An astronomical image content-based recommendation system using combined deep learning models in a fully unsupervised mode

Abstract

We have developed a method that maps large astronomical images onto a two-dimensional map and clusters them. A combination of various state-of-the-art machine learning (ML) algorithms is used to develop a fully unsupervised image quality assessment and clustering system. Our pipeline consists of a data pre-processing step where individual image objects are identified in a large astronomical image and converted to smaller pixel images. This data is then fed to a deep convolutional autoencoder jointly trained with a self-organizing map (SOM). This part can be used as a recommendation system. The resulting output is eventually mapped onto a two-dimensional grid using a second, deep, SOM. We use data taken from ground-based telescopes and, as a case study, compare the system's ability and performance with the results obtained by supervised methods presented by Teimoorinia et al. (2020). The availability of target labels in this data allowed a comprehensive performance comparison between our unsupervised and supervised methods. In addition to image-quality assessments performed in this project, our method can have various other applications. For example, it can help experts label images in a considerably shorter time with minimum human intervention. It can also be used as a content-based recommendation system capable of filtering images based on the desired content.

arXiv comment25 pages, 18 figures (accepted for publication in The Astronomical Journal)

References in corpus (21)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Activation Functions: Comparison of trends in Practice and Research for Deep Learning
• The Dark Energy Camera
• SDSS Data Management and Photometric Quality Assessment
• Recent Advances in Convolutional Neural Networks
• MegaPipe: the MegaCam image stacking pipeline at the Canadian Astronomical Data Centre
• Are galactic star formation and quenching governed by local, global or environmental phenomena?
• Deep learning predictions of galaxy merger stage and the importance of observational realism
• Finding high-redshift strong lenses in DES using convolutional neural networks
• The Hubble Sequence at $z\sim 0$ in the IllustrisTNG simulation with deep learning
• Galaxy Merger Rates up to z $\sim$ 3 using a Bayesian Deep Learning Model $-$ A Major-Merger classifier using IllustrisTNG Simulation data
• From Principal Subspaces to Principal Components with Linear Autoencoders
• LensExtractor: A Convolutional Neural Network in Search of Strong Gravitational Lenses
• An Artificial Neural Network Approach For Ranking Quenching Parameters In Central Galaxies
• Radio Galaxy Zoo: Unsupervised Clustering of Convolutionally Auto-encoded Radio-astronomical Images
• The infra-red luminosities of ~332,000 SDSS galaxies predicted from artificial neural networks and the Herschel Stripe 82 survey
• Max-Pooling Dropout for Regularization of Convolutional Neural Networks
• Comparison of Multi-Class and Binary Classification Machine Learning Models in Identifying Strong Gravitational Lenses
• Classifying galaxy spectra at 0.5<z<1 with self-organizing maps
• Assessment of astronomical images using combined machine learning models
• Artificial neural network based calibrations for the prediction of galactic [NII] $\lambda$ 6584 and H$\alpha$ line luminosities

Cited by in corpus (2)

• Mapping the Diversity of Galaxy Spectra with Deep Unsupervised Machine Learning
• Self-Supervised Clustering on Image-Subtracted Data with Deep-Embedded Self-Organizing Map