Training GAN to simulate EXO-200 scintillation signal Shaolei Li - PowerPoint PPT Presentation

Training GAN to simulate EXO-200 scintillation signal Shaolei Li DANCE-ML workshop 6 Aug 2020 1

Introductions • EXO-200 used large avalanche photodiodes (APDs) to measure scintillation light. • Simulations of APD signals were di ffi cult and time-consuming and so far there is not a good method to approach that goal. • A new approach to fast-simulations is generative adversarial networks (GANs). • They produce artificial images from random input while guided by real images. • The generator we want is constrained during the training such that the signals show the expected dependency on the energy and positions. 2

WGAN structure • Generator: get noise, label, and generate artificial waveform. • Critic (discriminator): receive artificial and real waveform, and give Wasserstein distance. • Constrainers: supervise training. • Keras and Tensorflow are used to train GAN at SLAC GPUs. 3

Training set • Total107210 events. • Being flatten in space in order to prevent networks from cheating. • Charge energy works as label during the training. • Weak Th calibration data are used to train GAN. 4

Convergence of constrainers 5

Generated waveform vs. Real waveform cm cm cm keV 6

Peak amplitude along z axis • Add up waveforms on one side of cylinder, and select maximum point as the amplitude. • Generator receives labels of 2615 keV and random positions, while selecting events around 2615 200 keV. ± • The plots show mean value of all events and the corresponding standard deviation as error-bars. Plane A Plane B 7

Training results reconstruction • GAN can also do reconstruction work using constrainer parts. • Comparing constrainer results after 100 epoch using both GAN and real waveforms and EXO-200 recon results. • The plots shows testing results using validation set with 6000 events. Compare DNN and EXO recon Compare DNN recon on GAN and real waveform 8

Deviations of energy around peak • Select events in 2300~3000 keV, and use labels to create artificial waveform. • Use constrainer to reconstruct energy from both artificial and real waveforms. • The histograms shows the deviations between them and means are close to 0. 9

Compare recon results of general events • 100000 events outside training and validation sets. 10

Conclusion and further studies • GAN is able to generate waveforms close to the real ones. • In order do better training, better constrainers will help. • We may try changing tensor shape in order to be closer to the real APDs range on the plane. 11