Use of Generative Adversarial Neural Networks in Scattering Muography
Abstract
Many muography applications make extensive use of simulations to determine detector design or to train
imaging or regression algorithms. The computing cost of producing these simulations is usually quite high,
especially concerning the interaction of cosmic muons with matter. This work explores the possibility of
using Generative Adversarial Neural (GAN) networks to produce a fast and realistic simulation of the
multiple scattering process. The results of the network are confronted with GEANT4 simulations using a
benchmark problem related to the measurement of the inner wear of industrial pipes. The GAN is able to
reproduce the angular distributions and correlations with a speed-up factor of roughly 50 with respect to
GEANT4.
Journal of Advanced Instrumentation in Science (JAIS) is an open access journal published by Andromeda Publishing and Education Services. The articles in JAIS are distributed according to the terms of the creative commons license CC-BY 4.0. Under the terms of this license, copyright is retained by the author while use, distribution and reproduction in any medium are permitted provided proper credit is given to original authors and sources.
Terms of Submission
By submitting an article for publication in JAIS, the submitting author asserts that:
1. The article presents original contributions by the author(s) which have not been published previously in a peer-reviewed medium and are not subject to copyright protection.
2. The co-authors of the article, if any, as well as any institution whose approval is required, agree to the publication of the article in JAIS.