Inference of the Mass Composition of Cosmic Rays with energies between 3 and 100 EeV using the data of the Pierre Auger Observatory and Deep Learning

Located in Argentina, the Pierre Auger Observatory is the largest cosmic-ray observatory on Earth. The Observatory is a hybrid detector employing different detection principles to observe multiple components of air showers. The core part of the detector is the Surface Detector (SD), which comprises $1600$ water-Cherenkov detectors with $1.5\,\mathrm{km}$ spacing in an area of $3000\,\mathrm{km}^2$. The highly sensitive Fluorescence Detector (FD) overlooks the area above the SD. Since the FD can only operate on nights with good atmospheric conditions and low moon fraction, its duty cycle is limited to approximately 15%. The indirect nature of measurements of the Pierre Auger Observatory poses several challenges. For example, estimating the mass of a primary cosmic ray. The atmospheric depth of the shower maximum $X_\mathrm{max}$ is a mass-sensitive observable. The FD measures the $X_\mathrm{max}$ directly, but the statistic is limited by the duty cycle. On the contrary, the SD of the Pierre Auger Observatory, operating almost at 100% duty cycle, allows for a significant increase in the data. In this contribution, we present the $X_\mathrm{max}$ reconstruction based on deep neural networks that extends the energy range and statistics. We probe the energy evolution of the mean and standard deviation of the reconstructed $X_\mathrm{max}$, which reflects the changes in the mass composition. The features found in the average $X_\mathrm{max}$ rate suggest a heavier and purer mass composition with increasing energy.

Authors

Publication Details

Published
2026-02-06
DOI
https://doi.org/10.22323/1.485.0095
Primary Topic
Astrophysics and Cosmic Phenomena
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Inference of the Mass Composition of Cosmic Rays with energies between 3 and 100 EeV using the data of the Pierre Auger Observatory and Deep Learning

Bin Yue, Enrique Varela, Alena Bakalová, Sergeï Vorobiov et al.
Astrophysics and Cosmic Phenomena
article

Inference of the Mass Composition of Cosmic Rays with energies between 3 and 100 EeV using the data of the Pierre Auger Observatory and Deep Learning

Bin Yue, Enrique Varela, Alena Bakalová, Sergeï Vorobiov, Therese Paulsen, Berenika Čermáková, Enrico Arnone, Alexey Yushkov, F. Guarino, Veronika Vašíčková, Alex Adrián Reyes Tapia, Tobias Schulz, Shima Ujjani Shivashankara, S. Buitink, Anastasia Yurevna Baluta, Tim Fehler, F. Montanet, MÁRIO PIMENTA, Anthony Bwembya, Jorge Caraça-Valente, Melanie Weitz, Nicolas Mendoza Leal, Stef Verpoest, Emanuele Avocone, Jan Ebr, Joaquín de Jesús, L. Cazon, Vincent Pelgrims, Miguel A.J.S. Martins, B. P. de Souza de Errico, J. M. González, Petr Trávníček, Jan Řídký, Olaf Scholten, Sven Querchfeld, Paul Sommers, Laura Valore, Tiina Suomijärvi, Johannes Blümer, Paul Matthew Mantsch, R. Pelayo, Fernando Gollan, Italo Epicoco, Antonio Gabriel Gómez Bueno, João C. dos Anjos, Tanguy Pierog, Ingomar Allekotte, A. Khakurdikar, J. Schulte, Markus Risse, Corbin Covault, Petr Tobiska, Alan Fuster, Marta Bianciotto, A. Criss, Vlastimil Jílek, Emanuele De Vito, Ezequiel Rodríguez, J. Vicha, C. Taricco, Shefali Negi, Pim van Dillen, Alex Reuzki, Ugo Gregorio Giaccari, Lukas Gülzow, Luca Deval, Jiří Blažek, Fred Sarazin, Sara Martinelli, Virginia Binet, Rúben Conceição, Marcos Cerda, Dariusz Gora, Felix Riehn, Max Büsken, Bernardo Tomé, Lorenzo Perrone, Radomir Smida, Sergio Dasso, Fabio Convenga, Luis LOPES, Samo Stanič, Belén Andrada, Fabian Gobbi, Bjarni Pont, Harald Schieler, Vitor de Souza, Pedro Ivo Lembo Silveira de Assis, Pavel Horvath, Srijan Sehgal, Carlos Hojvat, Tomáš Fodran, Luis A. Nunez, Michael Prouza, Simone Rossoni, Gonzalo Parente, Nataliia Borodai, Dave Nitz, Sergio Petrera, Kai Daumiller, Enrique Zas, Norbert Kunka, Hans Klages, Carla Aramo, Darko Veberic, Brian Fick, Valerio Verzi, Jeffrey Brack, Jan Pękala, Petr Hamal, Denise Boncioli, Juan Manuel Figueira, Achille Nucita, Fiona H. Ellwanger, Ralph Engel, Benjamin Flaggs, Libor Nozka, Armando di Matteo, Zuzana Svozilikova, Clara Keiko Oliveira Watanabe, Michael Unger, Matías Rolf Hampel, Tim Huege, Patricia María Hansen, Daniele Martello, Gualberto Avila, Martina Bohacova, Alberto Etchegoyen, Igor Vaiman, Carla Bonifazi, Indira D. Vergara Quispe, Juan Ammerman Yebra, Sergio J Sciutto, Fedor Tairli, Niklas Langner, Gonzalo Rodriguez Fernandez, Sonja Mayotte, Eva Santos, Carola Dobrigkeit, Heino Falcke, Martin Schimassek, Jaime Alvarez-Muñiz, Olena Tkachenko, Fernando Catalani, Mohit Saharan, Zbigniew Szadkowski, Juan Carlos Arteaga Velazquez, Chaitanya Priyadarshi, Dusan Mandat, Jörg Hörandel, Bruno L. Lago, Chloé Gaudu, James Matthews, Thomas Fitoussi, Juan Pallotta, Steffen Hahn, Hermann-Josef Mathes, Lawrence Wiencke, Roberto Mussa, Henryk Wilczyński, Humberto Ibarguen Salazar, Toshihiro Fujii, Marina Scornavacche, Frank Simon, Francesco de Palma, Alexandra Fernandes, Manuel Platino, Diego Melo, Leo Östman, Pedro Abreu, Geraldina Golup, Megha Mogarkar, Julian Rautenberg, Nicolas San Martin, Pranav Sampathkumar, Paul Filip, Diego Correia dos Santos, Edyvania Emily Pereira Martins, A. Daniel Supanitsky, Marko Zavrtanik, Adrian Sedoski, Teresa Bister, Patrick Stassi, Federico Campuzano, Marcus Niechciol, Roger W Clay, Vincenzo Rizi, Karl-Heinz Kampert, Antonino Del Popolo, Frederik Krieger, Sijbrand J. de Jong, Peter Mazur, Andreas Weindl, Adriel Bartz Mocellin, Dalibor Nosek, Karolina Syrokvas, Varada Varma Kizakke Covilakam, Luis A. Anchordoqui, Diego Ravignani, Bianca Keilhauer, Andrej Filipcic, Antonio Franco, Adrian Rovero, Matteo Conte, Viviana Scherini, Paula Gina Isar, Francesco Salamida, Mohamed Ismaiel, Matteo Tambone, Jon Paul Lundquist, Pedro J. Costa, Jiří Chudoba, Alexandra Saftoiu, Qader Dorosti, Luis Miguel Domingues Mendes, Olivier Deligny, Carlo Salvattore Cruz Sanchez, Pierpaolo Savina, Gustavo Medina-Tanco, P. Gabriel Brichetto Orchera, Jhansi Bhavani Vuta, Lorenzo Apollonio, Camilla Petrucci, Anderson Fauth, Matias Jorge Tueros, Leonel Morejon, José Ochoa, Mohsen Pourmohammad Shahvar, Katharine Mulrey, Mariano Gómez Berisso, Eric William Mayotte, Charles Timmermans, Gaetano Salina, Giovanni Consolati, Danilo Zavrtanik, Jelena Köhler, Yago Lema-Capeans, Ioana Codrina Maris, João Vitor Reginatto Akim, Federico Andrés Sánchez, Analisa Mariazzi, Miroslav Palatka, Giovanni Marsella, Danelise de Oliveira Franco, Carlos J. Todero Peixoto, Beatriz Garcia, Katarína Simkova, Stanislav Michal, Carmina Pérez Bertolli, Lino Miramonti, Jose F. Valdés Galicia, Nicolas Martin Gonzalez, Violet M. Harvey, Florian Lukas Briechle, Carmelo Evoli, Manuela Mallamaci, Brian Wundheiler, Luciana Andrade Dourado, Andreas Haungs, Karen S. Caballero-Mora, Jose A. Bellido, Lorenzo Caccianiga, Germano Guedes, Marco Aglietta, Agustín Cobos Cerutti, Maximilian Stadelmaier, Juan Carlos D'Olivo, Lukas Nellen, Simon Strähnz, Glennys R. Farrar, Miroslav Hrabovsky, Maria Isabel Micheletti, Ladislav Chytka, Frank G. Schröder, Adila Abdul Halim, Antonella Castellina, Vladimír Novotný, Marvin Gottowik, Harm Schoorlemmer, Markus Roth, Martin Erdmann, Adriana Vásquez-Ramírez, Fridtjof Feldbusch, Alessandro Cermenati, Silvia Mollerach, Nikolas Denner, Mateo Fernandez Alonso, Rogerio M. de Almeida, Thomas Hebbeker, Shayoni Panja, Primo F. Gómez Vitale, Petr Schovanek, Antonio Insolia, Antoine Letessier-Selvon, Cainã Oliveira, Roberto Aloisio, Markus Cristinziani, Giorgio Matthiae, Jonathan Biteau, Matthias Kleifges, Alexander S. Novikov, Kevin Almeida Cheminant, Khoa Nguyen, Paolo Privitera, Krzysztof Pytel, Rita Cassia dos Anjos, Jannis Pawlowsky, Federico Maria Mariani, Milton Freitas, David Schmidt, Cristina Galea, Alexander Menshikov, Alan Watson, Felicia Barbato, Sergio Cabana-Freire, Carmen Merx, Petr Janecek, Wilson M. Namasaka, João de Mello Neto, Jaroslaw Stasielak, Marcelo Augusto Leigui de Oliveira, Maximilian Straub, Gabriela Nicora, Peter L. Biermann, Jose Augusto Chinellato
article en

Abstract

Located in Argentina, the Pierre Auger Observatory is the largest cosmic-ray observatory on Earth. The Observatory is a hybrid detector employing different detection principles to observe multiple components of air showers. The core part of the detector is the Surface Detector (SD), which comprises $1600$ water-Cherenkov detectors with $1.5\,\mathrm{km}$ spacing in an area of $3000\,\mathrm{km}^2$. The highly sensitive Fluorescence Detector (FD) overlooks the area above the SD. Since the FD can only operate on nights with good atmospheric conditions and low moon fraction, its duty cycle is limited to approximately 15%. The indirect nature of measurements of the Pierre Auger Observatory poses several challenges. For example, estimating the mass of a primary cosmic ray. The atmospheric depth of the shower maximum $X_\mathrm{max}$ is a mass-sensitive observable. The FD measures the $X_\mathrm{max}$ directly, but the statistic is limited by the duty cycle. On the contrary, the SD of the Pierre Auger Observatory, operating almost at 100% duty cycle, allows for a significant increase in the data. In this contribution, we present the $X_\mathrm{max}$ reconstruction based on deep neural networks that extends the energy range and statistics. We probe the energy evolution of the mean and standard deviation of the reconstructed $X_\mathrm{max}$, which reflects the changes in the mass composition. The features found in the average $X_\mathrm{max}$ rate suggest a heavier and purer mass composition with increasing energy.

Affordable and clean energy
Openalex Percentile: Top 62%
Astrophysics and Cosmic Phenomena
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.