IOP : A deep-learning based raw waveform region-of-interest finder for the liquid argon time projection chamber

Acciarri, R.; Bromberg, C.; Lepetic, I.; Szelc, A.M.; Wu, W.; James, C.; Basque, V.; Luo, X.; Fleming, B.; Baller, B.; Wang, M.H.L.S.; Yang, T.; Spitz, J.; Green, P.; Cavanna, F.; Scanavini, G.; Edmunds, D.; Uboldi, L.; Soderberg, M.; Palamara, O.; Fitzpatrick, R.S.

doi:10.1088/1748-0221/17/01/P01018

Article
Report number	arXiv:2103.06391 ; FERMILAB-PUB-21-079-ND-SCD
Title	A deep-learning based raw waveform region-of-interest finder for the liquid argon time projection chamber
Author(s)	Acciarri, R. (Fermilab) ; Baller, B. (Fermilab) ; Basque, V. (Manchester U.) ; Bromberg, C. (Michigan State U.) ; Cavanna, F. (Fermilab) ; Edmunds, D. (Michigan State U.) ; Fitzpatrick, R.S. (Michigan U.) ; Fleming, B. (Yale U.) ; Green, P. (Manchester U.) ; James, C. (Fermilab) ; Lepetic, I. (Rutgers U., Piscataway) ; Luo, X. (UC, Santa Barbara) ; Palamara, O. (Fermilab) ; Scanavini, G. (Yale U.) ; Soderberg, M. (Syracuse U.) ; Spitz, J. (Michigan U.) ; Szelc, A.M. (Edinburgh U.) ; Uboldi, L. (CERN) ; Wang, M.H.L.S. (Fermilab) ; Wu, W. (Fermilab) ; Yang, T. (Fermilab)
Publication	2022-01-12
Imprint	2021-03-10
Number of pages	15
Note	15 pages, 12 figures
In:	JINST 17 (2022) P01018
DOI	10.1088/1748-0221/17/01/P01018 (publication)
Subject category	hep-ex ; Particle Physics - Experiment ; physics.ins-det ; Detectors and Experimental Techniques
Accelerator/Facility, Experiment	FNAL T 0962
Abstract	The liquid argon time projection chamber (LArTPC) detector technology has an excellent capability to measure properties of low-energy neutrinos produced by the sun and supernovae and to look for exotic physics at very low energies. In order to achieve those physics goals, it is crucial to identify and reconstruct signals in the waveforms recorded on each TPC wire. In this paper, we report on a novel algorithm based on a one-dimensional convolutional neural network (CNN) to look for the region-of-interest (ROI) in raw waveforms. We test this algorithm using data from the ArgoNeuT experiment in conjunction with an improved noise mitigation procedure and a more realistic data-driven noise model for simulated events. This deep-learning ROI finder shows promising performance in extracting small signals and gives an efficiency approximately twice that of the traditional algorithm in the low energy region of $\sim$0.03-0.1 MeV. This method offers great potential to explore low-energy physics using LArTPCs.
Related document	Slides FERMILAB-SLIDES-21-007-ND-SCD-V
Copyright/License	publication: © 2022-2025 IOP Publishing Ltd and Sissa Medialab preprint: (License: CC BY 4.0)