Stellar Cluster Detection using GMM with Deep Variational Autoencoder
This addresses the challenge of detecting stellar clusters in astronomy, which is important for astronomical research, but appears incremental as it combines existing techniques.
The paper tackles the problem of detecting stellar clusters in astronomical images by developing an unsupervised approach combining a Deep Variational Autoencoder with a Gaussian Mixture Model, showing it works significantly well compared to state-of-the-art detection algorithms in recognizing various star clusters even with noise and distortion.
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.