Software compensation for highly granular calorimeters using machine learning

The CALICE Collaboration

doi:10.1088/1748-0221/19/04/P04037

Software compensation for highly granular calorimeters using machine learning

The CALICE Collaboration

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

Abstract

A neural network for software compensation was developed for the highly granular CALICE Analogue Hadronic Calorimeter (AHCAL). The neural network uses spatial and temporal event information from the AHCAL and energy information, which is expected to improve sensitivity to shower development and the neutron fraction of the hadron shower. The neural network method produced a depth-dependent energy weighting and a time-dependent threshold for enhancing energy deposits consistent with the timescale of evaporation neutrons. Additionally, it was observed to learn an energy-weighting indicative of longitudinal leakage correction. In addition, the method produced a linear detector response and outperformed a published control method regarding resolution for every particle energy studied.

Original language	English
Article number	P04037
Journal	Journal of Instrumentation
Volume	19
Issue number	4
DOIs	https://doi.org/10.1088/1748-0221/19/04/P04037
Publication status	Published - 1 Apr 2024

Keywords

Large detector-systems performance
Pattern recognition, cluster finding, calibration and fitting methods
Performance of High Energy Physics Detectors

Access to Document

10.1088/1748-0221/19/04/P04037

Cite this

@article{5c1440e08f7c40d49c2c00616493657c,

title = "Software compensation for highly granular calorimeters using machine learning",

abstract = "A neural network for software compensation was developed for the highly granular CALICE Analogue Hadronic Calorimeter (AHCAL). The neural network uses spatial and temporal event information from the AHCAL and energy information, which is expected to improve sensitivity to shower development and the neutron fraction of the hadron shower. The neural network method produced a depth-dependent energy weighting and a time-dependent threshold for enhancing energy deposits consistent with the timescale of evaporation neutrons. Additionally, it was observed to learn an energy-weighting indicative of longitudinal leakage correction. In addition, the method produced a linear detector response and outperformed a published control method regarding resolution for every particle energy studied.",

keywords = "Large detector-systems performance, Pattern recognition, cluster finding, calibration and fitting methods, Performance of High Energy Physics Detectors",

author = "\{The CALICE Collaboration\} and S. Lai and J. Utehs and A. Wilhahn and O. Bach and E. Brianne and A. Ebrahimi and K. Gadow and P. G{\"o}ttlicher and O. Hartbrich and D. Heuchel and A. Irles and K. Kr{\"u}ger and J. Kvasnicka and S. Lu and C. Neub{\"u}ser and A. Provenza and M. Reinecke and F. Sefkow and S. Schuwalow and \{De Silva\}, M. and Y. Sudo and Tran, \{H. L.\} and E. Buhmann and E. Garutti and S. Ḣuck and G. Kasieczka and S. Martens and J. Rolph and J. Wellhausen and Blazey, \{G. C.\} and A. Dyshkant and K. Francis and V. Zutshi and B. Bilki and D. Northacker and Y. Onel and F. Hummer and F. Simon and K. Kawagoe and T. Onoe and T. Suehara and S. Tsumura and T. Yoshioka and Fouz, \{M. C.\} and L. Emberger and C. Graf and M. Wagner and R. P{\"o}schl and F. Richard and V. Boudry",

note = "Publisher Copyright: {\textcopyright} 2024 The Author(s)",

year = "2024",

month = apr,

day = "1",

doi = "10.1088/1748-0221/19/04/P04037",

language = "English",

volume = "19",

journal = "Journal of Instrumentation",

issn = "1748-0221",

number = "4",

}

TY - JOUR

T1 - Software compensation for highly granular calorimeters using machine learning

AU - The CALICE Collaboration

AU - Lai, S.

AU - Utehs, J.

AU - Wilhahn, A.

AU - Bach, O.

AU - Brianne, E.

AU - Ebrahimi, A.

AU - Gadow, K.

AU - Göttlicher, P.

AU - Hartbrich, O.

AU - Heuchel, D.

AU - Irles, A.

AU - Krüger, K.

AU - Kvasnicka, J.

AU - Lu, S.

AU - Neubüser, C.

AU - Provenza, A.

AU - Reinecke, M.

AU - Sefkow, F.

AU - Schuwalow, S.

AU - De Silva, M.

AU - Sudo, Y.

AU - Tran, H. L.

AU - Buhmann, E.

AU - Garutti, E.

AU - Ḣuck, S.

AU - Kasieczka, G.

AU - Martens, S.

AU - Rolph, J.

AU - Wellhausen, J.

AU - Blazey, G. C.

AU - Dyshkant, A.

AU - Francis, K.

AU - Zutshi, V.

AU - Bilki, B.

AU - Northacker, D.

AU - Onel, Y.

AU - Hummer, F.

AU - Simon, F.

AU - Kawagoe, K.

AU - Onoe, T.

AU - Suehara, T.

AU - Tsumura, S.

AU - Yoshioka, T.

AU - Fouz, M. C.

AU - Emberger, L.

AU - Graf, C.

AU - Wagner, M.

AU - Pöschl, R.

AU - Richard, F.

AU - Boudry, V.

PY - 2024/4/1

Y1 - 2024/4/1

N2 - A neural network for software compensation was developed for the highly granular CALICE Analogue Hadronic Calorimeter (AHCAL). The neural network uses spatial and temporal event information from the AHCAL and energy information, which is expected to improve sensitivity to shower development and the neutron fraction of the hadron shower. The neural network method produced a depth-dependent energy weighting and a time-dependent threshold for enhancing energy deposits consistent with the timescale of evaporation neutrons. Additionally, it was observed to learn an energy-weighting indicative of longitudinal leakage correction. In addition, the method produced a linear detector response and outperformed a published control method regarding resolution for every particle energy studied.

AB - A neural network for software compensation was developed for the highly granular CALICE Analogue Hadronic Calorimeter (AHCAL). The neural network uses spatial and temporal event information from the AHCAL and energy information, which is expected to improve sensitivity to shower development and the neutron fraction of the hadron shower. The neural network method produced a depth-dependent energy weighting and a time-dependent threshold for enhancing energy deposits consistent with the timescale of evaporation neutrons. Additionally, it was observed to learn an energy-weighting indicative of longitudinal leakage correction. In addition, the method produced a linear detector response and outperformed a published control method regarding resolution for every particle energy studied.

KW - Large detector-systems performance

KW - Pattern recognition, cluster finding, calibration and fitting methods

KW - Performance of High Energy Physics Detectors

UR - https://www.scopus.com/pages/publications/85191535240

U2 - 10.1088/1748-0221/19/04/P04037

DO - 10.1088/1748-0221/19/04/P04037

M3 - Article

AN - SCOPUS:85191535240

SN - 1748-0221

VL - 19

JO - Journal of Instrumentation

JF - Journal of Instrumentation

IS - 4

M1 - P04037

ER -

Software compensation for highly granular calorimeters using machine learning

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this