Prospects for Deep-Learning-Based Mass Reconstruction of Ultra-High-Energy Cosmic Rays using Simulated Air-Shower Profiles

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Zhuoyi, Mayotte, Eric, Mayotte, Sonja, Woo, Nathan, Burton-Heibges, Julia, Martin, Nicolas San, Smith, Cailyn
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915925152759808
author Wang, Zhuoyi
Mayotte, Eric
Mayotte, Sonja
Woo, Nathan
Burton-Heibges, Julia
Martin, Nicolas San
Smith, Cailyn
author_facet Wang, Zhuoyi
Mayotte, Eric
Mayotte, Sonja
Woo, Nathan
Burton-Heibges, Julia
Martin, Nicolas San
Smith, Cailyn
contents Knowledge of the mass composition of ultra-high-energy cosmic rays is crucial to understanding their origins; however, current approaches have limited event-by-event resolution. With fluorescence telescope measurements of the longitudinal shower profile, there are opportunities to improve this situation by applying Machine Learning (ML) to leverage more information beyond $X_{max}$ alone. To our knowledge, we present the first study of a deep-learning neural-network approach to predict a primary's mass ($\ln{A}$) directly from the longitudinal energy-deposit profile of simulated extensive air showers. We train and validate our model on simulated showers, generated with CONEX and EPOS-LHC, covering nuclei from $A = 1$ to 61, sampled uniformly in $\ln{A}$. After rescaling, our network achieves a maximum bias better than 0.4 in $\ln{A}$ with a resolution between 1.5 for protons and 1 for iron, corresponding to a proton-iron Merit Factor of 2.19 (AUC = 0.976). We benchmark this against simpler ML models trained on profile-shape parameters ($X_{ max}$, $E_{cal}$, $R$, and $L$) extracted from the same data. We find that even simple models can substantially exceed published benchmarks for combinations of these observables, demonstrating that ML methods applied even to standard profile-shape parameters can significantly improve available mass sensitivity. The CNN outperforms this strong baseline, and this performance is only mildly degraded when cross-predicting on simulations made with the Sibyll-2.3d hadronic interaction model, showing robustness against model choice. The network also maintains its performance across a wide range of noise conditions. An ablation study further demonstrates that the full profile contains composition-sensitive structure not captured by the GH parameterization, while the strong performance of the CNN suggests this information should be resolvable in real events.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13933
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Prospects for Deep-Learning-Based Mass Reconstruction of Ultra-High-Energy Cosmic Rays using Simulated Air-Shower Profiles
Wang, Zhuoyi
Mayotte, Eric
Mayotte, Sonja
Woo, Nathan
Burton-Heibges, Julia
Martin, Nicolas San
Smith, Cailyn
High Energy Astrophysical Phenomena
Instrumentation and Methods for Astrophysics
Knowledge of the mass composition of ultra-high-energy cosmic rays is crucial to understanding their origins; however, current approaches have limited event-by-event resolution. With fluorescence telescope measurements of the longitudinal shower profile, there are opportunities to improve this situation by applying Machine Learning (ML) to leverage more information beyond $X_{max}$ alone. To our knowledge, we present the first study of a deep-learning neural-network approach to predict a primary's mass ($\ln{A}$) directly from the longitudinal energy-deposit profile of simulated extensive air showers. We train and validate our model on simulated showers, generated with CONEX and EPOS-LHC, covering nuclei from $A = 1$ to 61, sampled uniformly in $\ln{A}$. After rescaling, our network achieves a maximum bias better than 0.4 in $\ln{A}$ with a resolution between 1.5 for protons and 1 for iron, corresponding to a proton-iron Merit Factor of 2.19 (AUC = 0.976). We benchmark this against simpler ML models trained on profile-shape parameters ($X_{ max}$, $E_{cal}$, $R$, and $L$) extracted from the same data. We find that even simple models can substantially exceed published benchmarks for combinations of these observables, demonstrating that ML methods applied even to standard profile-shape parameters can significantly improve available mass sensitivity. The CNN outperforms this strong baseline, and this performance is only mildly degraded when cross-predicting on simulations made with the Sibyll-2.3d hadronic interaction model, showing robustness against model choice. The network also maintains its performance across a wide range of noise conditions. An ablation study further demonstrates that the full profile contains composition-sensitive structure not captured by the GH parameterization, while the strong performance of the CNN suggests this information should be resolvable in real events.
title Prospects for Deep-Learning-Based Mass Reconstruction of Ultra-High-Energy Cosmic Rays using Simulated Air-Shower Profiles
topic High Energy Astrophysical Phenomena
Instrumentation and Methods for Astrophysics
url https://arxiv.org/abs/2508.13933