2020/09/30 by Bryan Ostdiek, Ana Díaz Rivero, Ana Diaz Rivero +1
Mathematics · Physics and Astronomy · #Artificial intelligence #Astronomy and Astrophysical Research #Astrophysics #Computer science #Dark matter #Einstein ring #Galaxies: Formation, Evolution, Phenomena #Galaxy #Gravitational lens #Image (mathematics) #Lens (geology) #Optics #Pattern recognition (psychology) #Physics #Pixel #Redshift #Segmentation #Stellar, planetary, and galactic studies #Substructure #astro-ph.CO #astro-ph.IM #hep-ph #physics.data-an #stat.ML
paper · pdf · doi:10.3847/1538-4357/ac2d8d
v1:23 + 5 pages, 12 + 2 figures. v2: matches accepted version in ApJ. v3: matches version published in ApJ
arxiv created 2022/02/14 · arxiv updated 2022/02/15 · openalex publication_date 2022/03/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
Abstract Detecting substructure within strongly lensed images is a promising route to shed light on the nature of dark matter. However, it is a challenging task, which traditionally requires detailed lens modeling and source reconstruction, taking weeks to analyze each system. We use machine learning to circumvent the need for lens and source modeling and develop a neural network to both locate subhalos in an image as well as determine their mass using the technique of image segmentation. The network is trained on images with a single subhalo located near the Einstein ring across a wide range of apparent source magnitudes. The network is then able to resolve subhalos with masses m ≳ 10 8.5 M ⊙ . Training in this way allows the network to learn the gravitational lensing of light, and, remarkably, it is then able to detect entire populations of substructure, even for locations further away from the Einstein ring than those used in training. Over a wide range of the apparent source magnitude, the false-positive rate is around three false subhalos per 100 images, coming mostly from the lightest detectable subhalo for that signal-to-noise ratio. With good accuracy and a low false-positive rate, counting the number of pixels assigned to each subhalo class over multiple images allows for a measurement of the subhalo mass function (SMF). When measured over three mass bins from 10 9 –10 10 M ⊙ the SMF slope is recovered with an error of 36% for 50 images, and this improves to 10% for 1000 images with Hubble Space Telescope-like noise.