J/A+A/621/A36 Shear measurement with machine learning code (Tewes+, 2019)
Weak-lensing shear measurement with machine learning.
Teaching artificial neural networks about feature noise.
Tewes M., Kuntzer T., Nakajima R., Courbin F., Hildebrandt H., Schrabback T.
<Astron. Astrophys. 621, A36 (2019)>
=2019A&A...621A..36T 2019A&A...621A..36T (SIMBAD/NED BibCode)
ADC_Keywords: Models ; Gravitational lensing
Keywords: methods: data analysis - gravitational lensing: weak -
cosmological parameters
Abstract:
Cosmic shear, that is weak gravitational lensing by the large-scale
matter structure of the Universe, is a primary cosmological probe for
several present and upcoming surveys investigating dark matter and
dark energy, such as Euclid or WFIRST. The probe requires an extremely
accurate measurement of the shapes of millions of galaxies based on
imaging data. Crucially, the shear measurement must address and
compensate for a range of interwoven nuisance effects related to the
instrument optics and detector, noise in the images, unknown galaxy
morphologies, colors, blending of sources, and selection effects. This
paper explores the use of supervised machine learning as a tool to
solve this inverse problem. We present a simple architecture that
learns to regress shear point estimates and weights via shallow
artificial neural networks. The networks are trained on simulations of
the forward observing process, and take combinations of moments of the
galaxy images as inputs. A challenging peculiarity of the shear
measurement task, in terms of machine learning applications, is the
combination of the noisiness of the input features and the
requirements on the statistical accuracy of the inverse regression. To
address this issue, the proposed training algorithm minimizes bias
over multiple realizations of individual source galaxies, reducing the
sensitivity to properties of the overall sample of source galaxies.
Importantly, an observational selection function of these source
galaxies can be straightforwardly taken into account via the weights.
We first introduce key aspects of our approach using toy-model
simulations, and then demonstrate its potential on images mimicking
Euclid data. Finally, we analyze images from the GREAT3 challenge,
obtaining competitively low multiplicative and additive shear biases
despite the use of a simple training set. We conclude that the further
development of suited machine learning approaches is of high interest
to meet the stringent requirements on the shear measurement in current
and future surveys. We make a demonstration implementation of our
technique publicly available.
Description:
The python code accompanying our paper is split into two packages.
"Tenbilac" is a simple artificial neural network library implementing
the peculiar distinction between training cases and realizations, in
python and numpy.
"MomentsML" is a toolbox for experimenting with shear and shape
estimators, build around GalSim and Astropy. It includes a simple
wrapper to process GREAT3 data, and an interface to tenbilac.
These packages provide a demonstration implementation of the
algorithms described in the paper. They are oriented towards
experimentation rather than being optimized for integration into a
shear analysis pipeline. Instructions on how to install and use the
packages are provided in the included README.md files. In particular,
to reproduce the results and figures from the paper, see the section
"Getting started" in the README.md inside of the momentsml directory.
Potential updates and extensions to these codes will be described at
https://astro.uni-bonn.de/~mtewes/ml-shear-meas/
File Summary:
--------------------------------------------------------------------------------
FileName Lrecl Records Explanations
--------------------------------------------------------------------------------
ReadMe 80 . This file
momentsml_tenbilac.tar 2237 28271 The code accompanying the paper
--------------------------------------------------------------------------------
Acknowledgements:
Malte Tewes, mtewes(at)astro.uni-bonn.de
Thibault Kuntzer, thibault.kuntzer(at)epfl.ch
(End) Patricia Vannier [CDS] 21-Nov-2018