[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124707-en":3,"doc-seo-124707-105":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},124707,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Supervised machine learning on Galactic filaments - Revealing the filamentary structure of the Galactic interstellar medium","Context. Filaments pervade the Milky Way and act as birthplaces of stars, making reliable detection essential for understanding star-formation processes. Aims. The work tests whether supervised machine learning can identify filamentary structures over the entire Galactic plane. Methods. Using two UNet-based segmentation networks, trained on Herschel Hi-GAL H2 column-density images with filament skeleton labels plus background and missing-data masks, eight training scenarios were evaluated. Results show improved pixel recovery by a factor of 2–7 versus the input skeletons, revealing additional low-contrast filaments. Conclusions. The study demonstrates robust proof-of-concept capabilities, enabling discovery of low-density structures previously unseen.","A&A 669, A120 (2023)  \n[https://doi.org/10.1051/0004-6361/202244103](https://doi.org/10.1051/0004-6361/202244103)[ ](https://doi.org/10.1051/0004-6361/202244103)© A. Zavagno et al. 2023  \n&~~t~~ronomy~~t~~rop~~h~~ys~~i~~cs  \nSupervised machine learning on Galactic filaments Revealing the filamentary structure of the Galactic interstellar medium  \nA. Zavagno 1 , 2 , F.-X. Dupé3 , ⋆ , S. Bensaid 1 , 3 , ⋆ , E. Schisano4 , G. Li Causi4 , M. Gray 1 , S. Molinari4 , D. Elia4 , J.-C. Lambert 1 , M. Brescia5 , D. Arzoumanian 1 , 6 , D. Russeil 1 , G. Riccio5 , and S. Cavuoti5  \n1 Aix-Marseille Univ, CNRS, CNES, LAM, 38 rue F. Joliot-Curie, 13013 Marseille, France e-mail: [annie.zavagno@lam.fr](annie.zavagno@lam.fr)  \n2 Institut Universitaire de France, Paris, France  \n3 Aix-Marseille Univ, CNRS, LIS, Ecole Centrale Marseille, 38 rue F. Joliot-Curie, 13013 Marseille, France  \n4 INAF-IAPS, via del Fosso del Cavaliere 100, 00133 Roma, Italy  \n5 INAF – Astronomical Observatory of Capodimonte, via Moiariello 16, 80131, Napoli, Italy  \n6 Division of Science, National Astronomical Observatory of Japan, 2-21-1 Osawa, Mitaka, Tokyo 181-8588, Japan  \nReceived 24 May 2022 / Accepted 20 November 2022  \nABSTRACT  \nContext. Filaments are ubiquitous in the Galaxy, and they host star formation. Detecting them in a reliable way is therefore key towards our understanding of the star formation process.  \nAims. We explore whether supervised machine learning can identify filamentary structures on the whole Galactic plane.  \nMethods. We used two versions of UNet-based networks for image segmentation. We used H2 column density images of the Galactic plane obtained with Herschel Hi-GAL data as input data. We trained the UNet-based networks with skeletons (spine plus branches) of filaments that were extracted from these images, together with background and missing data masks that we produced. We tested eight training scenarios to determine the best scenario for our astrophysical purpose of classifying pixels as filaments.  \nResults. The training of the UNets allows us to create a new image of the Galactic plane by segmentation in which pixels belonging to filamentary structures are identified. With this new method, we classify more pixels (more by a factor of 2 to 7, depending on the classification threshold used) as belonging to filaments than the spine plus branches structures we used as input. New structures are revealed, which are mainly low-contrast filaments that were not detected before. We use standard metrics to evaluate the performances of the different training scenarios. This allows us to demonstrate the robustness of the method and to determine an optimal threshold value that maximizes the recovery of the input labelled pixel classification.  \nConclusions. This proof-of-concept study shows that supervised machine learning can reveal filamentary structures that are present throughout the Galactic plane. The detection of these structures, including low-density and low-contrast structures that have never been seen before, offers important perspectives for the study of these filaments.  \nKey words. methods: statistical – stars: formation – ISM: general 1. Introduction  \nThe Herschel infrared Galactic Plane Survey, Hi-GAL (Molinari et al. 2010), revealed that the cold and warm interstellar medium (ISM) is organized in a network of filaments in which star formation is generally observed above a density threshold corresponding to AV =7 mag (André et al. 2014 ; Könyves et al. 2020) . The most massive stars are formed atthe junction of the densest filaments, called hubs (Kumar et al. 2020) . Because filaments host star formation and link the organization of the interstellar matter to the future star formation, studying them is central to our understanding of all properties related to star formation, such as the initial mass function, the star formation rate, and the star formation efficiency. Filaments are therefore extensively studied with observations ","cbCainEqLpPNrsCB","https://ap.wps.com/l/cbCainEqLpPNrsCB","pdf",8998803,1,23,"English","en",105,"# Abstract\n## Context and Aims\n## Methods\n## Results\n## Conclusions","[{\"question\":\"What is the main goal of the supervised machine learning study?\",\"answer\":\"To determine whether supervised machine learning can reliably identify filamentary structures across the whole Galactic plane using input data from Herschel Hi-GAL.\"},{\"question\":\"How were the filamentary structures learned and evaluated?\",\"answer\":\"Two UNet-based image segmentation networks were trained on H2 column-density maps using filament skeleton labels, along with background and missing-data masks, and eight training scenarios were tested using standard performance metrics.\"},{\"question\":\"What improvements and new structures does the method produce?\",\"answer\":\"The UNet segmentation classifies substantially more filament pixels than the skeleton structures used as input (by a factor of 2 to 7, depending on the threshold), and it reveals new mainly low-contrast filaments not previously detected.\"}]","Supervised machine learning on Galactic filaments - Revealing the filamentary structure of the Galactic interstellar medium | PDF",1785894026,58,{"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},"supervised-machine-learning-on-galactic-filaments-revealing-the-filamentary-structure-of-the-galactic-interstellar-medium","",{"@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/supervised-machine-learning-on-galactic-filaments-revealing-the-filamentary-structure-of-the-galactic-interstellar-medium/124707/",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","2026-08-05",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},"What is the main goal of the supervised machine learning study?","Question",{"text":75,"@type":76},"To determine whether supervised machine learning can reliably identify filamentary structures across the whole Galactic plane using input data from Herschel Hi-GAL.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were the filamentary structures learned and evaluated?",{"text":80,"@type":76},"Two UNet-based image segmentation networks were trained on H2 column-density maps using filament skeleton labels, along with background and missing-data masks, and eight training scenarios were tested using standard performance metrics.",{"name":82,"@type":73,"acceptedAnswer":83},"What improvements and new structures does the method produce?",{"text":84,"@type":76},"The UNet segmentation classifies substantially more filament pixels than the skeleton structures used as input (by a factor of 2 to 7, depending on the threshold), and it reveals new mainly low-contrast filaments not previously detected.","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"]