Generative adversarial networks for scintillation signal simulation in EXO-200

Li S, Ostrovskiy I, Li Z, Yang L, Al Kharusi S, Anton G, Barbeau PS, Badhrees I, Beck D, Belov V, Bhatta T, Breidenbach M, Brunner T, Cao GF, Cen WR, Chambers C, Cleveland B, Coon M, Craycraft A, Daniels T, Darroch L, Daugherty SJ, Davis J, Delaquis S, Der Mesrobian-Kabakian A, DeVoe R, Dilling J, Dolgolenko A, Dolinski MJ, Echevers J, Fairbank W, Fairbank D, Farine J, Feyzbakhsh S, Fierlinger P, Fu YS, Fudenberg D, Gautam P, Gornea R, Gratta G, Hall C, Hansen EV, Hößl J, Hufschmidt P, Hughes M, Iverson A, Jamil A, Jessiman C, Jewell MJ, Johnson A, Karelin A, Kaufman LJ, Koffas T, Krücken R, Kuchenkov A, Kumar KS, Lan Y, Larson A, Lenardo BG, Leonard DS, Li GS, Licciardi C, Lin YH, MacLellan R, McElroy T, Michel T, Mong B, Moore DC, Murray K, Njoya O, Nusair O, Odian A, Perna A, Piepke A, Pocar A, Retière F, Robinson AL, Rowson PC, Runge J, Schmidt S, Sinclair D, Skarpaas K, Soma AK, Stekhanov V, Tarka M, Thibado S, Todd J, Tolba T, Totev TI, Tsang R, Veenstra B, Veeraraghavan V, Vogel P, Vuilleumier JL, Wagenpfeil M, Watkins J, Weber M, Wen LJ, Wichoski U, Wrede G, Wu SX, Xia Q, Yahne DR, Yen YR, Zeldovich OY, Ziegler T (2023)

Publication Language: English

Publication Type: Journal article

Publication year: 2023

Journal

Book Volume: 18

Article Number: P06005

Journal Issue: 6

DOI: 10.1088/1748-0221/18/06/P06005

Abstract

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.

Authors with CRIS profile

Involved external institutions

Laurentian University Canada (CA) Stanford National Accelerator Laboratory (SLAC) United States (USA) (US) Drexel University United States (USA) (US) University of Maryland, College Park (UMD) United States (USA) (US) University of California, San Diego (UC San Diego, UCSD) United States (USA) (US) McGill University Canada (CA) Triangle Universities Nuclear Laboratory United States (USA) (US) University of Illinois at Urbana-Champaign United States (USA) (US) Indiana University United States (USA) (US) Stanford University United States (USA) (US) University of South Dakota United States (USA) (US) Institute of High Energy Physics (IHEP) / 中国科学院高能物理研究所 China (CN) Colorado State University United States (USA) (US) Institute for Theoretical and Experimental Physics (ITEP) /Институт теоретической и экспериментальной физики Russian Federation (RU) The University of Alabama United States (USA) (US) Carleton University Canada (CA) University of Massachusetts Amherst (UMass) United States (USA) (US) Institute for Basic Science Korea, Republic of (KR) California Institute of Technology (Caltech) United States (USA) (US) Universität Bern Switzerland (CH) TRIUMF Canada (CA) University of North Carolina Wilmington (UNCW) United States (USA) (US) Technische Universität München (TUM) Germany (DE) Yale University United States (USA) (US) State University of New York at Albany (UNY Albany / UAlbany) United States (USA) (US)

How to cite

APA:

Li, S., Ostrovskiy, I., Li, Z., Yang, L., Al Kharusi, S., Anton, G.,... Ziegler, T. (2023). Generative adversarial networks for scintillation signal simulation in EXO-200. Journal of Instrumentation, 18(6). https://doi.org/10.1088/1748-0221/18/06/P06005

MLA:

Li, S., et al. "Generative adversarial networks for scintillation signal simulation in EXO-200." Journal of Instrumentation 18.6 (2023).

BibTeX: Download