A study of Neural networks point source extraction on simulated Fermi/LAT Telescope images

TL;DR

This paper introduces a CNN-based method for extracting point sources from simulated Fermi/LAT images, significantly improving accuracy and inference speed over existing models.

Contribution

The study develops a CNN trained on artificial data to enhance point source detection in gamma-ray astrophysical images, outperforming prior models in accuracy and efficiency.

Findings

CNN accuracy increased by ~15%

Inference time reduced by at least 4 times

Effective point source extraction in simulated Fermi/LAT images

Abstract

Astrophysical images in the GeV band are challenging to analyze due to the strong contribution of the background and foreground astrophysical diffuse emission and relatively broad point spread function of modern space-based instruments. In certain cases, even finding of point sources on the image becomes a non-trivial task. We present a method for point sources extraction using a convolution neural network (CNN) trained on our own artificial data set which imitates images from the Fermi Large Area Telescope. These images are raw count photon maps of 10x10 degrees covering energies from 1 to 10 GeV. We compare different CNN architectures that demonstrate accuracy increase by ~15% and reduces the inference time by at least the factor of 4 accuracy improvement with respect to a similar state of the art models.