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.

Measured spectra in a high count rate environment are difficult to analyze because of the spectral distortions caused by the pulse pile-up effect. This study proposes a deep learning-based method for separating and predicting the true pulse height of a signal with pulse pile-up events for application to radiation measurement and spectroscopy with a scintillation detector. To train the deep learning model, pulse signals simulating scintillation pulses were prepared by using a predefined mathematical model with parameters determined by analysis of the scintillation pulse measured from a NaI(Tl) detector. To simulate realistic scintillation pulses, Gaussian noises corresponding to thermal and shot noises were added to the signals. The trained model was validated with signals measured from two gamma-ray sources, $^{\mathbf {22}}$ Na and $^{\mathbf {137}}$ Cs. The model was then evaluated using two performance indicators, restoration and separation rates, which represent how much the net count is restored in the region of interest (ROI) and the separation accuracy depending on the time interval. As a result, the deep learning model was confirmed to correctly estimate the pulse heights in a high pile-up environment up to certain restoration and separation rates.