Toward using GANs in astrophysical Monte-Carlo simulations
This work addresses the time-consuming nature of astrophysical simulations for researchers, though it is incremental as it applies an existing GAN method to a new domain-specific problem.
The paper tackled the computational inefficiency of Monte-Carlo simulations in astrophysics by using a GAN to replicate the Maxwell-Jüttner distribution, achieving an average Kolmogorov-Smirnov test value of 0.5, indicating the generated distribution is statistically indistinguishable from the true one.
Accurate modelling of spectra produced by X-ray sources requires the use of Monte-Carlo simulations. These simulations need to evaluate physical processes, such as those occurring in accretion processes around compact objects by sampling a number of different probability distributions. This is computationally time-consuming and could be sped up if replaced by neural networks. We demonstrate, on an example of the Maxwell-Jüttner distribution that describes the speed of relativistic electrons, that the generative adversarial network (GAN) is capable of statistically replicating the distribution. The average value of the Kolmogorov-Smirnov test is 0.5 for samples generated by the neural network, showing that the generated distribution cannot be distinguished from the true distribution.