Neural Networks approach to event reconstruction for the GAPS experiment

GAPS Collaboration

Neural Networks approach to event reconstruction for the GAPS experiment

GAPS Collaboration

Advanced Radiation Detection, Imaging, D

Research output: Contribution to journal › Conference article › peer-review

Abstract

The General Antiparticle Spectrometer (GAPS) is a balloon-borne experiment, scheduled for a first flight in the austral summer 2022. It is designed to measure low energy (< 0.25 GeV/n) cosmic antinuclei. A particular focus is on antideuterons, which are predicted to have an ultra-low astrophysical background as compared to signals from dark matter annihilation or decay in the Galactic halo. GAPS uses a novel technique for particle identification based on the formation and decay of exotic atoms. To achieve sufficient rejection power for particle identification, an accurate determination of several fundamental quantities is needed. The precise reconstruction of the energy deposition pattern on the primary track is a particularly intricate problem and we developed a strategy devised to solve this using modern machine learning techniques. In the future, this approach can also be used for particle identification. Here, we present preliminary results of these efforts obtained from simulations.

Original language	English
Article number	099
Journal	Proceedings of Science
Volume	395
State	Published - Mar 18 2022
Event	37th International Cosmic Ray Conference, ICRC 2021 - Virtual, Berlin, Germany Duration: Jul 12 2021 → Jul 23 2021

Funding

This work is supported in the U.S. by NASA APRA grants (NNX17AB44G, NNX17AB45G, NNX17AB46G, and NNX17AB47G) and in Japan by JAXA/ISAS Small Science Program FY2017. P. von Doetinchem received support from the National Science Foundation under award PHY-1551980 . H. Fuke is supported by JSPS KAKENHI grants ( JP17H01136 and JP19H05198 ) and Mitsubishi Foundation Research Grant 2019-10038. K. Perez and M. Xiao are supported by Heising-Simons award 2018-0766. F. Rogers is supported through the National Science Foundation Graduate Research Fellowship under Grant No. 1122374 . Y. Shimizu receives support from JSPS KAKENHI grant JP20K04002 and Sumitomo Foundation Grant No. 180322. This work is supported in Italy by Istituto Nazionale di Fisica Nucleare (INFN) and by the Italian Space Agency through the ASI INFN agreement no. 2018-28-HH.0: “Partecipazione italiana al GAPS -General AntiParticle Spectrometer”. The technical support and advanced computing resources from the University of Hawaii Information Technology Services - Cyberinfrastructure are gratefully acknowledged. This research was done using resources provided by the Open Science Grid [21, 22], which is supported by the National Science Foundation award #2030508.

Cite this

@article{a832e314473243e0abba8e3e57e39981,

title = "Neural Networks approach to event reconstruction for the GAPS experiment",

abstract = "The General Antiparticle Spectrometer (GAPS) is a balloon-borne experiment, scheduled for a first flight in the austral summer 2022. It is designed to measure low energy (< 0.25 GeV/n) cosmic antinuclei. A particular focus is on antideuterons, which are predicted to have an ultra-low astrophysical background as compared to signals from dark matter annihilation or decay in the Galactic halo. GAPS uses a novel technique for particle identification based on the formation and decay of exotic atoms. To achieve sufficient rejection power for particle identification, an accurate determination of several fundamental quantities is needed. The precise reconstruction of the energy deposition pattern on the primary track is a particularly intricate problem and we developed a strategy devised to solve this using modern machine learning techniques. In the future, this approach can also be used for particle identification. Here, we present preliminary results of these efforts obtained from simulations.",

author = "{GAPS Collaboration} and N. Marcelli and T. Aramaki and R. Bird and M. Boezio and Boggs, {S. E.} and V. Bonvicini and D. Campana and Craig, {W. W.} and E. Everson and L. Fabris and H. Fuke and F. Gahbauer and I. Garcia and C. Gerrity and Hailey, {C. J.} and T. Hayashi and C. Kato and A. Kawachi and S. Kobayashi and M. Kozai and A. Lenni and A. Lowell and M. Manghisoni and N. Marcelli and B. Mochizuki and Mognet, {S. A.I.} and K. Munakata and R. Munini and Y. Nakagami and J. Olson and Ong, {R. A.} and G. Osteria and K. Perez and S. Quinn and V. Re and E. Riceputi and B. Roach and F. Rogers and Ryan, {J. A.} and N. Saffold and V. Scotti and Y. Shimizu and M. Sonzogni and R. Sparvoli and A. Stoessl and A. Tiberio and E. Vannuccini and {von Doetinchem}, P. and T. Wada and M. Xiao",

note = "Publisher Copyright: {\textcopyright} Copyright owned by the author(s).; 37th International Cosmic Ray Conference, ICRC 2021 ; Conference date: 12-07-2021 Through 23-07-2021",

year = "2022",

month = mar,

day = "18",

language = "English",

volume = "395",

journal = "Proceedings of Science",

issn = "1824-8039",

publisher = "Sissa Medialab",

}

TY - JOUR

T1 - Neural Networks approach to event reconstruction for the GAPS experiment

AU - GAPS Collaboration

AU - Marcelli, N.

AU - Aramaki, T.

AU - Bird, R.

AU - Boezio, M.

AU - Boggs, S. E.

AU - Bonvicini, V.

AU - Campana, D.

AU - Craig, W. W.

AU - Everson, E.

AU - Fabris, L.

AU - Fuke, H.

AU - Gahbauer, F.

AU - Garcia, I.

AU - Gerrity, C.

AU - Hailey, C. J.

AU - Hayashi, T.

AU - Kato, C.

AU - Kawachi, A.

AU - Kobayashi, S.

AU - Kozai, M.

AU - Lenni, A.

AU - Lowell, A.

AU - Manghisoni, M.

AU - Marcelli, N.

AU - Mochizuki, B.

AU - Mognet, S. A.I.

AU - Munakata, K.

AU - Munini, R.

AU - Nakagami, Y.

AU - Olson, J.

AU - Ong, R. A.

AU - Osteria, G.

AU - Perez, K.

AU - Quinn, S.

AU - Re, V.

AU - Riceputi, E.

AU - Roach, B.

AU - Rogers, F.

AU - Ryan, J. A.

AU - Saffold, N.

AU - Scotti, V.

AU - Shimizu, Y.

AU - Sonzogni, M.

AU - Sparvoli, R.

AU - Stoessl, A.

AU - Tiberio, A.

AU - Vannuccini, E.

AU - von Doetinchem, P.

AU - Wada, T.

AU - Xiao, M.

PY - 2022/3/18

Y1 - 2022/3/18

N2 - The General Antiparticle Spectrometer (GAPS) is a balloon-borne experiment, scheduled for a first flight in the austral summer 2022. It is designed to measure low energy (< 0.25 GeV/n) cosmic antinuclei. A particular focus is on antideuterons, which are predicted to have an ultra-low astrophysical background as compared to signals from dark matter annihilation or decay in the Galactic halo. GAPS uses a novel technique for particle identification based on the formation and decay of exotic atoms. To achieve sufficient rejection power for particle identification, an accurate determination of several fundamental quantities is needed. The precise reconstruction of the energy deposition pattern on the primary track is a particularly intricate problem and we developed a strategy devised to solve this using modern machine learning techniques. In the future, this approach can also be used for particle identification. Here, we present preliminary results of these efforts obtained from simulations.

AB - The General Antiparticle Spectrometer (GAPS) is a balloon-borne experiment, scheduled for a first flight in the austral summer 2022. It is designed to measure low energy (< 0.25 GeV/n) cosmic antinuclei. A particular focus is on antideuterons, which are predicted to have an ultra-low astrophysical background as compared to signals from dark matter annihilation or decay in the Galactic halo. GAPS uses a novel technique for particle identification based on the formation and decay of exotic atoms. To achieve sufficient rejection power for particle identification, an accurate determination of several fundamental quantities is needed. The precise reconstruction of the energy deposition pattern on the primary track is a particularly intricate problem and we developed a strategy devised to solve this using modern machine learning techniques. In the future, this approach can also be used for particle identification. Here, we present preliminary results of these efforts obtained from simulations.

UR - http://www.scopus.com/inward/record.url?scp=85145009850&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85145009850

SN - 1824-8039

VL - 395

JO - Proceedings of Science

JF - Proceedings of Science

M1 - 099

T2 - 37th International Cosmic Ray Conference, ICRC 2021

Y2 - 12 July 2021 through 23 July 2021

ER -

Neural Networks approach to event reconstruction for the GAPS experiment

Abstract

Funding

Other files and links

Fingerprint

Cite this