Deep learning method for identifying mass composition of ultra-high-energy cosmic rays

TL;DR

This paper presents a deep learning approach using a two-stage neural network system to accurately determine the mass composition of ultra-high-energy cosmic rays from detector data, achieving a 7% error rate.

Contribution

It introduces a novel two-network deep learning method for cosmic ray composition analysis, improving accuracy over previous techniques.

Findings

Achieved 7% error in mass composition prediction on Monte Carlo data.

Demonstrated the method's potential for application to real experimental data.

Provided insights into challenges and solutions for real-world implementation.

Abstract

We introduce a novel method for identifying the mass composition of ultra-high-energy cosmic rays using deep learning. The key idea of the method is to use a chain of two neural networks. The first network predicts the type of a primary particle for individual events, while the second infers the mass composition of an ensemble of events. We apply this method to the Monte-Carlo data for the Telescope Array Surface Detectors readings, on which it yields an unprecedented low error of 7% for 4-component approximation. We also discuss the problems of applying the developed method to the experimental data, and the way they can be resolved.