Extracting the gamma-ray source-count distribution below the Fermi-LAT detection limit with deep learning

Abstract

We reconstruct the extra-galactic gamma-ray source-count distribution, or $dN/dS$, of resolved and unresolved sources by adopting machine learning techniques. Specifically, we train a convolutional neural network on synthetic 2-dimensional sky-maps, which are built by varying parameters of underlying source-counts models and incorporate the Fermi-LAT instrumental response functions. The trained neural network is then applied to the Fermi-LAT data, from which we estimate the source count distribution down to flux levels a factor of 50 below the Fermi-LAT threshold. We perform our analysis using 14 years of data collected in the $(1,10)$ GeV energy range. The results we obtain show a source count distribution which, in the resolved regime, is in excellent agreement with the one derived from catalogued sources, and then extends as $dN/dS\sim S^{-2}$ in the unresolved regime, down to fluxes of $5\cdot 10^{-12}$ cm${}^{-2}$ s${}^{-1}$. The neural network architecture and the devised methodology have the flexibility to enable future analyses to study the energy dependence of the source-count distribution.

26 pages + Appendix, 28 figures

References in corpus (13)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• The spectrum of isotropic diffuse gamma-ray emission between 100 MeV and 820 GeV
• Incremental Fermi Large Area Telescope Fourth Source Catalog
• The Fermi-LAT high-latitude Survey: Source Count Distributions and the Origin of the Extragalactic Diffuse Background
• The Origin of the Extragalactic Gamma-Ray Background and Implications for Dark-Matter Annihilation
• The angular power spectrum of the diffuse gamma-ray emission as measured by the Fermi Large Area Telescope and constraints on its Dark Matter interpretation
• Distinguishing Dark Matter from Unresolved Point Sources in the Inner Galaxy with Photon Statistics
• A neural simulation-based inference approach for characterizing the Galactic Center $\gamma$-ray excess
• Dim but not entirely dark: Extracting the Galactic Center Excess' source-count distribution with neural nets
• Source-count Distribution of Gamma-Ray Blazars
• A Compound Poisson Generator approach to Point-Source Inference in Astrophysics
• Detection is truncation: studying source populations with truncated marginal neural ratio estimation
• Characterizing the Expected Behavior of Non-Poissonian Template Fitting

Cited by in corpus (3)

• Ultra-high-energy Cosmic Ray Sources can be Gamma-ray Dim
• On the Energy Distribution of the Galactic Center Excess' Sources
• Deepening gamma-ray point-source catalogues with sub-threshold information