Preparation for CSST: Star-galaxy Classification using a Rotationally Invariant Supervised Machine Learning Method
arXiv:2409.13296 · doi:10.1088/1674-4527/ad6fe6
Abstract
Most existing star-galaxy classifiers depend on the reduced information from catalogs, necessitating careful data processing and feature extraction. In this study, we employ a supervised machine learning method (GoogLeNet) to automatically classify stars and galaxies in the COSMOS field. Unlike traditional machine learning methods, we introduce several preprocessing techniques, including noise reduction and the unwrapping of denoised images in polar coordinates, applied to our carefully selected samples of stars and galaxies. By dividing the selected samples into training and validation sets in an 8:2 ratio, we evaluate the performance of the GoogLeNet model in distinguishing between stars and galaxies. The results indicate that the GoogLeNet model is highly effective, achieving accuracies of 99.6% and 99.9% for stars and galaxies, respectively. Furthermore, by comparing the results with and without preprocessing, we find that preprocessing can significantly improve classification accuracy (by approximately 2.0% to 6.0%) when the images are rotated. In preparation for the future launch of the China Space Station Telescope (CSST), we also evaluate the performance of the GoogLeNet model on the CSST simulation data. These results demonstrate a high level of accuracy (approximately 99.8%), indicating that this model can be effectively utilized for future observations with the CSST.
11 pages, 9 figures, published in Research in Astronomy and Astrophysics, Volume 24, Number 9 (2024)
References in corpus (36)
- Gaia Data Release 3: Summary of the content and survey properties
- The Cosmic Evolution Survey (COSMOS) -- Overview
- EAZY: A Fast, Public Photometric Redshift Code
- Accurate photometric redshifts for the CFHT Legacy Survey calibrated using the VIMOS VLT Deep Survey
- Gaia Early Data Release 3: The astrometric solution
- The COSMOS2015 Catalog: Exploring the 1<z<6 Universe with half a million galaxies
- 3D-HST WFC3-selected Photometric Catalogs in the Five CANDELS/3D-HST Fields: Photometry, Photometric Redshifts and Stellar Masses
- Rotation-invariant convolutional neural networks for galaxy morphology prediction
- The COSMOS Survey: Hubble Space Telescope / Advanced Camera for Surveys (HST/ACS) Observations and Data Processing
- COSMOS2020: A panchromatic view of the Universe to from two complementary catalogs
- Weak Gravitational Lensing with COSMOS: Galaxy Selection and Shape Measurements
- Galaxia: a code to generate a synthetic survey of the Milky Way
- A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
- Star-galaxy Classification Using Deep Convolutional Neural Networks
- Ameliorating Systematic Uncertainties in the Angular Clustering of Galaxies: A Study using SDSS-III
- Galaxy And Mass Assembly (GAMA): The input catalogue and star-galaxy separation
- Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection
- Robust Machine Learning Applied to Astronomical Datasets I: Star-Galaxy Classification of the SDSS DR3 Using Decision Trees
- Decision Tree Classifiers for Star/Galaxy Separation
- A large accretion disk of extreme eccentricity in the TDE ASASSN-14li
- Star/galaxy separation at faint magnitudes: Application to a simulated Dark Energy Survey
- Excess Clustering on Large Scales in the MegaZ DR7 Photometric Redshift Survey
- Identification of Low Surface Brightness Tidal Features in Galaxies Using Convolutional Neural Networks
- Star-Galaxy Classification in Multi-Band Optical Imaging
- Resolution-independent modeling of environmental effects in semi-analytic models of galaxy formation that include ram-pressure stripping of both hot and cold gas
- J-PLUS: Morphological star/galaxy classification by PDF analysis
- A Hybrid Ensemble Learning Approach to Star-Galaxy Classification
- A Census of Object Types and Redshift Estimates in the SDSS Photometric Catalog from a Trained Decision-Tree Classifier
- Star-galaxy classification in the Dark Energy Survey Y1 dataset
- The Photometric Classification Server for Pan-STARRS1
- Automatic Classification of Galaxy Morphology: a rotationally invariant supervised machine learning method based on the UML-dataset
- Full-sky ray-tracing simulation of weak lensing using ELUCID simulations: exploring galaxy intrinsic alignment and cosmic shear correlations
- Effect of training characteristics on object classification: an application using Boosted Decision Trees
- The numbers of z~2 star-forming and passive galaxies in 2.5 square degrees of deep CFHT imaging
- Starduster: A multi-wavelength SED model based on radiative transfer simulations and deep learning
- Simulation of CSSTs astrometric capability