A standardized weak lensing benchmark dataset with realistic systematics is released alongside a two-phase ML uncertainty challenge to advance data-efficient and robust cosmological analysis.
Non-Gaussian information from weak lensing data via deep learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Weak lensing maps contain information beyond two-point statistics on small scales. Much recent work has tried to extract this information through a range of different observables or via nonlinear transformations of the lensing field. Here we train and apply a 2D convolutional neural network to simulated noiseless lensing maps covering 96 different cosmological models over a range of {$\Omega_m,\sigma_8$}. Using the area of the confidence contour in the {$\Omega_m,\sigma_8$} plane as a figure-of-merit, derived from simulated convergence maps smoothed on a scale of 1.0 arcmin, we show that the neural network yields $\approx 5 \times$ tighter constraints than the power spectrum, and $\approx 4 \times$ tighter than the lensing peaks. Such gains illustrate the extent to which weak lensing data encode cosmological information not accessible to the power spectrum or even other, non-Gaussian statistics such as lensing peaks.
citation-role summary
background 1
citation-polarity summary
fields
astro-ph.CO 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
AKRA produces the first unbiased kappa maps from HSC Y1 shear catalogs, with simulation tests confirming no bias in power spectrum, variance, skewness, and PDF statistics.
Machine learning techniques can mitigate limitations in traditional weak-lensing analyses and enhance extraction of cosmological information from galaxy imaging surveys.
citing papers explorer
-
FAIR Universe Weak Lensing ML Uncertainty Challenge: Handling Uncertainties and Distribution Shifts for Precision Cosmology
A standardized weak lensing benchmark dataset with realistic systematics is released alongside a two-phase ML uncertainty challenge to advance data-efficient and robust cosmological analysis.
-
The first AKRA mass map reconstruction from HSC Y1 data
AKRA produces the first unbiased kappa maps from HSC Y1 shear catalogs, with simulation tests confirming no bias in power spectrum, variance, skewness, and PDF statistics.
-
Machine-learning applications for weak-lensing cosmology
Machine learning techniques can mitigate limitations in traditional weak-lensing analyses and enhance extraction of cosmological information from galaxy imaging surveys.