A CNN predicts ln A from longitudinal shower profiles with bias under 0.4, resolution 1-1.5, and proton-iron merit factor 2.19, outperforming simpler ML models on shape parameters and remaining robust to hadronic model changes.
Comparison between methods for the determination of the primary cosmic ray mass composition from the longitudinal profile of atmospheric cascades
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
The determination of the primary cosmic ray mass composition from the longitudinal development of atmospheric cascades is still a debated issue. In this work we discuss several data analysis methods and show that if the entire information contained in the longitudinal profile is exploited, reliable results may be obtained. Among the proposed methods FCC ('Fit of the Cascade Curve'), MTA ('Multiparametric Topological Analysis') and NNA ('Neural Net Analysis') with conjugate gradient optimization algorithm give the best accuracy.
fields
astro-ph.HE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Prospects for Deep-Learning-Based Mass Reconstruction of Ultra-High-Energy Cosmic Rays using Simulated Air-Shower Profiles
A CNN predicts ln A from longitudinal shower profiles with bias under 0.4, resolution 1-1.5, and proton-iron merit factor 2.19, outperforming simpler ML models on shape parameters and remaining robust to hadronic model changes.