Identifying strong lenses with unsupervised machine learning using convolutional autoencoder

Cheng, Ting-Yun; Li, Nan; Conselice, Christopher J.; Aragón-Salamanca, Alfonso; Dye, S.; Metcalf, R. Benton

doi:10.1093/mnras/staa1015

Cited by 71 publications

(68 citation statements)

References 111 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are currently several types of astronomical studies that apply unsupervised machine learning techniques to images which reach reasonable results, including: galaxy morphology (Hocking et al 2018;Martin et al 2020), strong lensing identification (Cheng et al 2020), and anomaly detection (Xiong et al 2018;Margalef-Bentabol et al 2020). For example, Hocking et al (2018) and Martin et al (2020) apply a technique called Growing Neural Gas algorithm (Fritzke 1994), which is a type of Self-organising Map (SOM, Kohonen 1997), to extract features from images.…”

Section: Introductionmentioning

confidence: 99%

“…These features are then connected with a hierarchical clustering algorithm (Hastie et al 2009). On the other hand, Cheng et al (2020) use a fundamentally different approach by using a convolutional autoencoder (Masci et al 2011), which includes an architecture of convolutional neural networks, for feature extraction. This method connects the extracted features with a Bayesian Gaussian mixture model from which a clustering analysis can be done.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Beyond the hubble sequence – exploring galaxy morphology with unsupervised machine learning

Cheng

Huertas-Company

Conselice

et al. 2021

Monthly Notices of the Royal Astronomical Society

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Beyond the hubble sequence – exploring galaxy morphology with unsupervised machine learning

Cheng

Huertas-Company

Conselice

et al. 2021

Monthly Notices of the Royal Astronomical Society

Self Cite

View full text Add to dashboard Cite

show abstract

“…Several CNN searches for new strong lens candidates have focused on ground-based imaging data, from the CFHTLS (Jacobs et al 2017), KiDS DR3 (Petrillo et al 2017) and DR4 (Petrillo et al 2019;Li et al 2020), DES Year 3 (Jacobs et al 2019b,a), or the DESI DECam Legacy survey (Huang et al 2020a). Efficient classification pipelines using deep neural networks have also been developed and tested on simulated Euclid and LSST images to prepare for these forthcoming surveys which will tremendously increase the number of detectable strong lensing systems (Lanusse et al 2018;Schaefer et al 2018;Davies et al 2019;Cheng et al 2020;Avestruz et al 2019).…”

Section: Introductionmentioning

confidence: 99%

Holismokes

Cañameras

Schuldt

Suyu

et al. 2020

A&A

View full text Add to dashboard Cite

We present a systematic search for wide-separation (with Einstein radius θE ≳ 1.5″), galaxy-scale strong lenses in the 30 000 deg2 of the Pan-STARRS 3π survey on the Northern sky. With long time delays of a few days to weeks, these types of systems are particularly well-suited for catching strongly lensed supernovae with spatially-resolved multiple images and offer new insights on early-phase supernova spectroscopy and cosmography. We produced a set of realistic simulations by painting lensed COSMOS sources on Pan-STARRS image cutouts of lens luminous red galaxies (LRGs) with redshift and velocity dispersion known from the sloan digital sky survey (SDSS). First, we computed the photometry of mock lenses in gri bands and applied a simple catalog-level neural network to identify a sample of 1 050 207 galaxies with similar colors and magnitudes as the mocks. Second, we trained a convolutional neural network (CNN) on Pan-STARRS gri image cutouts to classify this sample and obtain sets of 105 760 and 12 382 lens candidates with scores of pCNN > 0.5 and > 0.9, respectively. Extensive tests showed that CNN performances rely heavily on the design of lens simulations and the choice of negative examples for training, but little on the network architecture. The CNN correctly classified 14 out of 16 test lenses, which are previously confirmed lens systems above the detection limit of Pan-STARRS. Finally, we visually inspected all galaxies with pCNN > 0.9 to assemble a final set of 330 high-quality newly-discovered lens candidates while recovering 23 published systems. For a subset, SDSS spectroscopy on the lens central regions proves that our method correctly identifies lens LRGs at z ∼ 0.1–0.7. Five spectra also show robust signatures of high-redshift background sources, and Pan-STARRS imaging confirms one of them as a quadruply-imaged red source at zs = 1.185, which is likely a recently quenched galaxy strongly lensed by a foreground LRG at zd = 0.3155. In the future, high-resolution imaging and spectroscopic follow-up will be required to validate Pan-STARRS lens candidates and derive strong lensing models. We also expect that the efficient and automated two-step classification method presented in this paper will be applicable to the ∼4 mag deeper gri stacks from the Rubin Observatory Legacy Survey of Space and Time (LSST) with minor adjustments.

show abstract

“…Autoencoders prove to be a reliable form of dimensionality reduction, which allows for unsupervised clustering algorithms to be used on data sets that would otherwise be too complex. For example, Cheng et al (2020) employ an autoencoder with convolutional layers to learn a latent representation from a data set of simulated gravitational lens imaging, which is then used to perform Bayesian Mixture Modelling to build a clustering and classification scheme for determining if a given image contains a gravitational lens. Note that there exist applications of autoencoders that embed the clustering process within the network itself.…”

Section: Autoencodersmentioning

confidence: 99%

“…However, recent work has shown that unsupervised learning methods also perform well at visually classifying astronomical objects. Cheng et al (2020) used a Convolutional Autoencoder (CAE), paired with Bayesian Gaussian Mixture Models (GMMs), to successfully construct a classifier for strong gravitational lenses. Ralph et al (2019) also exploited CAEs, combining the feature extraction capability of the autoencoder with a Self-Organised Map and k-means clustering to identify different classes of radio galaxy morphology.…”

Section: Introductionmentioning

confidence: 99%

AstroVaDEr: astronomical variational deep embedder for unsupervised morphological classification of galaxies and synthetic image generation

Spindler

Smith

2020

Monthly Notices of the Royal Astronomical Society

View full text Add to dashboard Cite

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 AstroVaDEr’s capabilities by training it on gray-scaled 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.

show abstract

Identifying strong lenses with unsupervised machine learning using convolutional autoencoder

Cited by 71 publications

References 111 publications

Beyond the hubble sequence – exploring galaxy morphology with unsupervised machine learning

Beyond the hubble sequence – exploring galaxy morphology with unsupervised machine learning

Holismokes

AstroVaDEr: astronomical variational deep embedder for unsupervised morphological classification of galaxies and synthetic image generation

Contact Info

Product

Resources

About