Studying deep convolutional neural networks with hexagonal lattices for imaging atmospheric Cherenkov telescope event reconstruction

Abstract

Deep convolutional neural networks (DCNs) are a promising machine learning technique to reconstruct events recorded by imaging atmospheric Cherenkov telescopes (IACTs), but require optimization to reach full performance. One of the most pressing challenges is processing raw images captured by cameras made of hexagonal lattices of photo-multipliers, a common layout among IACT cameras which topologically differs from the square lattices conventionally expected, as their input data, by DCN models. Strategies directed to tackle this challenge range from the conversion of the hexagonal lattices onto square lattices by means of oversampling or interpolation to the implementation of hexagonal convolutional kernels. In this contribution we present a comparison of several of those strategies, using DCN models trained on simulated IACT data.

8 pages, 3 figures, Proceedings of the ICRC 2019 PoS(ICRC2019)753

References in corpus (6)

• Implementation of the Random Forest Method for the Imaging Atmospheric Cherenkov Telescope MAGIC
• Gamma-Hadron Separation in Very-High-Energy gamma-ray astronomy using a multivariate analysis method
• Monte Carlo studies for the optimisation of the Cherenkov Telescope Array layout
• A new analysis strategy for detection of faint gamma-ray sources with Imaging Atmospheric Cherenkov Telescopes
• Improved $\gamma$/hadron separation for the detection of faint gamma-ray sources using boosted decision trees
• CTLearn: Deep Learning for Gamma-ray Astronomy

Cited by in corpus (2)

• Investigating a Deep Learning Method to Analyze Images from Multiple Gamma-ray Telescopes
• CTLearn: Deep Learning for Gamma-ray Astronomy