Pulse height estimation and pulse shape discrimination in pile-up neutron and gamma ray signals from an organic scintillation detector using multi-task learning.

We developed a multi-tasking deep learning model for simultaneous pulse height estimation and pulse shape discrimination for pile-up n/γ signals. Compared with single-tasking models, our model showed better spectral correction performance with higher recall for neutrons. Further, it achieved more stable neutron counting with less signal loss and a lower error rate in the predicted gamma ray spectra. Our model can be applied to a dual radiation scintillation detector to discriminatively reconstruct each radiation spectrum for radioisotope identification and quantitative analysis.

Pseudo-Gamma Spectroscopy Based on Plastic Scintillation Detectors Using Multitask Learning.

Although plastic scintillation detectors possess poor spectroscopic characteristics, they are extensively used in various fields for radiation measurement. Several methods have been proposed to facilitate their application of plastic scintillation detectors for spectroscopic measurement. However, most of these detectors can only be used for identifying radioisotopes. In this study, we present a multitask model for pseudo-gamma spectroscopy based on a plastic scintillation detector. A deep- learning model is implemented using multitask learning and trained through supervised learning. Eight gamma-ray sources are used for dataset generation. Spectra are simulated using a Monte Carlo N-Particle code (MCNP 6.2) and measured using a polyvinyl toluene detector for dataset generation based on gamma-ray source information. The spectra of single and multiple gamma-ray sources are generated using the random sampling technique and employed as the training dataset for the proposed model. The hyperparameters of the model are tuned using the Bayesian optimization method with the generated dataset. To improve the performance of the deep learning model, a deep learning module with weighted multi-head self-attention is proposed and used in the pseudo-gamma spectroscopy model. The performance of this model is verified using the measured plastic gamma spectra. Furthermore, a performance indicator, namely the minimum required count for single isotopes, is defined using the mean absolute percentage error with a criterion of 1% as the metric to verify the pseudo-gamma spectroscopy performance. The obtained results confirm that the proposed model successfully unfolds the full-energy peaks and predicts the relative radioactivity, even in spectra with statistical uncertainties.

Reconstruction of Compton Edges in Plastic Gamma Spectra Using Deep Autoencoder.

Plastic scintillation detectors are widely utilized in radiation measurement because of their unique characteristics. However, they are generally used for counting applications because of the energy broadening effect and the absence of a photo peak in their spectra. To overcome their weaknesses, many studies on pseudo spectroscopy have been reported, but most of them have not been able to directly identify the energy of incident gamma rays. In this paper, we propose a method to reconstruct Compton edges in plastic gamma spectra using an artificial neural network for direct pseudo gamma spectroscopy. Spectra simulated using MCNP 6.2 software were used to generate training and validation sets. Our model was trained to reconstruct Compton edges in plastic gamma spectra. In addition, we aimed for our model to be capable of reconstructing Compton edges even for spectra having poor counting statistics by designing a dataset generation procedure. Minimum reconstructible counts for single isotopes were evaluated with metric of mean averaged percentage error as 650 for 60Co, 2000 for 137Cs, 3050 for 22Na, and 3750 for 133Ba. The performance of our model was verified using the simulated spectra measured by a PVT detector. Although our model was trained using simulation data only, it successfully reconstructed Compton edges even in measured gamma spectra with poor counting statistics.

CALCULATION OF GAMMA SPECTRA IN A PLASTIC SCINTILLATOR FOR ENERGY CALIBRATIONAND DOSE COMPUTATION.

Plastic scintillation detectors have practical advantages in the field of dosimetry. Energy calibration of measured gamma spectra is important for dose computation, but it is not simple in the plastic scintillators because of their different characteristics and a finite resolution. In this study, the gamma spectra in a polystyrene scintillator were calculated for the energy calibration and dose computation. Based on the relationship between the energy resolution and estimated energy broadening effect in the calculated spectra, the gamma spectra were simply calculated without many iterations. The calculated spectra were in agreement with the calculation by an existing method and measurements.

PLASTIC SCINTILLATOR FOR RADIATION DOSIMETRY.

Inorganic scintillators, composed of high-atomic-number materials such as the CsI(Tl) scintillator, are commonly used in commercially available a silicon diode and a scintillator embedded indirect-type electronic personal dosimeters because the light yield of the inorganic scintillator is higher than that of an organic scintillator. However, when it comes to tissue-equivalent dose measurements, a plastic scintillator such as polyvinyl toluene (PVT) is a more appropriate material than an inorganic scintillator because of the mass energy absorption coefficient. To verify the difference in the absorbed doses for each scintillator, absorbed doses from the energy spectrum and the calculated absorbed dose were compared. From the results, the absorbed dose of the plastic scintillator was almost the same as that of the tissue for the overall photon energy. However, in the case of CsI, it was similar to that of the tissue only for a photon energy from 500 to 4000 keV. Thus, the values and tendency of the mass energy absorption coefficient of the PVT are much more similar to those of human tissue than those of the CsI.

Development and applications of a new neutron single-crystal diffractometer based on a two-dimensional large-area curved position-sensitive detector.

A new single-crystal neutron diffractometer based on a large-area curved two-dimensional position-sensitive detector (C-2DPSD) has been developed. The diffractometer commissioning is almost complete, together with development of the measurement methodology and the raw data processing software package, the Reciprocal Analyzer, and the instrument is now ready to be launched for users. Position decoding of the C-2DPSD is via a delay-line readout method with an effective angular range of 110 × 54° in the horizontal and vertical directions, respectively, with a nominal radius of curvature of 530 mm. The diffractometer is equipped with a Ge(311) mosaic monochromator and two supermirror vacuum guide paths, one before and one after the monochromator position. The commissioning incorporates corrections and calibration of the instrument using an NaCl crystal, various applications such as crystallographic and magnetic structure measurements, a crystallinity check on large crystals, and a study on the composition or dopant content of a mixed crystal of (Tm x Yb1-x )Mn2O5. The installation of the diffractometer and the measurement method, the calibration procedure and results, the raw data treatment and visualization, and several applications using the large C-2DPSD-based diffractometer are reported.