Background rejection in NEXT using deep neural networks

J. Renner; A. Farbin; J. Muñoz Vidal; J. M. Benlloch-Rodríguez; A. Botas; P. Ferrario; J. J. Gómez-Cadenas; V. Álvarez; C. D.R. Azevedo; F. I.G. Borges; S. Cárcel; J. V. Carrión; S. Cebrián; A. Cervera; C. A.N. Conde; J. Díaz; M. Diesburg; R. Esteve; L. M.P. Fernandes; A. L. Ferreira; E. D.C. Freitas; A. Goldschmidt; D. González-Díaz; R. M. Gutiérrez; J. Hauptman; C. A.O. Henriques; J. A.Hernando Morata; V. Herrero; B. Jones; L. Labarga; A. Laing; P. Lebrun; I. Liubarsky; N. López-March; D. Lorca; M. Losada; J. Martín-Albo; G. Martínez-Lema; A. Martínez; F. Monrabal; C. M.B. Monteiro; F. J. Mora; L. M. Moutinho; M. Nebot-Guinot; P. Novella; D. Nygren; B. Palmeiro; A. Para; J. Pérez; M. Querol; L. Ripoll; J. Rodríguez; F. P. Santos; J. M.F. Dos Santos; L. Serra; D. Shuman; A. Simón; C. Sofka; M. Sorel; J. F. Toledo; J. Torrent; Z. Tsamalaidze; J. F.C.A. Veloso; J. White; R. Webb; N. Yahlali; H. Yepes-Ramírez

doi:10.1088/1748-0221/12/01/T01004

Background rejection in NEXT using deep neural networks

J. Renner, A. Farbin, J. Muñoz Vidal, J. M. Benlloch-Rodríguez, A. Botas, P. Ferrario, J. J. Gómez-Cadenas, V. Álvarez, C. D.R. Azevedo, F. I.G. Borges, S. Cárcel, J. V. Carrión, S. Cebrián, A. Cervera, C. A.N. Conde, J. Díaz, M. Diesburg, R. Esteve, L. M.P. Fernandes, A. L. FerreiraE. D.C. Freitas, A. Goldschmidt, D. González-Díaz, R. M. Gutiérrez, J. Hauptman, C. A.O. Henriques, J. A.Hernando Morata, V. Herrero, B. Jones, L. Labarga, A. Laing, P. Lebrun, I. Liubarsky, N. López-March, D. Lorca, M. Losada, J. Martín-Albo, G. Martínez-Lema, A. Martínez, F. Monrabal, C. M.B. Monteiro, F. J. Mora, L. M. Moutinho, M. Nebot-Guinot, P. Novella, D. Nygren, B. Palmeiro, A. Para, J. Pérez, M. Querol, L. Ripoll, J. Rodríguez, F. P. Santos, J. M.F. Dos Santos, L. Serra, D. Shuman, A. Simón, C. Sofka, M. Sorel, J. F. Toledo, J. Torrent, Z. Tsamalaidze, J. F.C.A. Veloso, J. White, R. Webb, N. Yahlali, H. Yepes-Ramírez

Physics

Research output: Contribution to journal › Article › peer-review

Abstract

We investigate the potential of using deep learning techniques to reject background events in searches for neutrinoless double beta decay with high pressure xenon time projection chambers capable of detailed track reconstruction. The differences in the topological signatures of background and signal events can be learned by deep neural networks via training over many thousands of events. These networks can then be used to classify further events as signal or background, providing an additional background rejection factor at an acceptable loss of efficiency. The networks trained in this study performed better than previous methods developed based on the use of the same topological signatures by a factor of 1.2 to 1.6, and there is potential for further improvement.

Original language	English (US)
Article number	T01004
Journal	Journal of Instrumentation
Volume	12
Issue number	1
DOIs	https://doi.org/10.1088/1748-0221/12/01/T01004
State	Published - Jan 16 2017

Keywords

Analysis and statistical methods
Double-beta decay detectors
Pattern recognition
Time projection chambers
calibration and fitting methods
cluster finding

ASJC Scopus subject areas

Instrumentation
Mathematical Physics

Access to Document

10.1088/1748-0221/12/01/T01004

Cite this

Renner, J., Farbin, A., Vidal, J. M., Benlloch-Rodríguez, J. M., Botas, A., Ferrario, P., Gómez-Cadenas, J. J., Álvarez, V., Azevedo, C. D. R., Borges, F. I. G., Cárcel, S., Carrión, J. V., Cebrián, S., Cervera, A., Conde, C. A. N., Díaz, J., Diesburg, M., Esteve, R., Fernandes, L. M. P., ... Yepes-Ramírez, H. (2017). Background rejection in NEXT using deep neural networks. Journal of Instrumentation, 12(1), Article T01004. https://doi.org/10.1088/1748-0221/12/01/T01004

Renner, J, Farbin, A, Vidal, JM, Benlloch-Rodríguez, JM, Botas, A, Ferrario, P, Gómez-Cadenas, JJ, Álvarez, V, Azevedo, CDR, Borges, FIG, Cárcel, S, Carrión, JV, Cebrián, S, Cervera, A, Conde, CAN, Díaz, J, Diesburg, M, Esteve, R, Fernandes, LMP, Ferreira, AL, Freitas, EDC, Goldschmidt, A, González-Díaz, D, Gutiérrez, RM, Hauptman, J, Henriques, CAO, Morata, JAH, Herrero, V, Jones, B, Labarga, L, Laing, A, Lebrun, P, Liubarsky, I, López-March, N, Lorca, D, Losada, M, Martín-Albo, J, Martínez-Lema, G, Martínez, A, Monrabal, F, Monteiro, CMB, Mora, FJ, Moutinho, LM, Nebot-Guinot, M, Novella, P, Nygren, D, Palmeiro, B, Para, A, Pérez, J, Querol, M, Ripoll, L, Rodríguez, J, Santos, FP, Dos Santos, JMF, Serra, L, Shuman, D, Simón, A, Sofka, C, Sorel, M, Toledo, JF, Torrent, J, Tsamalaidze, Z, Veloso, JFCA, White, J, Webb, R, Yahlali, N & Yepes-Ramírez, H 2017, 'Background rejection in NEXT using deep neural networks', Journal of Instrumentation, vol. 12, no. 1, T01004. https://doi.org/10.1088/1748-0221/12/01/T01004

@article{487677a942c0434fa3f19a46150e0f4a,

title = "Background rejection in NEXT using deep neural networks",

abstract = "We investigate the potential of using deep learning techniques to reject background events in searches for neutrinoless double beta decay with high pressure xenon time projection chambers capable of detailed track reconstruction. The differences in the topological signatures of background and signal events can be learned by deep neural networks via training over many thousands of events. These networks can then be used to classify further events as signal or background, providing an additional background rejection factor at an acceptable loss of efficiency. The networks trained in this study performed better than previous methods developed based on the use of the same topological signatures by a factor of 1.2 to 1.6, and there is potential for further improvement.",

keywords = "Analysis and statistical methods, Double-beta decay detectors, Pattern recognition, Time projection chambers, calibration and fitting methods, cluster finding",

author = "J. Renner and A. Farbin and Vidal, {J. Mu{\~n}oz} and Benlloch-Rodr{\'i}guez, {J. M.} and A. Botas and P. Ferrario and G{\'o}mez-Cadenas, {J. J.} and V. {\'A}lvarez and Azevedo, {C. D.R.} and Borges, {F. I.G.} and S. C{\'a}rcel and Carri{\'o}n, {J. V.} and S. Cebri{\'a}n and A. Cervera and Conde, {C. A.N.} and J. D{\'i}az and M. Diesburg and R. Esteve and Fernandes, {L. M.P.} and Ferreira, {A. L.} and Freitas, {E. D.C.} and A. Goldschmidt and D. Gonz{\'a}lez-D{\'i}az and Guti{\'e}rrez, {R. M.} and J. Hauptman and Henriques, {C. A.O.} and Morata, {J. A.Hernando} and V. Herrero and B. Jones and L. Labarga and A. Laing and P. Lebrun and I. Liubarsky and N. L{\'o}pez-March and D. Lorca and M. Losada and J. Mart{\'i}n-Albo and G. Mart{\'i}nez-Lema and A. Mart{\'i}nez and F. Monrabal and Monteiro, {C. M.B.} and Mora, {F. J.} and Moutinho, {L. M.} and M. Nebot-Guinot and P. Novella and D. Nygren and B. Palmeiro and A. Para and J. P{\'e}rez and M. Querol and L. Ripoll and J. Rodr{\'i}guez and Santos, {F. P.} and {Dos Santos}, {J. M.F.} and L. Serra and D. Shuman and A. Sim{\'o}n and C. Sofka and M. Sorel and Toledo, {J. F.} and J. Torrent and Z. Tsamalaidze and Veloso, {J. F.C.A.} and J. White and R. Webb and N. Yahlali and H. Yepes-Ram{\'i}rez",

note = "Publisher Copyright: {\textcopyright} CERN 2017.",

year = "2017",

month = jan,

day = "16",

doi = "10.1088/1748-0221/12/01/T01004",

language = "English (US)",

volume = "12",

journal = "Journal of Instrumentation",

issn = "1748-0221",

publisher = "IOP Publishing Ltd.",

number = "1",

}

TY - JOUR

T1 - Background rejection in NEXT using deep neural networks

AU - Renner, J.

AU - Farbin, A.

AU - Vidal, J. Muñoz

AU - Benlloch-Rodríguez, J. M.

AU - Botas, A.

AU - Ferrario, P.

AU - Gómez-Cadenas, J. J.

AU - Álvarez, V.

AU - Azevedo, C. D.R.

AU - Borges, F. I.G.

AU - Cárcel, S.

AU - Carrión, J. V.

AU - Cebrián, S.

AU - Cervera, A.

AU - Conde, C. A.N.

AU - Díaz, J.

AU - Diesburg, M.

AU - Esteve, R.

AU - Fernandes, L. M.P.

AU - Ferreira, A. L.

AU - Freitas, E. D.C.

AU - Goldschmidt, A.

AU - González-Díaz, D.

AU - Gutiérrez, R. M.

AU - Hauptman, J.

AU - Henriques, C. A.O.

AU - Morata, J. A.Hernando

AU - Herrero, V.

AU - Jones, B.

AU - Labarga, L.

AU - Laing, A.

AU - Lebrun, P.

AU - Liubarsky, I.

AU - López-March, N.

AU - Lorca, D.

AU - Losada, M.

AU - Martín-Albo, J.

AU - Martínez-Lema, G.

AU - Martínez, A.

AU - Monrabal, F.

AU - Monteiro, C. M.B.

AU - Mora, F. J.

AU - Moutinho, L. M.

AU - Nebot-Guinot, M.

AU - Novella, P.

AU - Nygren, D.

AU - Palmeiro, B.

AU - Para, A.

AU - Pérez, J.

AU - Querol, M.

AU - Ripoll, L.

AU - Rodríguez, J.

AU - Santos, F. P.

AU - Dos Santos, J. M.F.

AU - Serra, L.

AU - Shuman, D.

AU - Simón, A.

AU - Sofka, C.

AU - Sorel, M.

AU - Toledo, J. F.

AU - Torrent, J.

AU - Tsamalaidze, Z.

AU - Veloso, J. F.C.A.

AU - White, J.

AU - Webb, R.

AU - Yahlali, N.

AU - Yepes-Ramírez, H.

PY - 2017/1/16

Y1 - 2017/1/16

N2 - We investigate the potential of using deep learning techniques to reject background events in searches for neutrinoless double beta decay with high pressure xenon time projection chambers capable of detailed track reconstruction. The differences in the topological signatures of background and signal events can be learned by deep neural networks via training over many thousands of events. These networks can then be used to classify further events as signal or background, providing an additional background rejection factor at an acceptable loss of efficiency. The networks trained in this study performed better than previous methods developed based on the use of the same topological signatures by a factor of 1.2 to 1.6, and there is potential for further improvement.

AB - We investigate the potential of using deep learning techniques to reject background events in searches for neutrinoless double beta decay with high pressure xenon time projection chambers capable of detailed track reconstruction. The differences in the topological signatures of background and signal events can be learned by deep neural networks via training over many thousands of events. These networks can then be used to classify further events as signal or background, providing an additional background rejection factor at an acceptable loss of efficiency. The networks trained in this study performed better than previous methods developed based on the use of the same topological signatures by a factor of 1.2 to 1.6, and there is potential for further improvement.

KW - Analysis and statistical methods

KW - Double-beta decay detectors

KW - Pattern recognition

KW - Time projection chambers

KW - calibration and fitting methods

KW - cluster finding

UR - http://www.scopus.com/inward/record.url?scp=85012054803&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85012054803&partnerID=8YFLogxK

U2 - 10.1088/1748-0221/12/01/T01004

DO - 10.1088/1748-0221/12/01/T01004

M3 - Article

AN - SCOPUS:85012054803

SN - 1748-0221

VL - 12

JO - Journal of Instrumentation

JF - Journal of Instrumentation

IS - 1

M1 - T01004

ER -

Background rejection in NEXT using deep neural networks

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this