Full LST-1 data reconstruction with the use of convolutional neural networks

TL;DR

This paper introduces a deep learning-based full-image reconstruction method for gamma-ray shower images using a modified InceptionV3 CNN, demonstrating improved performance over standard methods on simulated and real data from the LST-1 telescope.

Contribution

It presents a novel CNN-based reconstruction approach for Cherenkov telescope images, enhancing accuracy over traditional methods.

Findings

CNN method outperforms standard reconstruction on simulations

Effective on real LST-1 data

Improves gamma-ray shower image analysis

Abstract

The Cherenkov Telescope Array (CTA) will be the world's largest and most sensitive ground-based gamma-ray observatory in the energy range from a few tens of GeV to tens of TeV. The LST-1 prototype, currently in its commissioning phase, is the first of the four largest CTA telescopes, that will be built in the northern site of CTA in La Palma, Canary Islands, Spain. In this contribution, we present a full-image reconstruction method using a modified InceptionV3 deep convolutional neural network applied on non-parametrized shower images. We evaluate the performance of optimized networks on Monte Carlo simulations of LST-1 shower images, and compare the results with the performance of the standard reconstruction method. We also show how both methods work on real-data reconstruction.