Citation

BibTex format

@article{Abratenko:2024:10.1103/PhysRevD.110.092010,
author = {Abratenko, P and Alterkait, O and Andrade, Aldana D and Arellano, L and Asaadi, J and Ashkenazi, A and Balasubramanian, S and Baller, B and Barnard, A and Barr, G and Barrow, D and Barrow, J and Basque, V and Bateman, J and Benevides, Rodrigues O and Berkman, S and Bhanderi, A and Bhat, A and Bhattacharya, M and Bishai, M and Blake, A and Bogart, B and Bolton, T and Book, JY and Brunetti, MB and Camilleri, L and Cao, Y and Caratelli, D and Cavanna, F and Cerati, G and Chappell, A and Chen, Y and Conrad, JM and Convery, M and Cooper-Troendle, L and Crespo-Anadón, JI and Cross, R and Del, Tutto M and Dennis, SR and Detje, P and Diurba, R and Djurcic, Z and Dorrill, R and Duffy, K and Dytman, S and Eberly, B and Englezos, P and Ereditato, A and Evans, JJ and Fine, R and Foreman, W and Fleming, BT and Franco, D and Furmanski, AP and Gao, F and Garcia-Gamez, D and Gardiner, S and Ge, G and Gollapinni, S and Gramellini, E and Green, P and Greenlee, H and Gu, L and Gu, W and Guenette, R and G},
doi = {10.1103/PhysRevD.110.092010},
journal = {Physical Review D},
title = {Improving neutrino energy estimation of charged-current interaction events with recurrent neural networks in MicroBooNE},
url = {http://dx.doi.org/10.1103/PhysRevD.110.092010},
volume = {110},
year = {2024}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - 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.
AU  - Abratenko,P
AU  - Alterkait,O
AU  - Andrade,Aldana D
AU  - Arellano,L
AU  - Asaadi,J
AU  - Ashkenazi,A
AU  - Balasubramanian,S
AU  - Baller,B
AU  - Barnard,A
AU  - Barr,G
AU  - Barrow,D
AU  - Barrow,J
AU  - Basque,V
AU  - Bateman,J
AU  - Benevides,Rodrigues O
AU  - Berkman,S
AU  - Bhanderi,A
AU  - Bhat,A
AU  - Bhattacharya,M
AU  - Bishai,M
AU  - Blake,A
AU  - Bogart,B
AU  - Bolton,T
AU  - Book,JY
AU  - Brunetti,MB
AU  - Camilleri,L
AU  - Cao,Y
AU  - Caratelli,D
AU  - Cavanna,F
AU  - Cerati,G
AU  - Chappell,A
AU  - Chen,Y
AU  - Conrad,JM
AU  - Convery,M
AU  - Cooper-Troendle,L
AU  - Crespo-Anadón,JI
AU  - Cross,R
AU  - Del,Tutto M
AU  - Dennis,SR
AU  - Detje,P
AU  - Diurba,R
AU  - Djurcic,Z
AU  - Dorrill,R
AU  - Duffy,K
AU  - Dytman,S
AU  - Eberly,B
AU  - Englezos,P
AU  - Ereditato,A
AU  - Evans,JJ
AU  - Fine,R
AU  - Foreman,W
AU  - Fleming,BT
AU  - Franco,D
AU  - Furmanski,AP
AU  - Gao,F
AU  - Garcia-Gamez,D
AU  - Gardiner,S
AU  - Ge,G
AU  - Gollapinni,S
AU  - Gramellini,E
AU  - Green,P
AU  - Greenlee,H
AU  - Gu,L
AU  - Gu,W
AU  - Guenette,R
AU  - Guzowski,P
AU  - Hagaman,L
AU  - Hen,O
AU  - Hilgenberg,C
AU  - Horton-Smith,GA
AU  - Imani,Z
AU  - Irwin,B
AU  - Ismail,MS
AU  - James,C
AU  - Ji,X
AU  - Jo,JH
AU  - Johnson,RA
AU  - Jwa,YJ
AU  - Kalra,D
AU  - Kamp,N
AU  - Karagiorgi,G
AU  - Ketchum,W
AU  - Kirby,M
AU  - Kobilarcik,T
AU  - Kreslo,I
AU  - Lane,N
AU  - Lepetic,I
AU  - Li,JY
AU  - Li,Y
AU  - Lin,K
AU  - Littlejohn,BR
AU  - Liu,H
AU  - Louis,WC
AU  - Luo,X
AU  - Mariani,C
AU  - Marsden,D
AU  - Marshall,J
AU  - Martinez,N
AU  - Martinez,Caicedo DA
AU  - Martynenko,S
DO  - 10.1103/PhysRevD.110.092010
PY  - 2024///
SN  - 2470-0010
TI  - Improving neutrino energy estimation of charged-current interaction events with recurrent neural networks in MicroBooNE
T2  - Physical Review D
UR  - http://dx.doi.org/10.1103/PhysRevD.110.092010
VL  - 110
ER  -
Download