To clean or not to clean? Influence of pixel removal on event reconstruction using deep learning in CTAO

TL;DR

This paper evaluates how different pixel cleaning methods affect deep learning-based event reconstruction in the Cherenkov Telescope Array, highlighting the balance between data reduction and information retention.

Contribution

It provides an analysis of the impact of pixel removal on deep learning performance in gamma-ray event reconstruction for CTAO.

Findings

Pixel cleaning influences neural network accuracy

Data compression can lead to information loss

Optimal cleaning masks improve reconstruction performance

Abstract

The Cherenkov Telescope Array Observatory (CTAO) is the next generation of ground-based observatories employing the imaging air Cherenkov technique for the study of very high energy gamma rays. The software Gammalearn proposes to apply Deep Learning as a part of the CTAO data analysis to reconstruct event parameters directly from images captured by the telescopes with minimal pre-processing to maximize the information conserved. In CTAO, the data analysis will include a data volume reduction that will definitely remove pixels. This step is necessary for data transfer and storage but could also involve information loss that could be used by sensitive algorithms such as neural networks (NN). In this work, we evaluate the performance of the gamma-PhysNet when applying different cleaning masks on images from Monte-Carlo simulations from the first Large-Sized Telescope. This study is critical to assess the impact of pixel removal in the data processing, mainly motivated by data compression.