Generating Synthetic Images of Gamma-Ray Events for Imaging Atmospheric Cherenkov Telescopes Using Conditional Generative Adversarial Networks

Abstract

In recent years, machine learning techniques have seen huge adoption in astronomy applications. In this work, we discuss the generation of realistic synthetic images of gamma-ray events, similar to those captured by imaging atmospheric Cherenkov telescopes (IACTs), using the generative model called a conditional generative adversarial network (cGAN). The significant advantage of the cGAN technique is the much faster generation of new images compared to standard Monte Carlo simulations. However, to use cGAN-generated images in a real IACT experiment, we need to ensure that these images are statistically indistinguishable from those generated by the Monte Carlo method. In this work, we present the results of a study comparing the parameters of cGAN-generated image samples with the parameters of image samples obtained using Monte Carlo simulation. The comparison is made using the so-called Hillas parameters, which constitute a set of geometric features of the event image widely employed in gamma-ray astronomy. Our study demonstrates that the key point lies in the proper preparation of the training set for the neural network. A properly trained cGAN not only excels at generating individual images but also accurately reproduces the Hillas parameters for the entire sample of generated images. As a result, machine learning simulations are a compelling alternative to time-consuming Monte Carlo simulations, offering the speed required to meet the growing demand for synthetic images in IACT experiments.