TUBITAK Destekli Projelerden Çıkan Yayınlar Topluluğu
Published January 1, 2024 | Version v1
Journal article Open

Using graph neural networks to reconstruct charged pion showers in the CMS High Granularity Calorimeter

Creators

  • 1. Univ Maryland, College Pk, MD 20742 USA
  • 2. Georgian Tech Univ, Kostava Str 77, Tbilisi 0160, Georgia
  • 3. Florida State Univ, 600 W Coll Ave, Tallahassee, FL 32306 USA
  • 4. Natl Cent Univ, Chungli, Taiwan
  • 5. CERN, Geneva, Switzerland
  • 6. Tata Inst Fundamental Res B, Homi Bhabha Rd, Mumbai 400005, Maharashtra, India
  • 7. Indian Inst Sci Educ & Res, Dr Homi Bhabha Rd, Pune 411008, Maharashtra, India
  • 8. Quaid I Azam Univ, Natl Ctr Phys, Islamabad 44000, Pakistan
  • 9. Texas Tech Univ, Dept Phys & Astron, Lubbock, TX 79409 USA
  • 10. Yildiz Tech Univ, TR-34220 Istanbul, Turkiye
  • 11. Bogazici Univ, TR-34342 Bebek, Turkiye
  • 12. Istanbul Tech Univ, TR-80625 Istanbul, Turkiye
  • 13. Deutsch Elektronen Synchrotron DESY, Notkestr 85, D-22607 Hamburg, Germany
  • 14. Carnegie Mellon Univ, 5000 Forbes Ave, Pittsburgh, PA 15213 USA

Description

A novel method to reconstruct the energy of hadronic showers in the CMS High Granularity Calorimeter (HGCAL) is presented. The HGCAL is a sampling calorimeter with very fine transverse and longitudinal granularity. The active media are silicon sensors and scintillator tiles readout by SiPMs and the absorbers are a combination of lead and Cu/CuW in the electromagnetic section, and steel in the hadronic section. The shower reconstruction method is based on graph neural networks and it makes use of a dynamic reduction network architecture. It is shown that the algorithm is able to capture and mitigate the main effects that normally hinder the reconstruction of hadronic showers using classical reconstruction methods, by compensating for fluctuations in the multiplicity, energy, and spatial distributions of the shower's constituents. The performance of the algorithm is evaluated using test beam data collected in 2018 prototype of the CMS HGCAL accompanied by a section of the CALICE AHCAL prototype. The capability of the method to mitigate the impact of energy leakage from the calorimeter is also demonstrated.

Files

bib-e7e55da6-ab2e-42c4-b9fb-682d119aa523.txt

Files (407 Bytes)

Name Size Download all
md5:f44a51c3dde59d721880490b1175b3b4
407 Bytes Preview Download