Deep learning dark matter map reconstructions from DES SV weak lensing data

Aug 1, 2019
7 pages
Published in:
  • Mon.Not.Roy.Astron.Soc. 492 (2020) 4, 5023-5029
  • Published: Mar 11, 2020
e-Print:
DOI:

Citations per year

20192021202320252025024681012
Abstract: (Oxford University Press)
We present the first reconstruction of dark matter maps from weak lensing observational data using deep learning. We train a convolution neural network with a U-Net-based architecture on over 3.6 × 10^5 simulated data realizations with non-Gaussian shape noise and with cosmological parameters varying over a broad prior distribution. We interpret our newly created dark energy survey science verification (DES SV) map as an approximation of the posterior mean P(κ|γ) of the convergence given observed shear. Our DeepMass^1 method is substantially more accurate than existing mass-mapping methods. With a validation set of 8000 simulated DES SV data realizations, compared to Wiener filtering with a fixed power spectrum, the DeepMass method improved the mean square error (MSE) by 11 per cent. With N-body simulated MICE mock data, we show that Wiener filtering, with the optimal known power spectrum, still gives a worse MSE than our generalized method with no input cosmological parameters; we show that the improvement is driven by the non-linear structures in the convergence. With higher galaxy density in future weak lensing data unveiling more non-linear scales, it is likely that deep learning will be a leading approach for mass mapping with Euclid and LSST.
Note:
  • Accepted MNRAS, 7 pages, 5 figures, added interpretation of DeepMass improvement
  • gravitational lensing: weak
  • methods: statistical
  • (cosmology:) large-scale structure of Universe