[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122656-en":3,"doc-seo-122656-105":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},122656,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697",8,"Research & Report","Constraining Below-threshold Radio Source Counts With Machine Learning","Machine-learning technique determines the number density of radio sources versus flux density for next-generation radio surveys. A convolutional neural network is trained on simulated radio-sky realizations, using supervised learning across a broad family of number-count models that extend to fluxes down to 100 times below the source-detection threshold. The approach predicts source counts in multiple flux bins, while reconstruction quality and predictive uncertainties are benchmarked on dedicated test simulations. Strong performance is shown for fluxes as low as ten times below threshold, demonstrating deep-learning usefulness for future radio astronomy analyses.","arXiv :2306 . 15720v1 [ astro-ph .IM] 27 Jun 2023  \n.  \nConstraining Below-threshold Radio Source Counts With Machine Learning  \nElisa Todarelloa;b Andre Sca􀀎dib;c;d Marco Regisa;b Marco TaosobaDipartimento di Fisica, Universit􀀒a di Torino, Via P. Giuria 1, 10125 Torino, Italy bIstituto Nazionale di Fisica Nucleare, Sezione di Torino, Via P. Giuria 1, 10125 Torino,  \nItaly  \nc Scuola Internazionale Superiore di Studi Avanzati (SISSA), via Bonomea 265, 34136 Trieste, Italy  \ndINFN, Sezione di Trieste, via Valerio 2, 34127 Trieste, Italy  \nE-mail: elisamaria.todarello@unito.it, asca􀀎d@sissa.it, marco.regis@unito.it, [marco.taoso@to.infn.it](marco.taoso@to.infn.it)  \nAbstract. We propose a machine-learning-based technique to determine the number density of radio sources as a function of their 􀀍ux density, for use in next-generation radio surveys. The method uses a convolutional neural network trained on simulations of the radio sky to predict the number of sources in several 􀀍ux bins. To train the network, we adopt a supervised approach wherein we simulate training data stemming from a large domain of possible number count models going down to 􀀍uxes a factor of 100 below the threshold for source detection. We test the model reconstruction capabilities as well as benchmark the expected uncertainties in the model predictions, observing good performance for 􀀍uxes down to a factor of ten below the threshold. This work demonstrates that the capabilities of simple deep learning models for radio astronomy can be useful tools for future surveys.  \nContents  \n1 Introduction 1  \n2 Model architecture 2  \n3 Data sets 3  \n3.1 Simulation pipeline 3  \n3.2 Train and test sets 5  \n3.3 Labels 7  \n4 Results 7  \n4.1 Reconstruction accuracy 9  \n4.2 Uncertainty estimation 11  \n4.3 Veri􀀌cation of model generalization 13  \n5 Conclusions and outlook 13  \n1 Introduction  \nThe determination of the number density of radio sources as a function of their 􀀍ux density has been central in the understanding of the nature and evolution of extragalactic radio sources for more than 60 years [1] . At radio frequencies, cosmological studies have been  \nheavily based on debating source counts and the contribution of sources to the sky brightness temperature.  \nIn the faintest regime, the connection of counts with the isotropic radio background is somewhat puzzling. Indeed, an apparent bright high Galactic latitude di􀀋use radio zero level has been reported by di􀀋erent experiments (see [2] for a recent review) . The ARCADE 2 collaboration highlighted the fact that such emission is signi􀀌cantly brighter than expected contributions both of Galactic and extragalactic origin [3] . The isotropic component that can be isolated from radio images after subtracting foreground Galactic emission is a factor of a few larger than the total contribution obtained from extrapolating the number counts of extragalactic sources in the faint (observationally unreached) brightness regime.  \nIt is well known that relevant statistical information about below-threshold cosmological source populations residing in our Universe can be inferred by studying 􀀍uctuations in astronomical images, in particular, from pixels that do not belong to detected sources [1, 4{7] . A widely used approach is to compute the n-point correlation functions (with n from 1 up to 3 or 4) and from them to infer the number density of sources as a function of 􀀍ux and cosmological redshift. For radio interferometric images, these computations are \\disturbed\"by the fact that the space of the physical description (i.e., the celestial sphere) does not correspond to the \\space\" where data are taken (as for any interferometer) . The link is given by a Fourier transform, and di􀀋erent physical angular scales are mixed in the data. Radio imaging is nowadays well studied and developed to tackle this issue, nevertheless, there area few intrinsic limitations (e.g., observationally, one cannot access all the scales needed in the transfo","cbCailIf5PP4hogA","https://ap.wps.com/l/cbCailIf5PP4hogA","pdf",1376140,1,16,"English","en",105,"# Introduction\n## Motivation and background\n## Machine-learning motivation\n# Model architecture\n## CNN image input design\n# Data sets\n## Simulation pipeline\n## Train and test sets\n## Labels\n# Results\n## Reconstruction accuracy\n## Uncertainty estimation\n## Model generalization verification\n# Conclusions and outlook","[{\"question\":\"What problem does the paper address in radio astronomy?\",\"answer\":\"It targets how to infer the number density of radio sources as a function of flux density even below the detection threshold, where traditional approaches are challenged.\"},{\"question\":\"How does the proposed method estimate radio source counts?\",\"answer\":\"It uses a convolutional neural network trained on simulations of the radio sky to predict source numbers across multiple flux bins.\"},{\"question\":\"How does the study evaluate performance and uncertainty?\",\"answer\":\"It tests reconstruction capabilities and benchmarks expected uncertainties on simulated test sets, including assessment of how well the model generalizes.\"}]","Constraining Below-threshold Radio Source Counts With Machine Learning | PDF",1785811995,40,{"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},"constraining-below-threshold-radio-source-counts-with-machine-learning","",{"@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/constraining-below-threshold-radio-source-counts-with-machine-learning/122656/",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},"What problem does the paper address in radio astronomy?","Question",{"text":75,"@type":76},"It targets how to infer the number density of radio sources as a function of flux density even below the detection threshold, where traditional approaches are challenged.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method estimate radio source counts?",{"text":80,"@type":76},"It uses a convolutional neural network trained on simulations of the radio sky to predict source numbers across multiple flux bins.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the study evaluate performance and uncertainty?",{"text":84,"@type":76},"It tests reconstruction capabilities and benchmarks expected uncertainties on simulated test sets, including assessment of how well the model generalizes.","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},[93,97,101,105,110,115,119,122,127,130,134],{"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":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]