# Constraining strongly coupled new physics from cosmic rays with machine learning techniques

## TL;DR

This paper uses machine learning on cosmic-ray air shower simulations to set limits on strongly coupled new physics models at ultra-high energies.

## Contribution

It introduces a novel approach combining Monte Carlo simulations and machine learning to constrain new physics from cosmic-ray data.

## Key findings

- Limits on new physics cross sections established
- Machine learning improves event discrimination
- Method applicable to future cosmic-ray observations

## Abstract

Cosmic rays interacting with the atmosphere allow for the probing of fundamental interactions at ultra-high energies. We thus obtain limits on strongly coupled new physics models via their imprints on cosmic-ray air showers. Using the Monte Carlo event generators Herwig and HERBVI, and the air shower simulator CORSIKA, to simulate such processes, we apply machine learning algorithms to the simulated observables to discriminate the events arising via new physics from the QCD background. We then use the signal and background discrimination performance to set potential limits on the cross sections of the new physics models.