Proposes feeding seven 2D histograms of waveform parameters into ML algorithms alongside integrated charge images to better reject background in IACT observations.
Gamma-Hadron Separation in Very-High-Energy gamma-ray astronomy using a multivariate analysis method
3 Pith papers cite this work, alongside 159 external citations. Polarity classification is still indexing.
3
Pith papers citing it
159
external citations · Pith
abstract
In recent years, Imaging Atmospheric Cherenkov Telescopes (IACTs) have discovered a rich diversity of very high energy (VHE, > 100 GeV) gamma-ray emitters in the sky. These instruments image Cherenkov light emitted by gamma-ray induced particle cascades in the atmosphere. Background from the much more numerous cosmic-ray cascades is efficiently reduced by considering the shape of the shower images, and the capability to reduce this background is one of the key aspects that determine the sensitivity of a IACT. In this work we apply a tree classification method to data from the High Energy Stereoscopic System (H.E.S.S.). We show the stability of the method and its capabilities to yield an improved background reduction compared to the H.E.S.S. Standard Analysis.
citation-role summary
background 1
citation-polarity summary
fields
astro-ph.IM 3roles
background 1polarities
background 1representative citing papers
This review describes the IACT event reconstruction pipeline and the role of machine learning for classification and regression, highlighting timing features and ensemble methods as improvements over baseline approaches.
citing papers explorer
-
Prospects for the Use of Photosensor Timing Information with Machine Learning Techniques in Background Rejection
Proposes feeding seven 2D histograms of waveform parameters into ML algorithms alongside integrated charge images to better reject background in IACT observations.
-
Machine Learning for Event Reconstruction in Imaging Atmospheric Cherenkov Telescopes
This review describes the IACT event reconstruction pipeline and the role of machine learning for classification and regression, highlighting timing features and ensemble methods as improvements over baseline approaches.
- Enhancing event reconstruction for $\gamma$-ray particle detector arrays using transformers