A convolutional-neural-network estimator of CMB constraints on dark matter energy injection
arXiv:2101.10360 · doi:10.1088/1475-7516/2021/06/025
Abstract
We show that the impact of energy injection by dark matter annihilation on the cosmic microwave background power spectra can be apprehended via a residual likelihood map. By resorting to convolutional neural networks that can fully discover the underlying pattern of the map, we propose a novel way of constraining dark matter annihilation based on the Planck 2018 data. We demonstrate that the trained neural network can efficiently predict the likelihood and accurately place bounds on the annihilation cross-section in a fashion. The machinery will be made public in the near future.
25 pages, 8 figures; to match the published version
References in corpus (16)
- An Introduction to PYTHIA 8.2
- Secluded WIMP Dark Matter
- CMB Constraints on WIMP Annihilation: Energy Absorption During the Recombination Epoch
- Weak Corrections are Relevant for Dark Matter Indirect Detection
- General Constraints on Dark Matter Decay from the Cosmic Microwave Background
- Enhancement of Dark Matter Annihilation via Breit-Wigner Resonance
- Constraining Very Heavy Dark Matter Using Diffuse Backgrounds of Neutrinos and Cascaded Gamma Rays
- Model-Independent Bound on the Dark Matter Lifetime
- Circumscribing Late Dark Matter Decays Model Independently
- Singlet Majorana fermion dark matter: a comprehensive analysis in effective field theory
- Full-sky Cosmic Microwave Background Foreground Cleaning Using Machine Learning
- Probing Dark Matter with Future CMB Measurements
- Electron and Photon Energy Deposition in Universe
- ForSE: a GAN based algorithm for extending CMB foreground models to sub-degree angular scales
- Inpainting Galactic Foreground Intensity and Polarization maps using Convolutional Neural Network
- Foreground model recognition through Neural Networks for CMB B-mode observations