Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userGenerative deep fields: arbitrarily sized, random synthetic astronomical images through deep learning
106
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
Generative Adversarial Networks (GANs) are a class of artificial neural network that can produce realistic, but artificial, images that resemble those in a training set. In typical GAN architectures these images are small, but a variant known as Spatial-GANs (SGANs) can generate arbitrarily large images, provided training images exhibit some level of periodicity. Deep extragalactic imaging surveys meet this criteria due to the cosmological tenet of isotropy. Here we train an SGAN to generate images resembling the iconic Hubble Space Telescope eXtreme Deep Field (XDF). We show that the properties of galaxies in generated images have a high level of fidelity with galaxies in the real XDF in terms of abundance, morphology, magnitude distributions and colours. As a demonstration we have generated a 7.6-billion pixel generative deep field spanning 1.45 degrees. The technique can be generalised to any appropriate imaging training set, offering a new purely data-driven approach for producing realistic mock surveys and synthetic data at scale, in astrophysics and beyond.
rate research
Read More
Knowing the redshift of galaxies is one of the first requirements of many cosmological experiments, and as its 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 which 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-filter (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%) over the traditional Random Forest (RF), and the model performed even better at lower redshifts achieving a MSE=0.0007 (a 50% improvement over the RF) in the range of z<0.3. This method could be hugely beneficial to upcoming surveys such as the Vera C. Rubin Observatorys Legacy Survey of Space and Time (LSST) which will require vast numbers of photo-z estimates produced as quickly and accurately as possible.
With the advent of future big-data surveys, automated tools for unsupervised discovery are becoming ever more necessary. In this work, we explore the ability of deep generative networks for detecting outliers in astronomical imaging datasets. The main advantage of such generative models is that they are able to learn complex representations directly from the pixel space. Therefore, these methods enable us to look for subtle morphological deviations which are typically missed by more traditional moment-based approaches. We use a generative model to learn a representation of expected data defined by the training set and then look for deviations from the learned representation by looking for the best reconstruction of a given object. In this first proof-of-concept work, we apply our method to two different test cases. We first show that from a set of simulated galaxies, we are able to detect $sim90%$ of merging galaxies if we train our network only with a sample of isolated ones. We then explore how the presented approach can be used to compare observations and hydrodynamic simulations by identifying observed galaxies not well represented in the models.
We present AstroVaDEr, a variational autoencoder designed to perform unsupervised clustering and synthetic image generation using astronomical imaging catalogues. The model is a convolutional neural network that learns to embed images into a low dimensional latent space, and simultaneously optimises a Gaussian Mixture Model (GMM) on the embedded vectors to cluster the training data. By utilising variational inference, we are able to use the learned GMM as a statistical prior on the latent space to facilitate random sampling and generation of synthetic images. We demonstrate AstroVaDErs capabilities by training it on gray-scaled textit{gri} images from the Sloan Digital Sky Survey, using a sample of galaxies that are classified by Galaxy Zoo 2. An unsupervised clustering model is found which separates galaxies based on learned morphological features such as axis ratio, surface brightness profile, orientation and the presence of companions. We use the learned mixture model to generate synthetic images of galaxies based on the morphological profiles of the Gaussian components. AstroVaDEr succeeds in producing a morphological classification scheme from unlabelled data, but unexpectedly places high importance on the presence of companion objects---demonstrating the importance of human interpretation. The network is scalable and flexible, allowing for larger datasets to be classified, or different kinds of imaging data. We also demonstrate the generative properties of the model, which allow for realistic synthetic images of galaxies to be sampled from the learned classification scheme. These can be used to create synthetic image catalogs or to perform image processing tasks such as deblending.
In real-world applications, it is often expensive and time-consuming to obtain labeled examples. In such cases, knowledge transfer from related domains, where labels are abundant, could greatly reduce the need for extensive labeling efforts. In this scenario, transfer learning comes in hand. In this paper, we propose Deep Variational Transfer (DVT), a variational autoencoder that transfers knowledge across domains using a shared latent Gaussian mixture model. Thanks to the combination of a semi-supervised ELBO and parameters sharing across domains, we are able to simultaneously: (i) align all supervised examples of the same class into the same latent Gaussian Mixture component, independently from their domain; (ii) predict the class of unsupervised examples from different domains and use them to better model the occurring shifts. We perform tests on MNIST and USPS digits datasets, showing DVTs ability to perform transfer learning across heterogeneous datasets. Additionally, we present DVTs top classification performances on the MNIST semi-supervised learning challenge. We further validate DVT on a astronomical datasets. DVT achieves states-of-the-art classification performances, transferring knowledge across real stars surveys datasets, EROS, MACHO and HiTS, . In the worst performance, we double the achieved F1-score for rare classes. These experiments show DVTs ability to tackle all major challenges posed by transfer learning: different covariate distributions, different and highly imbalanced class distributions and different feature spaces.
We introduce QuasarNET, a deep convolutional neural network that performs classification and redshift estimation of astrophysical spectra with human-expert accuracy. We pose these two tasks as a emph{feature detection} problem: presence or absence of spectral features determines the class, and their wavelength determines the redshift, very much like human-experts proceed. When ran on BOSS data to identify quasars through their emission lines, QuasarNET defines a sample $99.51pm0.03$% pure and $99.52pm0.03$% complete, well above the requirements of many analyses using these data. QuasarNET significantly reduces the problem of line-confusion that induces catastrophic redshift failures to below 0.2%. We also extend QuasarNET to classify spectra with broad absorption line (BAL) features, achieving an accuracy of $98.0pm0.4$% for recognizing BAL and $97.0pm0.2$% for rejecting non-BAL quasars. QuasarNET is trained on data of low signal-to-noise and medium resolution, typical of current and future astrophysical surveys, and could be easily applied to classify spectra from current and upcoming surveys such as eBOSS, DESI and 4MOST.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
