Generative Adversarial Networks for Scintillation Signal Simulation in EXO-200
This work addresses the need for efficient simulation in particle physics experiments like EXO-200, though it is incremental as it applies an existing deep learning method to a specific domain problem.
The paper tackles the computational cost of simulating photodetector signals in the EXO-200 experiment by using a Wasserstein Generative Adversarial Network trained on real calibration data, achieving high-quality simulated waveforms an order of magnitude faster than traditional methods and correctly deducing key detector features like position dependency and dead channels.
Generative Adversarial Networks trained on samples of simulated or actual events have been proposed as a way of generating large simulated datasets at a reduced computational cost. In this work, a novel approach to perform the simulation of photodetector signals from the time projection chamber of the EXO-200 experiment is demonstrated. The method is based on a Wasserstein Generative Adversarial Network - a deep learning technique allowing for implicit non-parametric estimation of the population distribution for a given set of objects. Our network is trained on real calibration data using raw scintillation waveforms as input. We find that it is able to produce high-quality simulated waveforms an order of magnitude faster than the traditional simulation approach and, importantly, generalize from the training sample and discern salient high-level features of the data. In particular, the network correctly deduces position dependency of scintillation light response in the detector and correctly recognizes dead photodetector channels. The network output is then integrated into the EXO-200 analysis framework to show that the standard EXO-200 reconstruction routine processes the simulated waveforms to produce energy distributions comparable to that of real waveforms. Finally, the remaining discrepancies and potential ways to improve the approach further are highlighted.