Three-dimensional wide-field galaxy surveys are fundamental for cosmological studies. For higher redshifts (z ≳ 1.0), where galaxies are too faint, quasars still trace the large-scale structure of the Universe. Since available telescope time limits spectroscopic surveys, photometric methods are efficient for estimating redshifts for many quasars. Recently, machine-learning methods are increasingly successful for quasar photometric redshifts, however, they hinge on the distribution of the training set. Therefore, a rigorous estimation of reliability is critical. We extracted optical and infrared photometric data from the cross-matched catalogue of the WISE All-Sky and PS1 3$\pi$ DR2 sky surveys. We trained an XGBoost regressor and an artificial neural network on the relation between colour indices and spectroscopic redshift. We approximated the effective training set coverage with the K-nearest neighbours algorithm. We estimated reliable photometric redshifts of 2 562 878 quasars which overlap with the training set in feature space. We validated the derived redshifts with an independent, clustering-based redshift estimation technique. The final catalogue is publicly available.
Studies of cosmology, galaxy evolution, and astronomical transients with current and next-generation wide-field imaging surveys like the Rubin Observatory Legacy Survey of Space and Time are all critically dependent on estimates of photometric redshifts. Capsule networks are a new type of neural network architecture that is better suited for identifying morphological features of the input images than traditional convolutional neural networks. We use a deep capsule network trained on ugriz images, spectroscopic redshifts, and Galaxy Zoo spiral/elliptical classifications of ∼400 000 Sloan Digital Sky Survey galaxies to do photometric redshift estimation. We achieve a photometric redshift prediction accuracy and a fraction of catastrophic outliers that are comparable to or better than current methods for SDSS main galaxy sample-like data sets (r ≤ 17.8 and zspec ≤ 0.4) while requiring less data and fewer trainable parameters. Furthermore, the decision-making of our capsule network is much more easily interpretable as capsules act as a low-dimensional encoding of the image. When the capsules are projected on a two-dimensional manifold, they form a single redshift sequence with the fraction of spirals in a region exhibiting a gradient roughly perpendicular to the redshift sequence. We perturb encodings of real galaxy images in this low-dimensional space to create synthetic galaxy images that demonstrate the image properties (e.g. size, orientation, and surface brightness) encoded by each dimension. We also measure correlations between galaxy properties (e.g. magnitudes, colours, and stellar mass) and each capsule dimension. We publicly release our code, estimated redshifts, and additional catalogues at https://biprateep.github.io/encapZulate-1.
more » « less- Award ID(s):
- 2009251
- NSF-PAR ID:
- 10369625
- Publisher / Repository:
- Oxford University Press
- Date Published:
- Journal Name:
- Monthly Notices of the Royal Astronomical Society
- Volume:
- 515
- Issue:
- 4
- ISSN:
- 0035-8711
- Page Range / eLocation ID:
- p. 5285-5305
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
ABSTRACT -
null (Ed.)We present a new prospective analysis of deep multi-band imaging with the James Webb Space Telescope (JWST). In this work, we investigate the recovery of high-redshift 5 < z < 12 galaxies through extensive image simulations of accepted JWST programs, including the Early Release Science in the EGS field and the Guaranteed Time Observations in the HUDF. We introduced complete samples of ∼300 000 galaxies with stellar masses of log( M * / M ⊙ ) > 6 and redshifts of 0 < z < 15, as well as galactic stars, into realistic mock NIRCam, MIRI, and HST images to properly describe the impact of source blending. We extracted the photometry of the detected sources, as in real images, and estimated the physical properties of galaxies through spectral energy distribution fitting. We find that the photometric redshifts are primarily limited by the availability of blue-band and near-infrared medium-band imaging. The stellar masses and star formation rates are recovered within 0.25 and 0.3 dex, respectively, for galaxies with accurate photometric redshifts. Brown dwarfs contaminating the z > 5 galaxy samples can be reduced to < 0.01 arcmin −2 with a limited impact on galaxy completeness. We investigate multiple high-redshift galaxy selection techniques and find that the best compromise between completeness and purity at 5 < z < 10 using the full redshift posterior probability distributions. In the EGS field, the galaxy completeness remains higher than 50% at magnitudes m UV < 27.5 and at all redshifts, and the purity is maintained above 80 and 60% at z ≤ 7 and 10, respectively. The faint-end slope of the galaxy UV luminosity function is recovered with a precision of 0.1–0.25, and the cosmic star formation rate density within 0.1 dex. We argue in favor of additional observing programs covering larger areas to better constrain the bright end.more » « less
-
more » « less
ABSTRACT Knowing the redshift of galaxies is one of the first requirements of many cosmological experiments, and as it is impossible to perform spectroscopy for every galaxy being observed, photometric redshift (photo-z) estimations are still of particular interest. Here, we investigate different deep learning methods for obtaining photo-z estimates directly from images, comparing these with ‘traditional’ machine learning algorithms which make use of magnitudes retrieved through photometry. As well as testing a convolutional neural network (CNN) and inception-module CNN, we introduce a novel mixed-input model that allows for both images and magnitude data to be used in the same model as a way of further improving the estimated redshifts. We also perform benchmarking as a way of demonstrating the performance and scalability of the different algorithms. The data used in the study comes entirely from the Sloan Digital Sky Survey (SDSS) from which 1 million galaxies were used, each having 5-filtre (ugriz) images with complete photometry and a spectroscopic redshift which was taken as the ground truth. The mixed-input inception CNN achieved a mean squared error (MSE) =0.009, which was a significant improvement ($30{{\ \rm per\ cent}}$) over the traditional random forest (RF), and the model performed even better at lower redshifts achieving a MSE = 0.0007 (a $50{{\ \rm per\ cent}}$ improvement over the RF) in the range of z < 0.3. This method could be hugely beneficial to upcoming surveys, such as Euclid and the Vera C. Rubin Observatory’s Legacy Survey of Space and Time (LSST), which will require vast numbers of photo-z estimates produced as quickly and accurately as possible.
-
ABSTRACT As part of the cosmology analysis using Type Ia Supernovae (SN Ia) in the Dark Energy Survey (DES), we present photometrically identified SN Ia samples using multiband light curves and host galaxy redshifts. For this analysis, we use the photometric classification framework SuperNNovatrained on realistic DES-like simulations. For reliable classification, we process the DES SN programme (DES-SN) data and introduce improvements to the classifier architecture, obtaining classification accuracies of more than 98 per cent on simulations. This is the first SN classification to make use of ensemble methods, resulting in more robust samples. Using photometry, host galaxy redshifts, and a classification probability requirement, we identify 1863 SNe Ia from which we select 1484 cosmology-grade SNe Ia spanning the redshift range of 0.07 < z < 1.14. We find good agreement between the light-curve properties of the photometrically selected sample and simulations. Additionally, we create similar SN Ia samples using two types of Bayesian Neural Network classifiers that provide uncertainties on the classification probabilities. We test the feasibility of using these uncertainties as indicators for out-of-distribution candidates and model confidence. Finally, we discuss the implications of photometric samples and classification methods for future surveys such as Vera C. Rubin Observatory Legacy Survey of Space and Time.more » « less
-
null (Ed.)Convolutional neural networks (CNNs) have become a key asset to most of fields in AI. Despite their successful performance, CNNs suffer from a major drawback. They fail to capture the hierarchy of spatial relation among different parts of an entity. As a remedy to this problem, the idea of capsules was proposed by Hinton. In this paper, we propose the SubSpace Capsule Network (SCN) that exploits the idea of capsule networks to model possible variations in the appearance or implicitly-defined properties of an entity through a group of capsule subspaces instead of simply grouping neurons to create capsules. A capsule is created by projecting an input feature vector from a lower layer onto the capsule subspace using a learnable transformation. This transformation finds the degree of alignment of the input with the properties modeled by the capsule subspace.We show that SCN is a general capsule network that can successfully be applied to both discriminative and generative models without incurring computational overhead compared to CNN during test time. Effectiveness of SCN is evaluated through a comprehensive set of experiments on supervised image classification, semi-supervised image classification and high-resolution image generation tasks using the generative adversarial network (GAN) framework. SCN significantly improves the performance of the baseline models in all 3 tasks.more » « less
