Extracting the gamma-ray source-count distribution below the Fermi-LAT detection limit with deep learning
Not on the map. Why?
Abstract (arXiv)
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 ~ S-2 in the unresolved regime, down to fluxes of 5 · 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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 65 references that are in the map. First posted on arXiv 3 Feb 2023.
Builds on
18 of 65 references.
References · 18
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
- 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
- 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
- 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
- 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 660
- 2015Cyclical Learning Rates for Training Neural Networkscited by 627
- 2020A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospectscited by 396
- 2015Recent Advances in Convolutional Neural Networkscited by 360
- 2019Gauge Equivariant Convolutional Networks and the Icosahedral CNNcited by 262
- 2017L2 Regularization versus Batch and Weight Normalizationcited by 121
6 more
- 2020On Contrastive Learning for Likelihood-free Inferencecited by 96
- 2020DeepSphere: a graph-based spherical CNNcited by 65
- 2021Truncated Marginal Neural Ratio Estimationcited by 30
- 2017Learning Spherical Convolution for Fast Features from 360deg Imagerycited by 22
- 2021A neural simulation-based inference approach for characterizing the Galactic Center γ-ray excesscited by 12
- 2021Dim but not entirely dark: Extracting the Galactic Center Excess' source-count distribution with neural netscited by 2
Built on by
Citing papers per year: 2024: 1.
1 paper.