Weak lensing cosmology with convolutional neural networks on noisy data
Open Access
- 17 September 2019
- journal article
- research article
- Published by Oxford University Press (OUP) in Monthly Notices of the Royal Astronomical Society
- Vol. 490 (2) , 1843-1860
Abstract
Weak gravitational lensing is one of the most promising cosmological probes of the late universe. Several large ongoing (DES, KiDS, HSC) and planned (LSST, Euclid, WFIRST) astronomical surveys attempt to collect even deeper and larger scale data on weak lensing. Due to gravitational collapse, the distribution of dark matter is non-Gaussian on small scales. However, observations are typically evaluated through the two-point correlation function of galaxy shear, which does not capture non-Gaussian features of the lensing maps. Previous studies attempted to extract non-Gaussian information from weak lensing observations through several higher order statistics such as the three-point correlation function, peak counts, or Minkowski functionals. Deep convolutional neural networks (CNN) emerged in the field of computer vision with tremendous success, and they offer a new and very promising framework to extract information from 2D or 3D astronomical data sets, confirmed by recent studies on weak lensing. We show that a CNN is able to yield significantly stricter constraints of (σ8, Ωm) cosmological parameters than the power spectrum using convergence maps generated by full N-body simulations and ray-tracing, at angular scales and shape noise levels relevant for future observations. In a scenario mimicking LSST or Euclid, the CNN yields 2.4–2.8 times smaller credible contours than the power spectrum, and 3.5–4.2 times smaller at noise levels corresponding to a deep space survey such as WFIRST. We also show that at shape noise levels achievable in future space surveys the CNN yields 1.4–2.1 times smaller contours than peak counts, a higher order statistic capable of extracting non-Gaussian information from weak lensing maps.Keywords
All Related Versions
Funding Information
- NRDI Office (OTKA NN 129148)
- National Aeronautics and Space Administration (80NSSC18K1093)
This publication has 42 references indexed in Scilit:
- Cosmology with the shear-peak statisticsMonthly Notices of the Royal Astronomical Society, 2010
- THE COSMOLOGY DEPENDENCE OF WEAK LENSING CLUSTER COUNTSThe Astrophysical Journal, 2009
- A Technique for Weak Lensing with Velocity Maps: Eliminating Ellipticity Noise in H i Radio ObservationsThe Astrophysical Journal, 2006
- Simulating Weak Lensing by Large‐Scale StructureThe Astrophysical Journal, 2003
- Higher Order Moments of the Cosmic Shear and Other Spin‐2 FieldsThe Astrophysical Journal, 2003
- The three-point correlation function of cosmic shearAstronomy & Astrophysics, 2003
- Detecting Gravitational Lensing Cosmic Shear from Samples of Several Galaxies Using Two-dimensional Spectral ImagingThe Astrophysical Journal, 2002
- Implication of Ω[TINF][CLC][ITAL]m[/ITAL][/CLC][/TINF] through the Morphological Analysis of Weak Lensing FieldsThe Astrophysical Journal, 2001
- A new measure for cosmic shearMonthly Notices of the Royal Astronomical Society, 1998
- A Universal Density Profile from Hierarchical ClusteringThe Astrophysical Journal, 1997