Pulse Shape Discrimination in an Organic Scintillation Phoswich Detector Using Machine Learning Techniques

We developed machine learning algorithms for distinguishing scintillationsignals from a plastic-liquid coupled detector known as a phoswich. Thechallenge lies in discriminating signals from organic scintillators withsimilar shapes and short decay times. Using a single-readout phoswich detector,we successfully identified γ radiation signals from two scintillatingcomponents. Our Boosted Decision Tree algorithm demonstrated a maximumdiscrimination power of 3.02 ± 0.85 standard deviation in the 950 keVregion, providing an efficient solution for self-shielding and enhancingradiation detection capabilities.