Merging is potentially the dominant 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∼3 in all five CANDELS fields (UDS, EGS, GOODS-S, GOODS-N, COSMOS) using deep learning convolutional neural networks trained with simulated galaxies from the IllustrisTNG cosmological simulation. The deep learning architecture used is objectively selected by a Bayesian optimization 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 postmergers. We compare our machine-learning classifications on CANDELS galaxies and compare with visual merger classifications from Kartaltepe et al., and show that they are broadly consistent. We finish by demonstrating that our model is capable of measuring galaxy merger rates, , that are consistent with results found for CANDELS galaxies using close pairs statistics, with. This is the first general agreement between major mergers measured using pairs and structure at z<3.

In this paper we develop a new unsupervised machine learning technique comprising of a feature extractor, a convolutional autoencoder (CAE), and a clustering algorithm consisting of a Bayesian Gaussian mixture model (BGM). We applied 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 seen in the images. Our method successfully picks up ∼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 ± 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 gravitaional lensing systems, but also discuss the limitations and potential future uses of this technique.

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 seven common machine learning methods for galaxy classification (Convolutional Neural Network (CNN), K-nearest neighbour, Logistic Regression, Support Vector Machine, 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 seven methods in our study. Using a sample of ∼2,800 galaxies with visual classification from GZ1, we reach an accuracy of ∼0.99 for the morphological classification of Ellipticals and Spirals. The further investigation of the galaxies that were misclassified but with high predicted probabilities in our CNN reveals the incorrect classification provided by GZ1, and that 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 confirmed ∼2.5% galaxies are misclassified by GZ1 in our study. After correcting these galaxies' label, we improve our CNN performance to an average accuracy of over 0.99 (accuracy of 0.994 is our best result).

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., Sérsic 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 $\sim 87\%$ 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.