Photon detection probability prediction using one-dimensional generative neural network

Abstract Photon detection is important for liquid argon detectors direct dark matter searches or neutrino property measurements. Precise simulation of photon transport widely used to understand the probability in detectors. Traditional simulation, tracking every within framework Geant4, a major computational challenge kilo-tonne-scale and GeV-level energy depositions. In this work, we propose one-dimensional generative model which efficiently generates features using an OuterProduct-layer. This bypasses predicts number photons detected by particular at same level detail as Geant4 simulation. The application simulating systems demonstrates novel able reproduce with good accuracy 20 50 times faster. can be quickly predict huge like ProtoDUNE DUNE.