Search

We compare the two largest galaxy morphology catalogues, which separate early and late type galaxies at intermediate redshift. The two catalogues were built by applying supervised deep learning (convolutional neural networks, CNNs) to the Dark Energy Survey data down to a magnitude limit of $\sim$21 mag. The methodologies used for the construction of the catalogues include differences such as the cutout sizes, the labels used for training, and the input to the CNN - monochromatic images versus $gri$-band normalized images. In addition, one catalogue is trained using bright galaxies observed with DES ($i<18$), while the other is trained with bright galaxies ($r<17.5$) and `emulated' galaxies up to $r$-band magnitude $22.5$. Despite the different approaches, the agreement between the two catalogues is excellent up to $i<19$, demonstrating that CNN predictions are reliable for samples at least one magnitude fainter than the training sample limit. It also shows that morphological classifications based on monochromatic images are comparable to those based on $gri$-band images, at least in the bright regime. At fainter magnitudes, $i>19$, the overall agreement is good ($\sim$95\%), but is mostly driven by the large spiral fraction in the two catalogues. In contrast, the agreement within the elliptical population is not as good, especially at faint magnitudes. By studying the mismatched cases we are able to identify lenticular galaxies (at least up to $i<19$), which are difficult to distinguish using standard classification approaches. The synergy of both catalogues provides an unique opportunity to select a population of unusual galaxies., Comment: 17 pages, 14 figures (1 appendix for galaxy examples including 3 figures)

We develop a machine learning based algorithm using a convolutional neural network (CNN) to identify low HI column density Ly$\alpha$ absorption systems ($\log{N_{\mathrm{HI}}}/{\rm cm}^{-2}<17$) in the Ly$\alpha$ forest, and predict their physical properties, such as their HI column density ($\log{N}_{\mathrm{HI}}/{\rm cm}^{-2}$), redshift ($z_{\mathrm{HI}}$), and Doppler width ($b_{\mathrm{HI}}$). Our CNN models are trained using simulated spectra (S/N $\simeq10$), and we test their performance on high quality spectra of quasars at redshift $z\sim2.5-2.9$ observed with the High Resolution Echelle Spectrometer on the Keck I telescope. We find that $\sim78\%$ of the systems identified by our algorithm are listed in the manual Voigt profile fitting catalogue. We demonstrate that the performance of our CNN is stable and consistent for all simulated and observed spectra with S/N $\gtrsim10$. Our model can therefore be consistently used to analyse the enormous number of both low and high S/N data available with current and future facilities. Our CNN provides state-of-the-art predictions within the range $12.5\leq\log{N_{\mathrm{HI}}}/\mathrm{cm^{-2}}<15.5$ with a mean absolute error of $\Delta(\log{N}_{\mathrm{HI}}/{\rm cm}^{-2})=0.13$, $\Delta(z_{\mathrm{HI}})=2.7\times{10}^{-5}$, and $\Delta(b_{\mathrm{HI}})=4.1\ \mathrm{km\ s^{-1}}$. The CNN prediction costs $<3$ minutes per model per spectrum with a size of 120\,000 pixels using a laptop computer. We demonstrate that CNNs can significantly increase the efficiency of analysing Ly$\alpha$ forest spectra, and thereby greatly increase the statistics of Ly$\alpha$ absorbers., Comment: 22 pages including 2-pages Appendices, 14 figures plus 4 figures in Appendices. This paper is submitted to MNRAS and has addressed the first referee report

We present in this paper one of the largest galaxy morphological classification catalogues to date, including over 20 million of galaxies, using the Dark Energy Survey (DES) Year 3 data based on Convolutional Neural Networks (CNN). Monochromatic $i$-band DES images with linear, logarithmic, and gradient scales, matched with debiased visual classifications from the Galaxy Zoo 1 (GZ1) catalogue, are used to train our CNN models. With a training set including bright galaxies ($16\le{i}<18$) at low redshift ($z<0.25$), we furthermore investigate the limit of the accuracy of our predictions applied to galaxies at fainter magnitude and at higher redshifts. Our final catalogue covers magnitudes $16\le{i}<21$, and redshifts $z<1.0$, and provides predicted probabilities to two galaxy types -- Ellipticals and Spirals (disk galaxies). Our CNN classifications reveal an accuracy of over 99\% for bright galaxies when comparing with the GZ1 classifications ($i<18$). For fainter galaxies, the visual classification carried out by three of the co-authors shows that the CNN classifier correctly categorises disky galaxies with rounder and blurred features, which humans often incorrectly visually classify as Ellipticals. As a part of the validation, we carry out one of the largest examination of non-parametric methods, including $\sim$100,000 galaxies with the same coverage of magnitude and redshift as the training set from our catalogue. We find that the Gini coefficient is the best single parameter discriminator between Ellipticals and Spirals for this data set., Comment: 23 pages, 15 figures. Accepted by MNRAS

We explore unsupervised machine learning for galaxy morphology analyses using a combination of feature extraction with a vector-quantised variational autoencoder (VQ-VAE) and hierarchical clustering (HC). We propose a new methodology that includes: (1) consideration of the clustering performance simultaneously when learning features from images; (2) allowing for various distance thresholds within the HC algorithm; (3) using the galaxy orientation to determine the number of clusters. This setup provides 27 clusters created with this unsupervised learning which we show are well separated based on galaxy shape and structure (e.g., S\'ersic index, concentration, asymmetry, Gini coefficient). These resulting clusters also correlate well with physical properties such as the colour-magnitude diagram, and span the range of scaling-relations such as mass vs. size amongst the different machine-defined clusters. When we merge these multiple clusters into two large preliminary clusters to provide a binary classification, an accuracy of $\sim87\%$ is reached using an imbalanced dataset, matching real galaxy distributions, which includes 22.7\% early-type galaxies and 77.3\% late-type galaxies. Comparing the given clusters with classic Hubble types (ellipticals, lenticulars, early spirals, late spirals, and irregulars), we show that there is an intrinsic vagueness in visual classification systems, in particular galaxies with transitional features such as lenticulars and early spirals. Based on this, the main result in this work is not how well our unsupervised method matches visual classifications and physical properties, but that the method provides an independent classification that may be more physically meaningful than any visually based ones., Comment: 22 pages, 18 figures. Accepted by MNRAS

Merging is potentially the dominate process in galaxy formation, yet there is still debate about its history over cosmic time. To address this we classify major mergers and measure galaxy merger rates up to z $\sim$ 3 in all five CANDELS fields (UDS, EGS, GOODS-S, GOODS-N, COSMOS) using deep learning convolutional neural networks (CNNs) trained with simulated galaxies from the IllustrisTNG cosmological simulation. The deep learning architecture used is objectively selected by a Bayesian Optmization process over the range of possible hyperparameters. We show that our model can achieve 90% accuracy when classifying mergers from the simulation, and has the additional feature of separating mergers before the infall of stellar masses from post mergers. We compare our machine learning classifications on CANDELS galaxies and compare with visual merger classifications from Kartaltepe et al. (2015), and show that they are broadly consistent. We finish by demonstrating that our model is capable of measuring galaxy merger rates, $\mathcal{R}$, that are consistent with results found for CANDELS galaxies using close pairs statistics, with $\mathcal{R}(z) = 0.02 \pm 0.004 \times (1 +z) ^ {2.76 \pm 0.21}$. This is the first general agreement between major mergers measured using pairs and structure at z < 3., Comment: 22 pages, 13 figures, 3 tables, accepted for publication in ApJ

In this paper we develop a new unsupervised machine learning technique comprised of a feature extractor, a convolutional autoencoder (CAE), and a clustering algorithm consisting of a Bayesian Gaussian mixture model (BGM). We apply this technique to visual band space-based simulated imaging data from the Euclid Space Telescope using data from the Strong Gravitational Lenses Finding Challenge. Our technique promisingly captures a variety of lensing features such as Einstein rings with different radii, distorted arc structures, etc, without using predefined labels. After the clustering process, we obtain several classification clusters separated by different visual features which are seen in the images. Our method successfully picks up $\sim$63\ percent of lensing images from all lenses in the training set. With the assumed probability proposed in this study, this technique reaches an accuracy of $77.25\pm 0.48$\% in binary classification using the training set. Additionally, our unsupervised clustering process can be used as the preliminary classification for future surveys of lenses to efficiently select targets and to speed up the labelling process. As the starting point of the astronomical application using this technique, we not only explore the application to gravitationally lensed systems, but also discuss the limitations and potential future uses of this technique., Comment: 18 pages, 18 figures. Accepted to MNRAS

There are several supervised machine learning methods used for the application of automated morphological classification of galaxies; however, there has not yet been a clear comparison of these different methods using imaging data, or a investigation for maximising their effectiveness. We carry out a comparison between several common machine learning methods for galaxy classification (Convolutional Neural Network (CNN), K-nearest neighbour, Logistic Regression, Support Vector Machine, Random Forest, and Neural Networks) by using Dark Energy Survey (DES) data combined with visual classifications from the Galaxy Zoo 1 project (GZ1). Our goal is to determine the optimal machine learning methods when using imaging data for galaxy classification. We show that CNN is the most successful method of these ten methods in our study. Using a sample of $\sim$2,800 galaxies with visual classification from GZ1, we reach an accuracy of $\sim$0.99 for the morphological classification of Ellipticals and Spirals. The further investigation of the galaxies that have a different ML and visual classification but with high predicted probabilities in our CNN usually reveals an the incorrect classification provided by GZ1. We further find the galaxies having a low probability of being either spirals or ellipticals are visually Lenticulars (S0), demonstrating that supervised learning is able to rediscover that this class of galaxy is distinct from both Es and Spirals. We confirm that $\sim$2.5\% galaxies are misclassified by GZ1 in our study. After correcting these galaxies' labels, we improve our CNN performance to an average accuracy of over 0.99 (accuracy of 0.994 is our best result)., Comment: 20 pages, 19 figures. Accepted to MNRAS