Stellar Cluster Detection using GMM with Deep Variational Autoencoder
arXiv:1809.01434 · doi:10.1109/RAICS.2018.8634903
Abstract
Detecting stellar clusters have always been an important research problem in Astronomy. Although images do not convey very detailed information in detecting stellar density enhancements, we attempt to understand if new machine learning techniques can reveal patterns that would assist in drawing better inferences from the available image data. This paper describes an unsupervised approach in detecting star clusters using Deep Variational Autoencoder combined with a Gaussian Mixture Model. We show that our method works significantly well in comparison with state-of-the-art detection algorithm in recognizing a variety of star clusters even in the presence of noise and distortion.
5 pages, 7 figures, under review in IEEE RAICS 2018
References in corpus (12)
- The UKIDSS Galactic Plane Survey
- Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
- Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
- The UKIRT Infrared Deep Sky Survey Early Data Release
- The Spitzer Gould Belt Survey of Large Nearby Interstellar Clouds: Discovery of a Dense Embedded Cluster in the Serpens-Aquila Rift
- An Application of Deep Neural Networks in the Analysis of Stellar Spectra
- Structure and mass segregation in Galactic stellar clusters
- Identifying star clusters in a field: A comparison of different algorithms
- Star formation around the HII region Sh2-235
- Galaxy clusters at 0.6 < z < 1.4 in the UKIDSS Ultra Deep Survey Early Data Release
- A MST algorithm for source detection in gamma-ray images
- A multiwavelength study of the massive star forming region IRAS 06055+2039 (RAFGL 5179)