[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124431-en":3,"doc-seo-124431-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124431,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","Preparation for CSST - Star-Galaxy Classification using a Rotationally-invariant Supervised Machine-learning Method","Precise star–galaxy differentiation is essential for precision cosmology because cross-contamination between samples can bias astrophysical measurements, especially as upcoming wide-field surveys observe immense numbers of objects. This study develops a supervised machine-learning approach using a rotationally-invariant pipeline: denoised images are unwrapped into polar coordinates and combined with noise reduction preprocessing, then classified with GoogLeNet. Training and validation are split 8:2 to assess performance on COSMOS data, reaching 99.6% for stars and 99.9% for galaxies, with preprocessing improving accuracy by ~2.0%–6.0% under rotation. The method is also evaluated on CSST simulation data, achieving ~99.8% accuracy for future CSST observations.","arXiv :2409 . 13296v1 [ astro-ph .GA] 20 Sep 2024  \nResearch in Astronomy and Astrophysics manuscript no.  \n(LATEX: RAA-2024-0205.tex; printed on September 23, 2024; 0:26)  \nPreparation for CSST: Star-Galaxy Classification using a Rotationally-invariant Supervised Machine-learning Method  \nShiliang Zhang 1 , Guanwen Fang 1 , Jie Song2 ,3 , Ran Li4 , Yizhou Gu5 , Zesen Lin6 , Chichun Zhou7 , Yao Dai 1 and Xu Kong2 ,3  \n1 Institute of Astronomy and Astrophysics, Anqing Normal University, Anqing, 246133, China; [wen@mail.ustc.edu.cn](wen@mail.ustc.edu.cn) ;  \n2 Deep Space Exploration Laboratory/Department of Astronomy, University of Science and Technology of China, Hefei, 230026, China; [xkong@ustc.edu.cn](xkong@ustc.edu.cn) ;  \n3 School of Astronomy and Space Science, University of Science and Technology of China, Hefei, 230026, China;  \n4 National Astronomical Observatories, Chinese Academy of Sciences, Beijing, 100101, PR China;  \n5 Tsung-Dao Lee Institute and Key Laboratory for Particle Physics, Astrophysics and Cosmology, Ministry of Education, Shanghai Jiao Tong University, Shanghai, 200240, China;  \n6 Department of Physics, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong, S.A.R., China;  \n7 School of Engineering, Dali University, Dali, 671003, China;  \nAbstract 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%  \n2 Shiliang Zhang et al.  \nand 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.  \nKey words: methods: data analysis—techniques: image processing—stars: imaging  \n1 INTRODUCTION  \nIn astronomy, precise differentiation between stars and galaxies is paramount due to their representation of distinct astrophysical phenomena. For instance, the systematic contribution resulting from the crosscontamination of star and galaxy samples could significantly impact the field of “precision cosmology”(e.g., Ross et al. 2011; Thomas et al. 2011; Soumagnac et al. 2015; Sevilla-Noarbe et al. 2018) . This issue will become increasingly critical in future astronomical research, as the upcoming large-field sky surveys, such as those conducted by the Chinese Space Station Telescope (CSST) (Zhan, 2011, 2018), the Euclid Space Telescope (Euclid Collaboration et al., 2022), and the Roman Space Telescope (Spergel et al., 2015), will yield imaging of millions to billions of stars and galaxies. This necessitates the development of methods to accurately and rapidly distinguish between stars and galaxies.  \nSeveral methods are currently available to address this issue. The first classification method is morphology-based, involving the determination of an optimal threshold in the space of observable image properties (e.g., MacGillivray et al. 1976; Kron 1980; Le","cbCaigy2eYuLe33U","https://ap.wps.com/l/cbCaigy2eYuLe33U","pdf",1652147,1,22,"English","en",105,"# Abstract\n# Key words\n# Introduction\n## Motivation and challenge of cross-contamination\n## Morphology-based and color-based classification methods\n## Limitations of reduced features and role of CNNs\n## Background of machine learning approaches","[{\"question\":\"Why is accurate star–galaxy classification important for astronomy?\",\"answer\":\"Cross-contamination between star and galaxy samples can significantly affect precision cosmology results. As upcoming surveys observe vast numbers of objects, the need for accurate and efficient classification becomes increasingly critical.\"},{\"question\":\"What supervised model and preprocessing strategy does the method use?\",\"answer\":\"The study employs a supervised machine-learning model, GoogLeNet, and adds preprocessing steps such as noise reduction and unwrapping denoised images in polar coordinates to incorporate rotational invariance.\"},{\"question\":\"How effective is the approach on COSMOS and CSST simulation data?\",\"answer\":\"On COSMOS, the model achieves about 99.6% accuracy for stars and 99.9% for galaxies. With preprocessing, accuracy improves by roughly 2.0% to 6.0% when images are rotated, and on CSST simulation data the accuracy is about 99.8%.\"}]","Preparation for CSST - Star-Galaxy Classification using a Rotationally-invariant Supervised Machine-learning Method | PDF",1785822267,55,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"preparation-for-csst-star-galaxy-classification-using-a-rotationally-invariant-supervised-machine-learning-method","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/preparation-for-csst-star-galaxy-classification-using-a-rotationally-invariant-supervised-machine-learning-method/124431/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is accurate star–galaxy classification important for astronomy?","Question",{"text":75,"@type":76},"Cross-contamination between star and galaxy samples can significantly affect precision cosmology results. As upcoming surveys observe vast numbers of objects, the need for accurate and efficient classification becomes increasingly critical.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What supervised model and preprocessing strategy does the method use?",{"text":80,"@type":76},"The study employs a supervised machine-learning model, GoogLeNet, and adds preprocessing steps such as noise reduction and unwrapping denoised images in polar coordinates to incorporate rotational invariance.",{"name":82,"@type":73,"acceptedAnswer":83},"How effective is the approach on COSMOS and CSST simulation data?",{"text":84,"@type":76},"On COSMOS, the model achieves about 99.6% accuracy for stars and 99.9% for galaxies. With preprocessing, accuracy improves by roughly 2.0% to 6.0% when images are rotated, and on CSST simulation data the accuracy is about 99.8%.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]