Galaxy shape measurement with convolutional neural networks

Ribli, Dezső; Dobos, László; Csabai, István

doi:10.1093/mnras/stz2374

Cited by 13 publications

(7 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, it has been possible to apply machine learning techniques to a wide variety of astronomical problems for which observations indeed provide more information than theoretical models. Recent work has included the use of t-SNE to derive stellar chemical abundances (Anders et al 2018) and spectral information (Traven et al 2017), as well as the use of Convolutional Neural Networks to measure galaxy morphology (Dieleman et al 2015;Domínguez Sánchez et al 2018;Cheng et al 2019;Hausen & Robertson 2019) and shape (Ribli et al 2019), perform light profile fitting (Tuccillo et al 2018), identify mergers (Bottrell et al 2019), estimate cluster masses (Ho et al 2019), and classify supernovae (Muthukrishna et al 2019).…”

Section: Introductionmentioning

confidence: 99%

A Method to Distinguish Quiescent and Dusty Star-forming Galaxies with Machine Learning

Steinhardt¹,

Weaver²,

Maxfield

et al. 2020

ApJ

View full text Add to dashboard Cite

Large photometric surveys provide a rich source of observations of quiescent galaxies, including a surprisingly large population at z > 1. However, identifying large, but clean, samples of quiescent galaxies has proven difficult because of their near-degeneracy with interlopers such as dusty, starforming galaxies. We describe a new technique for selecting quiescent galaxies based upon t-distributed stochastic neighbor embedding (t-SNE), an unsupervised machine learning algorithm for dimensionality reduction. This t-SNE selection provides an improvement both over UVJ, removing interlopers which otherwise would pass color selection, and over photometric template fitting, more strongly towards high redshift. Due to the similarity between the colors of high-and low-redshift quiescent galaxies, under our assumptions t-SNE outperforms template fitting in 63% of trials at redshifts where a large training sample already exists. It also may be able to select quiescent galaxies more efficiently at higher redshifts than the training sample.

show abstract

Section: Introductionmentioning

confidence: 99%

A Method to Distinguish Quiescent and Dusty Star-forming Galaxies with Machine Learning

Steinhardt¹,

Weaver²,

Maxfield

et al. 2020

ApJ

View full text Add to dashboard Cite

show abstract

“…It is crucial therefore that no v el methods are developed, as well as existing methods refined, and that these are used to compare and verify shear estimates from different shape measurement pipelines. More recently, ML and, in particular, ANNs, have been applied to this task, with promising results (Gruen et al 2010 ;Ribli, Dobos & Csabai 2019 ;Tewes et al 2019 ;Zhang et al 2023 ). In this work, we hav e e xplored the potential of CNNs in precision shear measurement; in particular, employing a shallow network an MSB loss function, we have quantified the sensitivity of shear biases to the accuracy of the PSF model and, separately, the fidelity of the galaxy population, simulated in the training sets.…”

Section: Discussion a N D F U T U R E W O R Kmentioning

confidence: 99%

Impact of PSF misestimation and galaxy population bias on precision shear measurement using a CNN

Voigt

2024

Monthly Notices of the Royal Astronomical Society

View full text Add to dashboard Cite

Weak gravitational lensing of distant galaxies provides a powerful probe of dark energy. The aim of this study is to investigate the application of convolutional neural networks (CNNs) to precision shear estimation. In particular, using a shallow CNN, we explore the impact of point spread function (PSF) misestimation and ‘galaxy population bias’ (including ‘distribution bias’ and ‘morphology bias’), focusing on the accuracy requirements of next generation surveys. We simulate a population of noisy disk and elliptical galaxies and adopt a PSF that is representative of a Euclid-like survey. We quantify the accuracy achieved by the CNN assuming a linear relationship between the estimated and true shears and measure the multiplicative (m) and additive (c) biases. We make use of an unconventional loss function to mitigate the effects of noise bias and measure m and c when we use either: (i) an incorrect galaxy ellipticity distribution or size–magnitude relation, or the wrong ratio of morphological types, to describe the population of galaxies (distribution bias); (ii) an incorrect galaxy light profile (morphology bias); or (iii) a PSF with size or ellipticity offset from its true value (PSF misestimation). We compare our results to the Euclid requirements on the knowledge of the PSF model shape and size. Finally, we outline further work to build on the promising potential of CNNs in precision shear estimation.

show abstract

“…A CNN has been used to infer shape information directly from images at the pixel level. Ribli et al (2019a) developed a 13-layer CNN to measure galaxy shapes and apply it to the DES Y1 catalog, showing better consistency with CFHTLenS shapes. Multilayer fully-connected NNs have been used to emulate the relation between shear bias and observed galaxy properties.…”

Section: Introductionmentioning

confidence: 99%

FORKLENS: Accurate weak-lensing shear measurement with deep learning

Zhang,

Shan,

et al. 2024

A&A

View full text Add to dashboard Cite

Weak gravitational lensing is one of the most important probes of the nature of dark matter and dark energy. In order to extract cosmological information from next-generation weak lensing surveys (e.g. Euclid Roman LSST, and CSST) as much as possible, accurate measurements of weak lensing shear are required. There are existing algorithms to measure the weak lensing shear on imaging data, which have been successfully applied in previous surveys. In the meantime, machine learning (ML) has been widely recognized in various astrophysics applications in modeling and observations. In this work, we present a fully deep-learning-based approach to measuring weak lensing shear accurately. Our approach comprises two modules. The first one contains a convolutional neural network (CNN) with two branches for taking galaxy images and point spread function (PSF) simultaneously, and the output of this module includes the galaxy's magnitude, size, and shape. The second module includes a multiple-layer neural network (NN) to calibrate weak-lensing shear measurements. We name the program Forklens and make it publicly available online. Applying Forklens to CSST-like mock images, we achieve consistent accuracy with traditional approaches (such as moment-based measurement and forward model fitting) on the sources with high signal-to-noise ratios (S/N, > 20). For the sources with S/N < 10 Forklens exhibits an $ 36<!PCT!>$ higher Pearson coefficient on galaxy ellipticity measurements. After adopting galaxy weighting, the shear measurements with Forklens deliver accuracy levels to 0.2<!PCT!>. The whole procedure of Forklens is automated and costs about $0.7$ milliseconds per galaxy, which is appropriate for adequately taking advantage of the sky coverage and depth of the upcoming weak lensing surveys.

show abstract

Galaxy shape measurement with convolutional neural networks

Cited by 13 publications

References 60 publications

A Method to Distinguish Quiescent and Dusty Star-forming Galaxies with Machine Learning

A Method to Distinguish Quiescent and Dusty Star-forming Galaxies with Machine Learning

Impact of PSF misestimation and galaxy population bias on precision shear measurement using a CNN

FORKLENS: Accurate weak-lensing shear measurement with deep learning

Contact Info

Product

Resources

About