Improving neutrino energy estimation of charged-current interaction events with recurrent neural networks in MicroBooNE

被引：0

作者：

Abratenko, P. ^{[38
]}

Alterkait, O. ^{[38
]}

Aldana, D. Andrade ^{[15
]}

Arellano, L. ^{[21
]}

Asaadi, J. ^{[37
]}

Ashkenazi, A. ^{[35
]}

Balasubramanian, S. ^{[12
]}

Baller, B. ^{[12
]}

Barnard, A. ^{[28
]}

Barr, G. ^{[28
]}

Barrow, D. ^{[28
]}

Barrow, J. ^{[25
]}

Basque, V. ^{[12
]}

Bateman, J. ^{[21
]}

Rodrigues, O. Benevides ^{[15
]}

Berkman, S. ^{[24
]}

Bhanderi, A. ^{[21
]}

Bhat, A. ^{[7
]}

Bhattacharya, M. ^{[12
]}

Bishai, M. ^{[3
]}

Blake, A. ^{[18
]}

Bogart, B. ^{[23
]}

Bolton, T. ^{[17
]}

Book, J. Y. ^{[14
]}

Brunetti, M. B. ^{[41
]}

Camilleri, L. ^{[10
]}

Cao, Y. ^{[21
]}

Caratelli, D. ^{[4
]}

Cavanna, F. ^{[12
]}

Cerati, G. ^{[12
]}

Chappell, A. ^{[41
]}

Chen, Y. ^{[31
]}

Conrad, J. M. ^{[22
]}

Convery, M. ^{[31
]}

Cooper-Troendle, L. ^{[29
]}

Crespo-Anadon, J. I. ^{[6
]}

Cross, R. ^{[41
]}

Del Tutto, M. ^{[12
]}

Dennis, S. R. ^{[5
]}

Detje, P. ^{[5
]}

Diurba, R. ^{[2
]}

Djurcic, Z. ^{[1
]}

Dorrill, R. ^{[15
]}

Duffy, K. ^{[28
]}

Dytman, S. ^{[29
]}

Eberly, B. ^{[33
]}

Englezos, P. ^{[30
]}

Ereditato, A. ^{[7
,12
]}

Evans, J. J. ^{[21
]}

Fine, R. ^{[19
]}

机构：

[1] Argonne Natl Lab, Lemont, IL 60439 USA

[2] Univ Bern, CH-3012 Bern, Switzerland

[3] Brookhaven Natl Lab, Upton, NY 11973 USA

[4] Univ Calif Santa Barbara, Santa Barbara, CA 93106 USA

[5] Univ Cambridge, Cambridge CB3 0HE, England

[6] Ctr Invest Energet Medioambientales & Technol CIE, E-28040 Madrid, Spain

[7] Univ Chicago, Chicago, IL 60637 USA

[8] Univ Cincinnati, Cincinnati, OH 45221 USA

[9] Colorado State Univ, Ft Collins, CO 80523 USA

[10] Columbia Univ, New York, NY 10027 USA

[11] Univ Edinburgh, Edinburgh EH9 3FD, Midlothian, Scotland

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

[13] Univ Granada, E-18071 Granada, Spain

[14] Harvard Univ, Cambridge, MA 02138 USA

[15] IIT, Chicago, IL 60616 USA

[16] Indiana Univ, Bloomington, IN 47405 USA

[17] Kansas State Univ, Manhattan, KS 66506 USA

[18] Univ Lancaster, Lancaster LA1 4YW, England

[19] Los Alamos Natl Lab, Los Alamos, NM 87545 USA

[20] Louisiana State Univ, Baton Rouge, LA 70803 USA

[21] Univ Manchester, Manchester M13 9PL, Lancs, England

[22] MIT, 77 Massachusetts Ave, Cambridge, MA 02139 USA

[23] Univ Michigan, Ann Arbor, MI 48109 USA

[24] Michigan State Univ, E Lansing, MI 48824 USA

[25] Univ Minnesota, Minneapolis, MN 55455 USA

[26] Nankai Univ, Tianjin 300071, Peoples R China

[27] New Mexico State Univ, Las Cruces, NM 88003 USA

[28] Univ Oxford, Oxford OX1 3RH, England

[29] Univ Pittsburgh, Pittsburgh, PA 15260 USA

[30] Rutgers State Univ, Piscataway, NJ 08854 USA

[31] SLAC Natl Accelerator Lab, Menlo Pk, CA 94025 USA

[32] South Dakota Sch Mines & Technol, Rapid City, SD 57701 USA

[33] Univ Southern Maine, Portland, ME 04104 USA

[34] Syracuse Univ, Syracuse, NY 13244 USA

[35] Tel Aviv Univ, IL-69978 Tel Aviv, Israel

[36] Univ Tennessee, Knoxville, TN 37996 USA

[37] Univ Texas Arlington, Arlington, TX 76019 USA

[38] Tufts Univ, Medford, MA 02155 USA

[39] UCL, London WC1E 6BT, England

[40] Virginia Tech, Ctr Neutrino Phys, Blacksburg, VA 24061 USA

[41] Univ Warwick, Coventry CV4 7AL, W Midlands, England

[42] Yale Univ, Dept Phys, Wright Lab, New Haven, CT 06520 USA

来源：

PHYSICAL REVIEW D | 2024年 / 110卷 / 09期

基金：

英国科学技术设施理事会; 美国国家科学基金会; 瑞士国家科学基金会; 英国科研创新办公室;

关键词：

SCATTERING;

D O I：

10.1103/PhysRevD.110.092010

中图分类号：

P1 [天文学];

学科分类号：

0704 ;

摘要：

We present a deep learning-based method for estimating the neutrino energy of charged-current neutrino-argon interactions. We employ a recurrent neural network (RNN) architecture for neutrino energy estimation in the MicroBooNE experiment, utilizing liquid argon time projection chamber (LArTPC) detector technology. Traditional energy estimation approaches in LArTPCs, which largely rely on reconstructing and summing visible energies, often experience sizable biases and resolution smearing because of the complex nature of neutrino interactions and the detector response. The estimation of neutrino energy can be improved after considering the kinematics information of reconstructed final-state particles. Utilizing kinematic information of reconstructed particles, the deep learning-based approach shows improved resolution and reduced bias for the muon neutrino Monte Carlo simulation sample compared to the traditional approach. In order to address the common concern about the effectiveness of this method on experimental data, the RNN-based energy estimator is further examined and validated with dedicated data-simulation consistency tests using MicroBooNE data. We also assess its potential impact on a neutrino oscillation study after accounting for all statistical and systematic uncertainties and show that it enhances physics sensitivity. This method has good potential to improve the performance of other physics analyses.

引用

页数：19

共 46 条

[41] A method for the detection of neutrino oscillations in a long-baseline experiment using energy measurements of nu(mu) charged current events
Cobb, JH
NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 1996, 372 (03): : 501 - 514
[42] First measurement of muon neutrino charged-current interactions on hydrocarbon without pions in the final state using multiple detectors with correlated energy spectra at T2K
Abe, K.
Akhlaq, N.
Akutsu, R.
Alarakia-Charles, H.
Ali, A.
Hakim, Y. I. Alj
Monsalve, S. Alonso
Alt, C.
Andreopoulos, C.
Antonova, M.
Aoki, S.
Arihara, T.
Asada, Y.
Ashida, Y.
Atkin, E. T.
Barbi, M.
Barker, G. J.
Barr, G.
Barrow, D.
Batkiewicz-Kwasniak, M.
Bench, F.
Berardi, V.
Berns, L.
Bhadra, S.
Blanchet, A.
Blondel, A.
Bolognesi, S.
Bonus, T.
Bordoni, S.
Boyd, S. B.
Bravar, A.
Bronner, C.
Bron, S.
Bubak, A.
Avanzini, M. Buizza
Caballero, J. A.
Calabria, N. F.
Cao, S.
Carabadjac, D.
Carter, A. J.
Cartwright, S. L.
Casado, M. P.
Catanesi, M. G.
Cervera, A.
Chakrani, J.
Cherdack, D.
Chong, P. S.
Christodoulou, G.
Chvirova, A.
Cicerchia, M.
PHYSICAL REVIEW D, 2023, 108 (11)
[43] Investigating Current-Based and Gating Approaches for Accurate and Energy-Efficient Spiking Recurrent Neural Networks
Dampfhoffer, Manon
Mesquida, Thomas
Valentian, Alexandre
Anghel, Lorena
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2022, PT III, 2022, 13531 : 359 - 370
[44] Measurements of (ν)over-barμ and (ν)over-barμ + νμ charged-current cross-sections without detected pions or protons on water and hydrocarbon at a mean anti-neutrino energy of 0.86 GeV
Abe, K.
Akhlaq, N.
Akutsu, R.
Ali, A.
Alt, C.
Andreopoulos, C.
Anthony, L.
Antonova, M.
Aoki, S.
Ariga, A.
Arihara, T.
Asada, Y.
Ashida, Y.
Atkin, E. T.
Awataguchi, Y.
Ban, S.
Barbi, M.
Barker, G. J.
Barr, G.
Barrow, D.
Barry, C.
Batkiewicz-Kwasniak, M.
Beloshapkin, A.
Bench, F.
Berardi, V
Berkman, S.
Berns, L.
Bhadra, S.
Bienstock, S.
Blanchet, A.
Blondel, A.
Bolognesi, S.
Bonus, T.
Bourguille, B.
Boyd, S. B.
Brailsford, D.
Bravar, A.
Berguno, D. Bravo
Bronner, C.
Bron, S.
Bubak, A.
Avanzini, M. Buizza
Calcutt, J.
Campbell, T.
Cao, S.
Cartwright, S. L.
Catanesi, M. G.
Cervera, A.
Chappell, A.
Checchia, C.
PROGRESS OF THEORETICAL AND EXPERIMENTAL PHYSICS, 2021, 2021 (04):
[45] Lithium-Ion Battery State-of-Charge and State-of-Energy Simultaneous Estimation via Sparse- Quasi Recurrent Neural Networks(S-QRNN)
Sharma, Sakshi
Panigrahi, Bijaya Ketan
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2025, 61 (01) : 774 - 783
[46] Study of the Neutrino-Oxygen Cross Sections of the Charged-Current Reaction 16O((ν)over-bare, e+)16N(0 MeV, 2-) and the Neutral-Current Reaction 16O(ν, ν′)16O(12.97/12.53 MeV, 2-), Producing High-Energy γ Rays
Sakuda, Makoto
Suzuki, Toshio
Nakazato, Ken'ichiro
Suzuki, Hideyuki
PROGRESS OF THEORETICAL AND EXPERIMENTAL PHYSICS, 2024, 2024 (10):

← 1 2 3 4 5 →