Gamma/Hadron Separation in Imaging Air Cherenkov Telescopes Using Deep Learning Libraries TensorFlow and PyTorch

Abstract

In this work we compare two open source machine learning libraries, PyTorch and TensorFlow, as software platforms for rejecting hadron background events detected by imaging air Cherenkov telescopes (IACTs). Monte Carlo simulation for the TAIGA-IACT telescope is used to estimate background rejection quality. A wide variety of neural network algorithms provided by both libraries can easily be tested on various types of data, which is useful for various imaging air Cherenkov experiments. The work is a component of the Astroparticle.online project, which collaborates with the TAIGA and KASCADE experiments and welcomes any astroparticle experiment to join.

6 pages, 2 figures. Submitted to JPCS, 26th Extended European Cosmic Ray Symposium and 35th Russian Cosmic Ray Conference (E+CRS 2018 / RCRC 2018), Barnaul - Belokurikha, July 6 - 10, 2018

References in corpus (6)

• Implementation of the Random Forest Method for the Imaging Atmospheric Cherenkov Telescope MAGIC
• Observations of Mkn 421 with the MAGIC Telescope
• Gamma-Hadron Separation in Very-High-Energy gamma-ray astronomy using a multivariate analysis method
• Very-high energy gamma-ray astronomy: A 23-year success story in high-energy astroparticle physics
• Hybrid method for identifying mass groups of primary cosmic rays in the joint operation of IACTs and wide angle Cherenkov timing arrays
• Study on Cosmic Ray Background Rejection with a 30 m Stand-Alone IACT using Non-parametric Multivariate Methods in a sub-100 GeV Energy Range

Cited by in corpus (3)

• Deep learning techniques for Imaging Air Cherenkov Telescopes
• Selection of gamma events from IACT images with deep learning methods
• Machine Learning in Gamma Astronomy