EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Precision calibration of calorimeter signals in the ATLAS experiment using an uncertainty-aware neural network

ATLAS Collaboration, Georges Aad, Erlend Aakvaag, Braden Keim Abbott, Sara Abdelhameed, Kira Abeling, Nils Julius Abicht, Haider Abidi, Mohammed Aboelela, Asmaa Aboulhorma, Halina Abramowicz, Yiming Abulaiti und 28 weitere

SciPost Physics · 16.12.2025 · 19 (6)

DOI: 10.21468/scipostphys.19.6.155 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SciPost Physics, online erschienen am 16.12.2025. Verfasst von ATLAS Collaboration und 39 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agence Nationale de la Recherche, Agencia Estatal de Investigación, Agencia Nacional de Investigación y Desarrollo.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The ATLAS experiment at the Large Hadron Collider explores the use of modern neural networks for a multi-dimensional calibration of its calorimeter signal defined by clusters of topologically connected cells (topo-clusters). The Bayesian neural network (BNN) approach not only yields a continuous and smooth calibration function that improves performance relative to the standard calibration but also provides uncertainties on the calibrated energies for each topo-cluster. The results obtained by using a trained BNN are compared to the standard local hadronic calibration and to a calibration provided by training a deep neural network. The uncertainties predicted by the BNN are interpreted in the context of a fractional contribution to the systematic uncertainties of the trained calibration. They are also compared to uncertainty predictions obtained from an alternative estimator employing repulsive ensembles.

Förderung

  • Agence Nationale de la Recherche
  • Agencia Estatal de Investigación
  • Agencia Nacional de Investigación y Desarrollo
  • Agencia Nacional de Promoción Científica y Tecnológica
  • Alexander von Humboldt-Stiftung
  • Alliance de recherche numérique du Canada
  • Australian Research Council
  • Austrian Science Fund

Zitieren

APA

Collaboration, A., Aad, G., Aakvaag, E., Abbott, B. K., Abdelhameed, S., Abeling, K., Abicht, N. J., Abidi, H., Aboelela, M., Aboulhorma, A., Abramowicz, H., Abulaiti, Y., Acharya, B. S., Ackermann, A., Bourdarios, C. A., Adamczyk, L., Addepalli, S., Addison, M., Adelman, J., …, & Alberghi, G. L. (2025). Precision calibration of calorimeter signals in the ATLAS experiment using an uncertainty-aware neural network. SciPost Physics, 19(6). https://doi.org/10.21468/scipostphys.19.6.155

Vancouver

Collaboration A, Aad G, Aakvaag E, Abbott BK, Abdelhameed S, Abeling K, et al. Precision calibration of calorimeter signals in the ATLAS experiment using an uncertainty-aware neural network. SciPost Physics. 2025;19(6). doi:10.21468/scipostphys.19.6.155

BibTeX
@article{Collaboration2025,
  author = {Collaboration, ATLAS and Aad, Georges and Aakvaag, Erlend and Abbott, Braden Keim and Abdelhameed, Sara and Abeling, Kira and Abicht, Nils Julius and Abidi, Haider and Aboelela, Mohammed and Aboulhorma, Asmaa and Abramowicz, Halina and Abulaiti, Yiming and Acharya, Bobby Samir and Ackermann, Anke and Bourdarios, Claire Adam and Adamczyk, Leszek and Addepalli, Sagar and Addison, Matt and Adelman, Jahred and Adiguzel, Aytul and Adye, Tim and Affolder, Tony and Afik, Yoav and Agaras, Merve Nazlim and Aggarwal, Anamika and Agheorghiesei, Catalin and Ahmadov, Faig and Ahuja, Sudha and Ai, Xiaocong and Aielli, Giulio and Aikot, Arya and Tamlihat, Malak Ait and Aitbenchikh, Brahim and Akbiyik, Melike and Akesson, Torsten and Akimov, Andrei and Akiyama, Daiya and Akolkar, Nilima Nilesh and Aktas, Sina and Alberghi, Gian Luigi},
  title = {Precision calibration of calorimeter signals in the ATLAS experiment using an uncertainty-aware neural network},
  journal = {SciPost Physics},
  year = {2025},
  volume = {19},
  number = {6},
  doi = {10.21468/scipostphys.19.6.155}
}
Kostenlos starten →