An Astronomical Image Content-based Recommendation System Using Combined Deep Learning Models in a Fully Unsupervised Mode

  title={An Astronomical Image Content-based Recommendation System Using Combined Deep Learning Models in a Fully Unsupervised Mode},
  author={Hossen Teimoorinia and Sara Shishehchi and Ahnaf Tazwar and Ping-Cherng Lin and Finn Archinuk and Stephen D. J. Gwyn and JJ. Kavelaars},
  journal={The Astronomical Journal},
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 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 auto-encoder… 

Data Dimension Reduction makes ML Algorithms efficient

It is demonstrated that pre-processing not only speeds up the algorithms but also improves accuracy in both supervised and unsupervised learning.

Mapping the Diversity of Galaxy Spectra with Deep Unsupervised Machine Learning

Modern spectroscopic surveys of galaxies such as MaNGA consist of millions of diverse spectra covering different regions of thousands of galaxies. We propose and implement a deep unsupervised



MegaCam: the new Canada-France-Hawaii Telescope wide-field imaging camera

MegaCam is an imaging camera with a 1 square degree field of view for the new prime focus of the 3.6 meter Canada-France-Hawaii Telescope. This instrument will mainly be used for large deep surveys

Assessment of Astronomical Images Using Combined Machine-learning Models

This work presents a two-component machine-learning-based approach for classifying astronomical images by data quality via an examination of sources detected in the images and image pixel values from representative sources within those images, and achieves 97% agreement when compared to classification generated via manual image inspection.

Comparison of Multi-Class and Binary Classification Machine Learning Models in Identifying Strong Gravitational Lenses

Using Hubble Space Telescope images, in the F814W filter, the usage of binary and multi-class classification models applied to the lens finding task is compared and it is concluded there is not a significant benefit to using the multi- class model over a binary model.

Self-organized formation of topographically correct feature maps

Galaxy Merger Rates up to z ∼ 3 Using a Bayesian Deep Learning Model: A Major-merger Classifier Using IllustrisTNG Simulation Data

This 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, which is the first general agreement between major mergers measured using pairs and structure at z < 3.

Are galactic star formation and quenching governed by local, global, or environmental phenomena?

We present an analysis of star formation and quenching in the SDSS-IV MaNGA-DR15, utilizing over 5 million spaxels from ∼3500 local galaxies. We estimate star formation rate surface densities

Deep learning predictions of galaxy merger stage and the importance of observational realism

Machine learning is becoming a popular tool to quantify galaxy morphologies and identify mergers. However, this technique relies on using an appropriate set of training data to be successful. By

Radio Galaxy Zoo: Unsupervised Clustering of Convolutionally Auto-encoded Radio-astronomical Images

This paper demonstrates a novel and efficient unsupervised clustering method with the combination of a self-organizing map (SOM) and a convolutional autoencoder capable of accurately separating outliers on a SOM with neighborhood similarity and K-means clustering of radio-astronomical features.

Ground-based and Airborne Instrumentation for Astronomy III