Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Automatic detection of cataclysmic variables from SDSS images

Journal Article · · Publications of the Astronomical Society of Australia
DOI:https://doi.org/10.1017/pasa.2023.34· OSTI ID:2425110

Abstract

Investigating rare and new objects have always been an important direction in astronomy. Cataclysmic variables (CVs) are ideal and natural celestial bodies for studying the accretion process of semi-detached binaries with accretion processes. However, the sample size of CVs must increase because a lager gap exists between the observational and the theoretical expanding CVs. Astronomy has entered the big data era and can provide massive images containing CV candidates. CVs as a type of faint celestial objects, are highly challenging to be identified directly from images using automatic manners. Deep learning has rapidly developed in intelligent image processing and has been widely applied in some astronomical fields with excellent detection results. YOLOX, as the latest YOLO framework, is advantageous in detecting small and dark targets. This work proposes an improved YOLOX-based framework according to the characteristics of CVs and Sloan Digital Sky Survey (SDSS) photometric images to train and verify the model to realise CV detection. We use the Convolutional Block Attention Module to increase the number of output features with the feature extraction network and adjust the feature fusion network to obtain fused features. Accordingly, the loss function is modified. Experimental results demonstrate that the improved model produces satisfactory results, with average accuracy (mean averagePrecisionat 0.5) of 92.0%,Precisionof 92.9%,Recallof 94.3%, and$F1-score$of 93.6% on the test set. The proposed method can efficiently achieve the identification of CVs in test samples and search for CV candidates in unlabeled images. The image data vastly outnumber the spectra in the SDSS-released data. With supplementary follow-up observations or spectra, the proposed model can help astronomers in seeking and detecting CVs in a new manner to ensure that a more extensive CV catalog can be built. The proposed model may also be applied to the detection of other kinds of celestial objects.

Research Organization:
US Department of Energy (USDOE), Washington, DC (United States). Office of Science, Sloan Digital Sky Survey (SDSS)
Sponsoring Organization:
USDOE
OSTI ID:
2425110
Journal Information:
Publications of the Astronomical Society of Australia, Journal Name: Publications of the Astronomical Society of Australia Vol. 40; ISSN 1323-3580
Publisher:
CSIRO
Country of Publication:
United States
Language:
English

References (20)

The Catalina Real-time Transient Survey journal September 2011
Extended Feature Pyramid Network for Small Object Detection journal January 2022
Deep learning journal May 2015
Cataclysmic Variables from Sloan Digital Sky Survey. V. The Fifth Year (2004) journal February 2006
A catalog and atlas of cataclysmic variables journal February 1993
Cataclysmic Variables from Sloan Digital Sky Survey. VI. The Sixth Year (2005) journal May 2007
The Pascal Visual Object Classes Challenge: A Retrospective journal June 2014
Cataclysmic Variables from the Sloan Digital Sky Survey. III. The Third Year journal October 2004
Cataclysmic Variables from The Sloan Digital Sky Survey. I. The First Results journal January 2002
Spectroscopically Identified Cataclysmic Variables from the LAMOST Survey. I. The Sample journal January 2020
Cataclysmic variables from the Catalina Real-time Transient Survey journal May 2014
Cataclysmic Variables from Sloan Digital Sky Survey. IV. The Fourth Year (2003) journal May 2005
Cataclysmic Variables from Sdss. vii. the Seventh year (2006) journal March 2009
Ratio Sum Versus Sum Ratio for Linear Discriminant Analysis journal December 2022
CBAM: Convolutional Block Attention Module book January 2018
Cataclysmic variables based on the stellar spectral survey LAMOST DR3 journal June 2018
Cataclysmic Variable Stars book January 2009
Automatic Search of Cataclysmic Variables Based on LightGBM in LAMOST-DR7 journal November 2021
Interpolation revisited [medical images application] journal July 2000
Cataclysmic Variables from the Sloan Digital Sky Survey. II. The Second Year journal September 2003

Similar Records

A data-driven method for modelling dissipation rates in stratified turbulence
Journal Article · 2023 · Journal of Fluid Mechanics · OSTI ID:2246688

Finite orbit width effects in large aspect ratio stellarators
Journal Article · 2022 · Journal of Plasma Physics · OSTI ID:1896539

Development of compact tokamak fusion reactor use cases to inform future transport studies
Journal Article · 2023 · Journal of Plasma Physics · OSTI ID:1997428

Related Subjects