Imaging Atmospheric Cherenkov telescopes (IACTs) are designed to detect cosmic gamma rays. As a by-product, IACTs detect Cherenkov flashes generated by millions of hadronic air showers every night. We present the proton energy spectrum from several hundred GeV to several hundred TeV, retrieved from the hadron induced showers detected by the MAGIC telescopes. The protons are discriminated from He and other heavy nuclei by means of using machine learning classification. The energy estimation is based on a specially developed deep neural network regressor. In the last decade, Deep Learning methods gained much interest in the scientific community for their ability to extract complex relations in data and process large datasets in a short time. The proton energy spectrum obtained in this work is compared to the spectra obtained by dedicated cosmic ray experiments.

Protons Spectrum from the MAGIC Telescopes data

Ansoldi S.;De Lotto B.;
2022-01-01

Abstract

Imaging Atmospheric Cherenkov telescopes (IACTs) are designed to detect cosmic gamma rays. As a by-product, IACTs detect Cherenkov flashes generated by millions of hadronic air showers every night. We present the proton energy spectrum from several hundred GeV to several hundred TeV, retrieved from the hadron induced showers detected by the MAGIC telescopes. The protons are discriminated from He and other heavy nuclei by means of using machine learning classification. The energy estimation is based on a specially developed deep neural network regressor. In the last decade, Deep Learning methods gained much interest in the scientific community for their ability to extract complex relations in data and process large datasets in a short time. The proton energy spectrum obtained in this work is compared to the spectra obtained by dedicated cosmic ray experiments.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11390/1239911
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact