in this study a dual energy gamma attenuation technique in combination with artificial neural network (ANN) is proposed to simultaneously determine type and amount of four different petroleum by-products. The detection system is composed of a dual energy gamma source, including americium-241 and barium-133 radioisotopes, and one 2.54 cm × 2.54 cm sodium iodide detector for recording the transmitted photons. Two signals recorded in transmission detector, namely the counts under photo peak of Americium-241 with energy of 59.5 keV and the counts under photo peak of Barium-133 with energy of 356 keV, were applied to the ANN as the two inputs and volume percentages of petroleum by-products were assigned as the outputs.

• Nuclear Engineering and Technology
• /
• v.54 no.8
• /
• pp.3034-3042
• /
• 2022

The results of radioecological monitoring of the cooling pond Beloyarsk NPP (Russia) have been presented. The influence of waste technological waters of thermal and fast NPP reactors on the content of artificial radionuclides in surface waters and bottom sediments of the Beloyarsk reservoir has been studied. The long-term dynamics of the specific activity of ⁶⁰Co, ⁹⁰Sr, ¹³⁷Cs and ³H in the main components of the freshwater ecosystem at different distances from the source of radionuclide discharge has been estimated. Critical radionuclides (⁶⁰Co and ¹³⁷Cs), routes of their entry and periods of maximum discharge of radioisotopes into the cooling pond have been determined. It is shown that the technology of electricity generation at Beloyarsk NPP, based on fast reactors, has a much smaller effect on the flow of artificial radionuclides into the freshwater ecosystem of the reservoir. During the entire period of monitoring studies, the decrease in the specific activity of radionuclides from NPP origin in surface waters was 4.3-74.5 times, in bottom sediments 10-505 times. The maximum discharge of artificial radionuclides into the reservoir was noted during the period of restoration and decontamination work aimed at eliminating emergencies at the AMB thermal reactors of the first stage of the Beloyarsk NPP.

• Journal of Radiation Protection and Research
• /
• v.15 no.2
• /
• pp.75-85
• /
• 1990

The dose calculations were carried out using environmental montoring data around Karlsruhe Nuclear Research Center(KfK). Ingestion of plant foods was the most important pathway, and the K-40 and Pb-210 natural radioisotopes in food were the most effective radiation source to man. The dose received from artificial nuclides were mostly emitted by gamma irradiation of Cs-134 and Cs-137 deposited on the ground. The effective dose equivalent in the KfK environment was far less than the dose equivalent limit recommended by ICRP.

• Nuclear Engineering and Technology
• /
• v.53 no.12
• /
• pp.4072-4079
• /
• 2021

This article presents a study on the state-of-the-art methods for automated radioactive material detection and identification, using gamma-ray spectra and modern machine learning methods. The recent developments inspired this in deep learning algorithms, and the proposed method provided better performance than the current state-of-the-art models. Machine learning models such as: fully connected, recurrent, convolutional, and gradient boosted decision trees, are applied under a wide variety of testing conditions, and their advantage and disadvantage are discussed. Furthermore, a hybrid model is developed by combining the fully-connected and convolutional neural network, which shows the best performance among the different machine learning models. These improvements are represented by the model's test performance metric (i.e., F1 score) of 93.33% with an improvement of 2%-12% than the state-of-the-art model at various conditions. The experimental results show that fusion of classical neural networks and modern deep learning architecture is a suitable choice for interpreting gamma spectra data where real-time and remote detection is necessary.

• Nuclear Engineering and Technology
• /
• v.51 no.6
• /
• pp.1626-1632
• /
• 2019

Monitoring of environmental radioactivity is essential for ensuring the radiological safety of residents who live near nuclear power plants. Ulsan, South Korea, is surrounded by 16 nuclear power plants, the highest density in the country. In addition, the city contains facilities for conducting radiological nondestructive testing and using radioisotopes for medical purposes. It makes the confirmation of radiological safety particularly necessary. In this study, sampling points were selected based on regional characteristics, and surface water samples were pretreated and analyzed for gross beta and gamma radiation levels. In addition, the distribution of the city's gamma dose rate was determined using a mobile monitoring system and distribution visualization program. The results showed that there is no effect on the gross beta and gamma nuclides of artificial radionuclides, and the gamma dose rate of the entire region did not exceed the environmental radiation level in South Korea overall, confirming the radiological safety of the city.

• Clean Technology
• /
• v.22 no.2
• /
• pp.122-131
• /
• 2016

Caesium radioisotopes, ¹³⁴Cs and ¹³⁷Cs which come from the atmospheric nuclear tests and discharges from nuclear power plants, are very important to study artificial radioactivity. In this work, in order to lower the minimum detection activity (MDA) we investigated environmental radioactivity according to the Environment Measurement Laboratory procedure by ¹³⁷Cs and ¹³⁴Cs which is similar to chemical and environmental behaviors of ¹³⁷Cs. The environmental soils in high mountain areas near nuclear power plant were collected, and an Ammonium Molybdophosphate (AMP) precipitation method, which showed high selectivity toward Cs⁺ ions, was applied to chemically extract and concentrate Caesium radioisotopes. Radioactivity was estimated by a gamma-ray spectrometry. In gamma energy spectrum, with an increasing of ⁴⁰K radioactivity, it increased the MDA of ¹³⁴Cs and ¹³⁷Cs. Therefore, if the natural radionuclides were removed from the soil samples, the MDA of Caesium may be reduced, and the contents of ¹³⁷Cs of in the environmental soils can effectively be estimated. In the standard soil sample of Korea Institute of Nuclear Safety, radioactivity of ⁴⁰K was removed more than 84% on average, and the MDA of ¹³⁴Cs was reduced 2 times. The content of ¹³⁷Cs was recovered over 84%. On the other hand, in environmental soils, AMP precipitation method showed removal ratio of ⁴⁰K up to 180 times, which reduced the MDA about 5 times smaller than those of Direct method. ¹³⁷Cs recovery ratio showed from 54.54% to 70.06%. When considering the MDA and recovery ratio, AMP precipitation method is effective for detection of Caesium radioisotopes in low concentration.