Deep learning the astrometric signature of dark matter substructure

Abstract

We study the application of machine learning techniques for the detection of the astrometric signature of dark matter substructure. In this proof of principle a population of dark matter subhalos in the Milky Way will act as lenses for sources of extragalactic origin such as quasars. We train {\it ResNet-18}, a state-of-the-art convolutional neural network to classify angular velocity maps of a population of quasars into lensed and no lensed classes. We show that an SKA -like survey with extended operational baseline can be used to probe the substructure content of the Milky Way, and demonstrate how axiomatic attribution can be used to localize substructures in lensing maps.

arXiv commentReplaced with version accepted for publication in Physics. Rev. D

References in corpus (76)

• The Structure of Cold Dark Matter Halos
• Deep Residual Learning for Image Recognition
• Axiomatic Attribution for Deep Networks
• Machine learning and the physical sciences
• Local Kinematics and the Local Standard of Rest
• Dark Matter Search Results from a One Tonne$\times$Year Exposure of XENON1T
• Results from a search for dark matter in the complete LUX exposure
• Dark Matter Results From 54-Ton-Day Exposure of PandaX-II Experiment
• Constraints on the Self-Interaction Cross-Section of Dark Matter from Numerical Simulations of the Merging Galaxy Cluster 1E 0657-5
• Experimental Searches for the Axion and Axion-like Particles
• A Search for Invisible Axion Dark Matter with the Axion Dark Matter Experiment
• Direct Detection of CDM Substructure
• The APOSTLE simulations: solutions to the Local Group's cosmic puzzles
• Evidence for substructure in lens galaxies?
• The Extended Rotation Curve and the Dark Matter Halo of M33
• Gravitational detection of a low-mass dark satellite at cosmological distance
• Detection of lensing substructure using ALMA observations of the dusty galaxy SDP.81
• Detection of a Dark Substructure through Gravitational Imaging
• Bayesian Strong Gravitational-Lens Modeling on Adaptive Grids: Objective Detection of Mass Substructure in Galaxies
• Limits to dark matter annihilation cross-section from a combined analysis of MAGIC and Fermi-LAT observations of dwarf satellite galaxies
• The RAVE survey: the Galactic escape speed and the mass of the Milky Way
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• The flattening of the concentration-mass relation towards low halo masses and its implications for the annihilation signal boost
• Inference of the Cold Dark Matter substructure mass function at z=0.2 using strong gravitational lenses
• The Spur and the Gap in GD-1: Dynamical evidence for a dark substructure in the Milky Way halo
• Dark Energy Survey Year 1 Results: Measurement of the Baryon Acoustic Oscillation scale in the distribution of galaxies to redshift 1
• DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
• The number and size of subhalo-induced gaps in stellar streams
• Limits on Dark Matter Annihilation Signals from the Fermi LAT 4-year Measurement of the Isotropic Gamma-Ray Background
• Cosmological constraints with deep learning from KiDS-450 weak lensing maps
• The clustering of the SDSS-IV extended Baryon Oscillation Spectroscopic Survey DR14 quasar sample: structure growth rate measurement from the anisotropic quasar power spectrum in the redshift range $0.8<z<2.2$
• A Comprehensive Search for Dark Matter Annihilation in Dwarf Galaxies
• Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
• Dark Matter Constraints from a Joint Analysis of Dwarf Spheroidal Galaxy Observations with VERITAS
• Low-mass halo perturbations in strong gravitational lenses at redshift z$\sim$0.5 are consistent with CDM
• Pulsar Timing Probes of Primordial Black Holes and Subhalos
• Statistics of mass substructure from strong gravitational lensing: quantifying the mass fraction and mass function
• Dark Matter Limits From Dwarf Spheroidal Galaxies with The HAWC Gamma-Ray Observatory
• Search for Neutrinos from Dark Matter Self-Annihilations in the center of the Milky Way with 3 years of IceCube/DeepCore
• Constraints on mediator-based dark matter and scalar dark energy models using $\sqrt{s}=13$ TeV $pp$ collision data collected by the ATLAS detector
• Dark Matter and the XENON1T electron recoil excess
• Halometry from Astrometry
• Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning
• HOLISMOKES -- II. Identifying galaxy-scale strong gravitational lenses in Pan-STARRS using convolutional neural networks
• DeepCMB: Lensing Reconstruction of the Cosmic Microwave Background with Deep Neural Networks
• Constraining the astrophysics and cosmology from 21cm tomography using deep learning with the SKA
• SHARP - IV. An apparent flux ratio anomaly resolved by the edge-on disc in B0712+472
• Baryonic and dark matter distribution in cosmological simulations of spiral galaxies
• Data-Driven Reconstruction of Gravitationally Lensed Galaxies using Recurrent Inference Machines
• Detecting Dark Matter Substructures around the Milky Way with Gaia
• Annual Modulation in Direct Dark Matter Searches
• Using gaps in N-body tidal streams to probe missing satellites
• Dark matter substructure modelling and sensitivity of the Cherenkov Telescope Array to Galactic dark halos
• Microarcsecond Astrometry using the SKA
• Detecting the disruption of dark-matter halos with stellar streams
• On the Power Spectrum of Dark Matter Substructure in Strong Gravitational Lenses
• Gravitational Lensing and the Power Spectrum of Dark Matter Substructure: Insights from the ETHOS N-body Simulations
• Deep Learning the Morphology of Dark Matter Substructure
• Direct Detection of Dark Matter Substructure in Strong Lens Images with Convolutional Neural Networks
• First Results on Dark Matter Substructure from Astrometric Weak Lensing
• Search for new physics in the monophoton final state in proton-proton collisions at sqrt(s) = 13 TeV
• Stellar Wakes from Dark Matter Subhalos
• Search for neutrinos from annihilation of captured low-mass dark matter particles in the Sun by Super-Kamiokande
• Modeling GD-1 Gaps in a Milky-Way Potential
• Astrophysical and cosmological probes of dark matter
• The Power of Halometry
• The Effects of Halo-to-Halo Variation on Substructure Lensing
• Bias-Free Shear Estimation using Artificial Neural Networks
• Gamma-Ray Dark Matter Searches in Milky Way Satellites -- A Comparative Review of Data Analysis Methods and Current Results
• Galactic Origin of Relativistic Bosons and XENON1T Excess
• Foreground model recognition through Neural Networks for CMB B-mode observations
• Gravitational Nanolensing from Subsolar Mass Dark Matter Halos
• Self-interacting dark matter constraints in a thick dark disk scenario
• Stream-subhalo interactions in the Aquarius simulations
• Hopfield Neural Network deconvolution for weak lensing measurement
• Baryon density extraction and isotropy analysis of Cosmic Microwave Background using Deep Learning

Cited by in corpus (6)

• The tidal evolution of dark matter substructure -- II. The impact of artificial disruption on subhalo mass functions and radial profiles
• Decoding Dark Matter Substructure without Supervision
• Reconstructing Cosmic Polarization Rotation with ResUNet-CMB
• Astrometric Weak Lensing with Gaia DR3 and Future Catalogs: Searches for Dark Matter Substructure
• Detecting Dark Compact Objects in Gaia DR4: A Data Analysis Pipeline for Transient Astrometric Lensing Searches
• Detecting dark matter subhalos with the Nancy Grace Roman Space Telescope