Neutral pion reconstruction using machine learning in the MINERvA experiment at 〈Ev〉 ∼ 6GeV

A. Ghosh; B. Yaeggy; R. Galindo; Zubair Ahmad Dar; F. Akbar; M. Ascencio; A. Bashyal; A. Bercellie; J. L. Bonilla; G. F.R.V. Caceres; T. Cai; M. F. Carneiro; H. Da Motta; G. A. Díaz; J. Felix; A. Filkins; R. Fine; A. Gago; T. Golan; R. Gran; D. A. Harris; S. Henry; S. Jena; D. Jena; J. Kleykamp; M. Kordosky; D. Last; T. Le; A. Lozano; X. G. Lu; E. Maher; S. Manly; W. A. Mann; C. Mauger; K. S. McFarland; B. Messerly; J. Miller; L. M. Montano; D. Naples; J. K. Nelson; C. Nguyen; A. Olivier; V. Paolone; G. N. Perdue; M. A. Ramirez; H. Ray; D. Ruterbories; C. J.Solano Salinas; H. Su; M. Sultana; V. S. Syrotenko; E. Valencia; M. Wospakrik; C. Wret; K. Yang; L. Zazueta

Neutral pion reconstruction using machine learning in the MINERvA experiment at 〈Ev〉 ∼ 6GeV

A. Ghosh, B. Yaeggy, R. Galindo, Zubair Ahmad Dar, F. Akbar, M. Ascencio, A. Bashyal, A. Bercellie, J. L. Bonilla, G. F.R.V. Caceres, T. Cai, M. F. Carneiro, H. Da Motta, G. A. Díaz, J. Felix, A. Filkins, R. Fine, A. Gago, T. Golan, R. GranD. A. Harris, S. Henry, S. Jena, D. Jena, J. Kleykamp, M. Kordosky, D. Last, T. Le, A. Lozano, X. G. Lu, E. Maher, S. Manly, W. A. Mann, C. Mauger, K. S. McFarland, B. Messerly, J. Miller, L. M. Montano, D. Naples, J. K. Nelson, C. Nguyen, A. Olivier, V. Paolone, G. N. Perdue, M. A. Ramirez, H. Ray, D. Ruterbories, C. J.Solano Salinas, H. Su, M. Sultana, V. S. Syrotenko, E. Valencia, M. Wospakrik, C. Wret, K. Yang, L. Zazueta

Producción científica: Contribución a una revista › Artículo › revisión exhaustiva

Resumen

This paper presents a novel neutral-pion reconstruction that takes advantage of the machine learning technique of semantic segmentation using MINERvA data collected between 2013-2017, with an average neutrino energy of 6 GeV. Semantic segmentation improves the purity of neutral pion reconstruction from two γs from 70.7 ± 0.9% to 89.3 ± 0.7% and improves the efficiency of the reconstruction by approximately 40%. We demonstrate our method in a charged current neutral pion production analysis where a single neutral pion is reconstructed. This technique is applicable to modern tracking calorimeters, such as the new generation of liquid-argon time projection chambers, exposed to neutrino beams with 〈Ev〉 between 1-10 GeV. In such experiments it can facilitate the identification of ionization hits which are associated with electromagnetic showers, thereby enabling improved reconstruction of charged-current ve events arising from vμ → ve appearance.

Idioma original	Español
Publicación	Journal of Instrumentation
Volumen	16
Estado	Publicada - 1 jul. 2021

Citar esto

Ghosh, A., Yaeggy, B., Galindo, R., Dar, Z. A., Akbar, F., Ascencio, M., Bashyal, A., Bercellie, A., Bonilla, J. L., Caceres, G. F. R. V., Cai, T., Carneiro, M. F., Da Motta, H., Díaz, G. A., Felix, J., Filkins, A., Fine, R., Gago, A., Golan, T., ... Zazueta, L. (2021). Neutral pion reconstruction using machine learning in the MINERvA experiment at 〈Ev〉 ∼ 6GeV. Journal of Instrumentation, 16.

@article{35d27d93143848f084241479a151b2ee,

title = "Neutral pion reconstruction using machine learning in the MINERvA experiment at 〈Ev〉 ∼ 6GeV",

abstract = "This paper presents a novel neutral-pion reconstruction that takes advantage of the machine learning technique of semantic segmentation using MINERvA data collected between 2013-2017, with an average neutrino energy of 6 GeV. Semantic segmentation improves the purity of neutral pion reconstruction from two γs from 70.7 ± 0.9% to 89.3 ± 0.7% and improves the efficiency of the reconstruction by approximately 40%. We demonstrate our method in a charged current neutral pion production analysis where a single neutral pion is reconstructed. This technique is applicable to modern tracking calorimeters, such as the new generation of liquid-argon time projection chambers, exposed to neutrino beams with 〈Ev〉 between 1-10 GeV. In such experiments it can facilitate the identification of ionization hits which are associated with electromagnetic showers, thereby enabling improved reconstruction of charged-current ve events arising from vμ → ve appearance.",

author = "A. Ghosh and B. Yaeggy and R. Galindo and Dar, {Zubair Ahmad} and F. Akbar and M. Ascencio and A. Bashyal and A. Bercellie and Bonilla, {J. L.} and Caceres, {G. F.R.V.} and T. Cai and Carneiro, {M. F.} and {Da Motta}, H. and D{\'i}az, {G. A.} and J. Felix and A. Filkins and R. Fine and A. Gago and T. Golan and R. Gran and Harris, {D. A.} and S. Henry and S. Jena and D. Jena and J. Kleykamp and M. Kordosky and D. Last and T. Le and A. Lozano and Lu, {X. G.} and E. Maher and S. Manly and Mann, {W. A.} and C. Mauger and McFarland, {K. S.} and B. Messerly and J. Miller and Montano, {L. M.} and D. Naples and Nelson, {J. K.} and C. Nguyen and A. Olivier and V. Paolone and Perdue, {G. N.} and Ramirez, {M. A.} and H. Ray and D. Ruterbories and Salinas, {C. J.Solano} and H. Su and M. Sultana and Syrotenko, {V. S.} and E. Valencia and M. Wospakrik and C. Wret and K. Yang and L. Zazueta",

year = "2021",

month = jul,

day = "1",

language = "Espa{\~n}ol",

volume = "16",

journal = "Journal of Instrumentation",

issn = "1748-0221",

}

Ghosh, A, Yaeggy, B, Galindo, R, Dar, ZA, Akbar, F, Ascencio, M, Bashyal, A, Bercellie, A, Bonilla, JL, Caceres, GFRV, Cai, T, Carneiro, MF, Da Motta, H, Díaz, GA, Felix, J, Filkins, A, Fine, R, Gago, A, Golan, T, Gran, R, Harris, DA, Henry, S, Jena, S, Jena, D, Kleykamp, J, Kordosky, M, Last, D, Le, T, Lozano, A, Lu, XG, Maher, E, Manly, S, Mann, WA, Mauger, C, McFarland, KS, Messerly, B, Miller, J, Montano, LM, Naples, D, Nelson, JK, Nguyen, C, Olivier, A, Paolone, V, Perdue, GN, Ramirez, MA, Ray, H, Ruterbories, D, Salinas, CJS, Su, H, Sultana, M, Syrotenko, VS, Valencia, E, Wospakrik, M, Wret, C, Yang, K & Zazueta, L 2021, 'Neutral pion reconstruction using machine learning in the MINERvA experiment at 〈Ev〉 ∼ 6GeV', Journal of Instrumentation, vol. 16.

TY - JOUR

T1 - Neutral pion reconstruction using machine learning in the MINERvA experiment at 〈Ev〉 ∼ 6GeV

AU - Ghosh, A.

AU - Yaeggy, B.

AU - Galindo, R.

AU - Dar, Zubair Ahmad

AU - Akbar, F.

AU - Ascencio, M.

AU - Bashyal, A.

AU - Bercellie, A.

AU - Bonilla, J. L.

AU - Caceres, G. F.R.V.

AU - Cai, T.

AU - Carneiro, M. F.

AU - Da Motta, H.

AU - Díaz, G. A.

AU - Felix, J.

AU - Filkins, A.

AU - Fine, R.

AU - Gago, A.

AU - Golan, T.

AU - Gran, R.

AU - Harris, D. A.

AU - Henry, S.

AU - Jena, S.

AU - Jena, D.

AU - Kleykamp, J.

AU - Kordosky, M.

AU - Last, D.

AU - Le, T.

AU - Lozano, A.

AU - Lu, X. G.

AU - Maher, E.

AU - Manly, S.

AU - Mann, W. A.

AU - Mauger, C.

AU - McFarland, K. S.

AU - Messerly, B.

AU - Miller, J.

AU - Montano, L. M.

AU - Naples, D.

AU - Nelson, J. K.

AU - Nguyen, C.

AU - Olivier, A.

AU - Paolone, V.

AU - Perdue, G. N.

AU - Ramirez, M. A.

AU - Ray, H.

AU - Ruterbories, D.

AU - Salinas, C. J.Solano

AU - Su, H.

AU - Sultana, M.

AU - Syrotenko, V. S.

AU - Valencia, E.

AU - Wospakrik, M.

AU - Wret, C.

AU - Yang, K.

AU - Zazueta, L.

PY - 2021/7/1

Y1 - 2021/7/1

N2 - This paper presents a novel neutral-pion reconstruction that takes advantage of the machine learning technique of semantic segmentation using MINERvA data collected between 2013-2017, with an average neutrino energy of 6 GeV. Semantic segmentation improves the purity of neutral pion reconstruction from two γs from 70.7 ± 0.9% to 89.3 ± 0.7% and improves the efficiency of the reconstruction by approximately 40%. We demonstrate our method in a charged current neutral pion production analysis where a single neutral pion is reconstructed. This technique is applicable to modern tracking calorimeters, such as the new generation of liquid-argon time projection chambers, exposed to neutrino beams with 〈Ev〉 between 1-10 GeV. In such experiments it can facilitate the identification of ionization hits which are associated with electromagnetic showers, thereby enabling improved reconstruction of charged-current ve events arising from vμ → ve appearance.

AB - This paper presents a novel neutral-pion reconstruction that takes advantage of the machine learning technique of semantic segmentation using MINERvA data collected between 2013-2017, with an average neutrino energy of 6 GeV. Semantic segmentation improves the purity of neutral pion reconstruction from two γs from 70.7 ± 0.9% to 89.3 ± 0.7% and improves the efficiency of the reconstruction by approximately 40%. We demonstrate our method in a charged current neutral pion production analysis where a single neutral pion is reconstructed. This technique is applicable to modern tracking calorimeters, such as the new generation of liquid-argon time projection chambers, exposed to neutrino beams with 〈Ev〉 between 1-10 GeV. In such experiments it can facilitate the identification of ionization hits which are associated with electromagnetic showers, thereby enabling improved reconstruction of charged-current ve events arising from vμ → ve appearance.

M3 - Artículo

SN - 1748-0221

VL - 16

JO - Journal of Instrumentation

JF - Journal of Instrumentation

ER -