[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119738-en":3,"doc-seo-119738-105":30,"detail-sidebar-cat-0-en-105":84},{"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":20,"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},119738,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697",8,"Research & Report","Machine Learning and galaxy morphology - for what purpose","Galaxy morphology classification traditionally relies on visual inspection of galaxy images, but the scale of forthcoming surveys makes this approach impractical. Deep learning and other machine-learning methods have been proposed to automate the task, yet their outputs appear to shift away from classical Hubble-style morphological paradigms. This work tests how clustering algorithms respond to image features that may not map directly to established morphological schemes, while still yielding meaningful physical insight.","arXiv :2306 .02626v1 [ astro-ph .GA] 5 Jun 2023  \nMachine Learning and galaxy morphology: for what purpose?  \nD. Fraix-Burnet 1 ★  \n1 Univ. Grenoble Alpes, CNRS, IPAG, Grenoble, France  \nReceived May 15, 2023; accepted  \nABSTRACT  \nClassification of galaxies is traditionally associated with their morphologies through visual inspection of images. The amount of data to come renders this task inhuman and Machine Learning (mainly Deep Learning) has been called to the rescue for more thana decade. However, the results look mitigate and there seems to be a shift away from the paradigm of the traditional morphological classification of galaxies. In this paper, I want to show that the algorithms indeed are very sensitive to the features present in images, features that do not necessarily correspond to the Hubble or de Vaucouleurs vision of a galaxy. However, this does not preclude to get the correct insights into the physics of galaxies. I have applied a state-of-the-art \"traditional\" Machine Learning clustering tool, called Fisher-EM, a latent discriminant subspace Gaussian Mixture Model algorithm, to 4458 galaxies carefully classified into 18 types by the EFIGI project. The optimum number of clusters given by the Integrated Complete Likelihood criterion is 47 . The correspondence with the EFIGI classification is correct, but it appears that the Fisher-EM algorithm gives a great importance to the distribution of light which translates to characteristics such as the bulge to disk ratio, the inclination or the presence of foreground stars. The discrimination of some physical parameters (bulge-to-total luminosity ratio, (􀀗 − 􀀫)􀀩 , intrinsic diameter, presence of flocculence or dust, arm strength) is very comparable in the two classifications.  \nKey words: methods: statistical – methods: data analysis – galaxies: general – galaxies: structure – techniques: image processing  \n1 INTRODUCTION  \nThe original Hubble morphological classification (Hubble 1926) has four categories: ellipticals, spirals, barred spirals and irregulars. Later, more sophisticated classifications were designed. Schutter & Shamir (2015) provides a thorough history of morphological classification with the detailed nomenclatures that have been introduced. All these classifications come from visual inspection of images in the visible domain. Apart from the original Hubble scheme, the best known classification is the numerical T-type imagined by de Vaucouleurs (1963) and used in the RC3 catalog with 18 stages (e.g. Baillard et al. 2011) .  \nIt has long been recognised that huge surveys require an automatic classification of the images of galaxies. Machine Learning generates alot of hopes and in particular the supervised Deep Learning approach seems appropriate. Unfortunately, this requires large and reliable training samples. Astronomers being too few, the idea of citizen science emerged.  \nGalaxy Zoo 1 (Lintott et al. 2008) considered six classes (ellipticals, spiral clockwise and anticlockwise, edge-on spirals, merger, and star/artefact) that can be easily identified by eye from non experts. Following the success of this first attempt, the Galaxy Zoo 2 project (Willett et al. 2013) went further and proposed a decision tree with 11 tasks leading to the identification of 37 features. It is thus more detailed than the de Vaucouleurs classification but noticeably departs from the traditional way to classify galaxies. Actually, the Galaxy Zoo 2 project proposes a description of more than 300 000 images of galaxies, with a median of 44 citizen-classifications per  \n★ didier.fraix-burnet@univ-grenoble-alpes.fr  \ngalaxy. It seems difficult to extend this kind of work to build a larger training sample suited for the billions of images that will soon populate the data bases (Fielding et al. 2022) unless we call on myriad‘micro-workers’ that support Artificial Intelligence in other domains (e.g. Tubaro et al. 2020) .  \nIn the EFIGI project (Baillard et al. 2011), a small group of astronomers performe","cbCairqmy8cGfgIA","https://ap.wps.com/l/cbCairqmy8cGfgIA","pdf",933961,1,18,"English","en",105,"# Abstract\n# Introduction\n## Classical morphological classification\n## Survey-driven automation and citizen science\n## EFIGI dataset and expert dispersion\n## Supervised learning limits with many classes","[{\"question\":\"How is Fisher-EM applied and what does it emphasize?\",\"answer\":\"Fisher-EM clustering is applied to 4458 EFIGI-classified galaxies, and its cluster structure matches the EFIGI classification. The method highlights light distribution-related characteristics such as bulge-to-disk ratio, inclination, and the presence of foreground stars.\"}]","Machine Learning and galaxy morphology - for what purpose | PDF",1785726036,45,{"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":79,"head_meta":81,"extra_data":83,"updated_unix":28},"machine-learning-and-galaxy-morphology-for-what-purpose","",{"@graph":36,"@context":78},[37,54,69],{"@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/machine-learning-and-galaxy-morphology-for-what-purpose/119738/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-03",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72],{"name":73,"@type":74,"acceptedAnswer":75},"How is Fisher-EM applied and what does it emphasize?","Question",{"text":76,"@type":77},"Fisher-EM clustering is applied to 4458 EFIGI-classified galaxies, and its cluster structure matches the EFIGI classification. The method highlights light distribution-related characteristics such as bulge-to-disk ratio, inclination, and the presence of foreground stars.","Answer","https://schema.org",{"og:url":52,"og:type":80,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":82,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":85},[86,90,94,98,103,108,113,116,121,124,128],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":87,"show_sort_weight":88,"slug":89},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":91,"show_sort_weight":92,"slug":93},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Exam",70,"exam",{"id":99,"doc_module":4,"doc_module_name":46,"category_name":100,"show_sort_weight":101,"slug":102},5,"Comic",60,"comic",{"id":104,"doc_module":4,"doc_module_name":46,"category_name":105,"show_sort_weight":106,"slug":107},6,"Technology",50,"technology",{"id":109,"doc_module":4,"doc_module_name":46,"category_name":110,"show_sort_weight":111,"slug":112},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":114,"slug":115},30,"research-report",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},9,"Religion & Spirituality",20,"religion-spirituality",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":122,"show_sort_weight":119,"slug":123},"World Cup","world-cup",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":125,"slug":127},10,"Lifestyle","lifestyle",{"id":129,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":99,"slug":131},19,"General","general"]