Extracting gamma-ray information from images with convolutional neural network methods on simulated Cherenkov Telescope Array data

TL;DR

This paper explores the use of convolutional neural networks to analyze simulated Cherenkov Telescope Array images, aiming to improve gamma-ray signal discrimination and parameter reconstruction for future large-scale gamma-ray data analysis.

Contribution

It demonstrates that CNNs trained on simulated data can effectively extract gamma-ray information, enhancing analysis capabilities for CTA's large datasets.

Findings

High rejection factors in signal-background discrimination

Effective reconstruction of gamma-ray event parameters

CNNs trained on simulated data outperform traditional methods

Abstract

The Cherenkov Telescope Array (CTA) will be the world's leading ground-based gamma-ray observatory allowing us to study very high energy phenomena in the Universe. CTA will produce huge data sets, of the order of petabytes, and the challenge is to find better alternative data analysis methods to the already existing ones. Machine learning algorithms, like deep learning techniques, give encouraging results in this direction. In particular, convolutional neural network methods on images have proven to be effective in pattern recognition and produce data representations which can achieve satisfactory predictions. We test the use of convolutional neural networks to discriminate signal from background images with high rejections factors and to provide reconstruction parameters from gamma-ray events. The networks are trained and evaluated on artificial data sets of images. The results show that neural networks trained with simulated data can be useful to extract gamma-ray information. Such networks would help us to make the best use of large quantities of real data coming in the next decades.