Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment

被引：18

作者：

Kekic, M. ^{[19
,20
,22
]}

Adams, C. ^{[2
]}

Woodruff, K. ^{[3
]}

Renner, J. ^{[19
,20
,22
]}

Church, E. ^{[21
]}

Del Tutto, M. ^{[5
]}

Hernando Morata, J. A. ^{[22
]}

Gomez-Cadenas, J. J. ^{[9
,16
]}

Alvarez, V ^{[23
]}

Arazi, L. ^{[6
]}

Arnquist, I. J. ^{[21
]}

Azevedo, C. D. R. ^{[4
]}

Bailey, K. ^{[2
]}

Ballester, F. ^{[23
]}

Benlloch-Rodriguez, J. M. ^{[16
,19
,20
]}

Borges, F. I. G. M. ^{[14
]}

Byrnes, N. ^{[3
]}

Carcel, S. ^{[19
,20
]}

Carrion, J., V ^{[19
,20
]}

Cebrian, S. ^{[24
]}

Conde, C. A. N. ^{[14
]}

Contreras, T. ^{[11
]}

Diaz, G. ^{[22
]}

Diaz, J. ^{[19
,20
]}

Diesburg, M. ^{[5
]}

Escada, J. ^{[14
]}

Esteve, R. ^{[23
]}

Felkai, R. ^{[6
,7
,19
,20
]}

Fernandes, A. F. M. ^{[13
]}

Fernandes, L. M. P. ^{[13
]}

Ferrario, P. ^{[9
,16
]}

Ferreira, A. L. ^{[4
]}

Freitas, E. D. C. ^{[13
]}

Generowicz, J. ^{[16
]}

Ghosh, S. ^{[11
]}

Goldschmidt, A. ^{[8
]}

Gonzalez-Diaz, D. ^{[22
]}

Guenette, R. ^{[11
]}

Gutierrez, R. M. ^{[10
]}

Haefner, J. ^{[11
]}

Hafidi, K. ^{[2
]}

Hauptman, J. ^{[1
]}

Henriques, C. A. O. ^{[13
]}

Herrero, P. ^{[16
]}

Herrero, V ^{[23
]}

Ifergan, Y. ^{[6
,7
]}

Jones, B. J. P. ^{[3
]}

Labarga, L. ^{[18
]}

Laing, A. ^{[3
]}

Lebrun, P. ^{[5
]}

机构：

[1] Iowa State Univ, Dept Phys & Astron, 12 Phys Hall, Ames, IA 50011 USA

[2] Argonne Natl Lab, 9700 S Cass Ave, Argonne, IL 60439 USA

[3] Univ Texas Arlington, Dept Phys, POB 19059, Arlington, TX 76019 USA

[4] Univ Aveiro, Inst Nanostruct Nanomodelling & Nanofabricat i3N, Campus Santiago, P-3810193 Aveiro, Portugal

[5] Fermilab Natl Accelerator Lab, POB 500, Batavia, IL 60510 USA

[6] Ben Gurion Univ Negev, Fac Engn Sci, Nucl Engn Unit, POB 653, IL-8410501 Beer Sheva, Israel

[7] Nucl Res Ctr Negev, IL-84190 Beer Sheva, Israel

[8] Lawrence Berkeley Natl Lab, 1 Cyclotron Rd, Berkeley, CA 94720 USA

[9] Ikerbasque, Basque Fdn Sci, E-48013 Bilbao, Spain

[10] Univ Antonio Narino, Ctr Invest Ciencias Basicas & Aplicadas, Sede Circunvalar, Carretera 3 Este 47 A-15, Bogota, Colombia

[11] Harvard Univ, Dept Phys, Cambridge, MA 02138 USA

[12] Lab Subterraneo Canfranc, Paseo Ayerbe S-N, E-22880 Canfranc Estacion, Spain

[13] Univ Coimbra, Phys Dept, LIBPhys, Rua Larga, P-3004516 Coimbra, Portugal

[14] Univ Coimbra, Dept Phys, LIP, P-3004516 Coimbra, Portugal

[15] Texas A&M Univ, Dept Phys & Astron, College Stn, TX 77843 USA

[16] Donostia Int Phys Ctr DIPC, Paseo Manuel Lardizabal 4, E-20018 Donostia San Sebastian, Spain

[17] Univ Girona, Escola Politecn Super, Av Montilivi S-N, E-17071 Girona, Spain

[18] Univ Autonoma Madrid, Dept Fis Teor, Campus Cantoblanco, E-28049 Madrid, Spain

[19] CSIC, Inst Fis Corpuscular IFIC, Calle Catedrat Jose Beltran 2, E-46980 Paterna, Spain

[20] Univ Valencia, Calle Catedrat Jose Beltran 2, E-46980 Paterna, Spain

[21] Pacific Northwest Natl Lab, Richland, WA 99352 USA

[22] Univ Santiago de Compostela, Inst Gallego Fis Altas Energias, Campus Sur,Rua Xose Maria Suarez Nunez S-N, E-15782 Santiago De Compostela, Spain

[23] Univ Politecn Valencia, Ctr Mixto, CSIC, Inst Instrumentac Imagen Mol I3M, Camino Vera S-N, E-46022 Valencia, Spain

[24] Univ Zaragoza, Ctr Astroparticulas & Fis Altas Energias CAPA, Calle Pedro Cerbuna 12, E-50009 Zaragoza, Spain

[25] Weizmann Inst Sci, Rehovot, Israel

[26] Univ Texas Austin, Austin, TX 78712 USA

来源：

JOURNAL OF HIGH ENERGY PHYSICS | 2021年 / 2021卷 / 01期

基金：

欧洲研究理事会;

关键词：

Dark Matter and Double Beta Decay (experiments);

D O I：

10.1007/JHEP01(2021)189

中图分类号：

O412 [相对论、场论]; O572.2 [粒子物理学];

学科分类号：

摘要：

Convolutional neural networks (CNNs) are widely used state-of-the-art computer vision tools that are becoming increasingly popular in high-energy physics. In this paper, we attempt to understand the potential of CNNs for event classification in the NEXT experiment, which will search for neutrinoless double-beta decay in Xe-136. To do so, we demonstrate the usage of CNNs for the identification of electron-positron pair production events, which exhibit a topology similar to that of a neutrinoless double-beta decay event. These events were produced in the NEXT-White high-pressure xenon TPC using 2.6 MeV gamma rays from a Th-228 calibration source. We train a network on Monte Carlo-simulated events and show that, by applying on-the-fly data augmentation, the network can be made robust against differences between simulation and data. The use of CNNs offers significant improvement in signal efficiency and background rejection when compared to previous non-CNN-based analyses.

引用

页数：22

共 50 条

[1] Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment
M. Kekic
C. Adams
K. Woodruff
J. Renner
E. Church
M. Del Tutto
J. A. Hernando Morata
J. J. Gómez-Cadenas
V. Álvarez
L. Arazi
I. J. Arnquist
C. D. R. Azevedo
K. Bailey
F. Ballester
J. M. Benlloch-Rodríguez
F. I. G. M. Borges
N. Byrnes
S. Cárcel
J. V. Carrión
S. Cebrián
C. A. N. Conde
T. Contreras
G. Díaz
J. Díaz
M. Diesburg
J. Escada
R. Esteve
R. Felkai
A. F. M. Fernandes
L. M. P. Fernandes
P. Ferrario
A. L. Ferreira
E. D. C. Freitas
J. Generowicz
S. Ghosh
A. Goldschmidt
D. González-Díaz
R. Guenette
R. M. Gutiérrez
J. Haefner
K. Hafidi
J. Hauptman
C. A. O. Henriques
P. Herrero
V. Herrero
Y. Ifergan
B. J. P. Jones
L. Labarga
A. Laing
P. Lebrun
Journal of High Energy Physics, 2021
[2] Background rejection in NEXT using deep neural networks
Renner, J.
Farbin, A.
Munoz Vidal, J.
Benlloch-Rodriguez, J. M.
Botas, A.
Ferrario, P.
Gomez-Cadenas, J. J.
Alvarez, V.
Azevedo, C. D. R.
Borges, F. I. G.
Carcel, S.
Carrion, J. V.
Cebrian, S.
Cervera, A.
Conde, C. A. N.
Diaz, J.
Diesburg, M.
Esteve, R.
Fernandes, L. M. P.
Ferreira, A. L.
Freitas, E. D. C.
Goldschmidt, A.
Gonzalez-Diaz, D.
Gutierrez, R. M.
Hauptman, J.
Henriques, C. A. O.
Hernando Morata, J. A.
Herrero, V.
Jones, B.
Labarga, L.
Laing, A.
Lebrun, P.
Liubarsky, I.
Lopez-March, N.
Lorca, D.
Losada, M.
Martin-Albo, J.
Martinez-Lema, G.
Martinez, A.
Monrabal, F.
Monteiro, C. M. B.
Mora, F. J.
Moutinho, L. M.
Nebot-Guinot, M.
Novella, P.
Nygren, D.
Palmeiro, B.
Para, A.
Perez, J.
Querol, M.
JOURNAL OF INSTRUMENTATION, 2017, 12
[3] Background rejection in atmospheric Cherenkov telescopes using recurrent convolutional neural networks
Parsons, R. D.
Ohm, S.
EUROPEAN PHYSICAL JOURNAL C, 2020, 80 (05):
[4] Background rejection in atmospheric Cherenkov telescopes using recurrent convolutional neural networks
R. D. Parsons
S. Ohm
The European Physical Journal C, 2020, 80
[5] Background subtraction based on deep convolutional neural networks features
Dou, Jianfang
Qin, Qin
Tu, Zimei
MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (11) : 14549 - 14571
[6] Background subtraction based on deep convolutional neural networks features
Jianfang Dou
Qin Qin
Zimei Tu
Multimedia Tools and Applications, 2019, 78 : 14549 - 14571
[7] Binarization of music score with complex background by deep convolutional neural networks
Tran, Minh-Trieu
Vo, Quang-Nhat
Lee, Guee-Sang
MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (07) : 11031 - 11047
[8] Deep Background Subtraction with Scene-Specific Convolutional Neural Networks
Braham, Marc
Van Droogenbroeck, Marc
PROCEEDINGS OF THE 23RD INTERNATIONAL CONFERENCE ON SYSTEMS, SIGNALS AND IMAGE PROCESSING, (IWSSIP 2016), 2016, : 113 - 116
[9] Binarization of music score with complex background by deep convolutional neural networks
Minh-Trieu Tran
Quang-Nhat Vo
Guee-Sang Lee
Multimedia Tools and Applications, 2021, 80 : 11031 - 11047
[10] Location Embedding and Deep Convolutional Neural Networks for Next Location Prediction
Sassi, Abdessamed
Brahimi, Mohammed
Bechkit, Walid
Bachir, Abdelmalik
2019 IEEE 44TH LOCAL COMPUTER NETWORKS (LCN) SYMPOSIUM ON EMERGING TOPICS IN NETWORKING (LCN SYMPOSIUM 2019), 2019, : 149 - 157

← 1 2 3 4 5 →