What question did this study set out to answer?

To enhance the understanding of cosmic rays by improving mass composition sensitivity through machine learning techniques.

February 14, 2026Open Access

Mass Composition of Primary Cosmic Rays with GRAPES-3 Using Machine Learning Techniques

Key Points

To enhance the understanding of cosmic rays by improving mass composition sensitivity through machine learning techniques.
Applied a Deep Neural Network (DNN) combining muon multiplicity and shower age.
Utilized additional high-level reconstructed shower parameters.
Conducted spectral measurements to assess proton spectrum modifications.
Observed a spectral hardening in the proton spectrum at ∼166TeV.
Demonstrated the DNN's capability to improve composition sensitivity.
Validated the reliability of the DNN-based approach for mass composition studies.

Abstract

Precise measurements of the nuclear composition and energy spectrum of primary cosmic rays around the knee are essential to understand their origin, acceleration, and propagation. The GRAPES-3 experiment in Ooty, India, recently reported a spectral hardening in the proton spectrum at ∼166TeV using Gold’s unfolding method based on muon multiplicity distributions. To enhance composition sensitivity by incorporating additional observables, we implement a Deep Neural Network (DNN) using both muon multiplicity and shower age, along with other high-level reconstructed shower parameters. This work presents the strategy, performance, and reliability of the DNN-based approach for mass composition studies at GRAPES-3.

Bookmark

View Full Paper

Cite This Study

Rout et al. (Wed,) studied this question.

synapsesocial.com/papers/699011812ccff479cfe5837f https://doi.org/https://doi.org/10.5445/ir/1000190583

Bookmark

View Full Paper