Restoring the saturation response of a PMT using pulse-shape and artificial-neural-networks

Abstract The linear response of a photomultiplier tube (PMT) is required property for photon counting and reconstruction the neutrino energy. linearity valid region saturation PMT were investigated using linear-alkyl-benzene (LAB)-based liquid scintillator. A correlation was observed between two different responses, with pulse-shape distortion pulse-area decrease. provides useful information estimation relative to pulse-area. This correlation-based diagnosis allows an in-situ range, which previously challenging. measured responses employed train artificial-neural-network (ANN) predict decrease in from pulse-shape. ANN-predicted enables prediction ideal number photoelectrons irrelevant behavior. pulse-shape-based machine learning technique offers novel method restoring PMTs.