Generative Neural Network for Simulating Radio Emission from Extensive Air Showers

TL;DR

This paper introduces a neural network model that efficiently simulates radio emissions from cosmic ray air showers, enabling accurate $X_ ext{max}$ reconstruction with reduced computational costs.

Contribution

The authors develop a neural network approach for simulating radio emissions from extensive air showers, offering a faster alternative to traditional Monte Carlo simulations.

Findings

Neural network accurately reproduces radio pulse simulations.

Comparable $X_ ext{max}$ resolution to full Monte Carlo methods.

Significant reduction in simulation time.

Abstract

Cosmic ray shower detection using large radio arrays has gained significant traction in recent years. With massive improvements in signal modelling and microscopic simulations, the analysis of incoming events is still severely limited by the simulation cost of radio emission to interpret the data. In this work, we show that a neural network can be used for simulating such radio pulses. We also demonstrate how such a neural network can be used for $X_\mathrm{max}$ reconstruction, while retaining comparable resolution to using full Monte-Carlo CORSIKA/CoREAS simulations for radio emission.