[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127912-en":3,"doc-seo-127912-105":31,"detail-sidebar-cat-0-en-105":92},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},127912,137451207643,"Noah","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Signal-preserving CMB component separation with machine learning","Microwave sky analysis, including cosmic microwave background (CMB) studies, requires reliable component separation across frequencies to isolate distinct signals and suppress contaminants. While blind methods such as internal linear combination (ILC) assume only known frequency dependence, they can underperform when foregrounds are non-Gaussian or statistically anisotropic. A hybrid approach is introduced: an ML model trained on signal-free combinations predicts foregrounds, which are combined with ILC to reduce residual variance without bias. Tests on simulations show improved performance for extragalactic temperature and Galactic polarization, including reduced B-mode residual variance up to a factor of five, with generalization to unseen foreground models.","arXiv :2404 .03557v2 [ astro-ph .CO] 31 Jul 2024  \nSignal-preserving CMB component separation with machine learning  \nFiona McCarthy, 1, 2, 3, ∗ J. Colin Hill,4 William R. Coulton,2, 1, 3 and David W. Hogg3, 5, 6  \n1 DAMTP, Centre for Mathematical Sciences, Wilberforce Road, Cambridge CB3 0WA, UK  \n2 Kavli Institute for Cosmology Cambridge, Madingley Road, Cambridge, CB3 0HA, UK  \n3 Center for Computational Astrophysics, Flatiron Institute, New York, NY, USA 10010  \n4 Department of Physics, Columbia University, New York, NY, USA 10027  \n5 Max-Planck-Institut fur Astronomie, Konigstuhl 17, D-69117 Heidelberg, Germany  \n6 Center for Cosmology and Particle Physics, Department of Physics,  \nNew York University, 726 Broadway, New York, NY 10003, USA  \n(Dated: August 2, 2024)  \nAnalysis of microwave sky signals, such as the cosmic microwave background, often requires component separation using multi-frequency methods, whereby different signals are isolated according to their different frequency behaviors. Many so-called “blind” methods, such as the internal linear combination (ILC), make minimal assumptions about the spatial distribution of the signal or contaminants, and only assume knowledge of the frequency dependence of the signal. The ILC produces a minimum-variance linear combination of the measured frequency maps. In the case of Gaussian, statistically isotropic fields, this is the optimal linear combination, as the variance is the only statistic of interest. However, in many cases the signal we wish to isolate, or the foregrounds we wish to remove, are non-Gaussian and/or statistically anisotropic (in particular for the case of Galactic foregrounds) . In such cases, it is possible that machine learning (ML) techniques can be used to exploit the non-Gaussian features of the foregrounds and thereby improve component separation. However, many ML techniques require the use of complex, difficult-to-interpret operations on the data. We propose a hybrid method whereby we train an ML model using only combinations of the data that do not contain the signal, and combine the resulting ML-predicted foreground estimate with the ILC solution to reduce the error from the ILC. We demonstrate our methods on simulations of extragalactic temperature and Galactic polarization foregrounds, and show that our ML model can exploit non-Gaussian features, such as point sources and spatially-varying spectral indices, to produce lower-variance maps than ILC — e.g., reducing the variance of the B-mode residual by factors of up to 5—while preserving the signal of interest in an unbiased manner. Moreover, we often find improved performance even when applying our ML technique to foreground models on which it was not trained.  \nI. INTRODUCTION  \nWhen we observe the sky, we detect emission from many different sources, including extragalactic and Galactic. A notable example is the measurement of the cosmic microwave background (CMB) radiation at millimeter wavelengths, at which we detect not only the primary CMB but also the Sunyaev–Zel’dovich effect (sourced by the scattering of the CMB from free electrons in late-Universe structures); the cosmic infrared background (CIB); radio emission from extragalactic sources; and various types of radiation from our own Galaxy, including thermal dust radiation, synchrotron, and free-free emission. Much information can be extracted from these signals, but it is necessary tobe able to separate them reliably. The science goals of current and upcoming CMB anisotropy experiments—such as the search for evidence of primordial gravitational waves by the BICEP Array [1], Simons Observatory (SO) [2], CMB-S4 [3], and LiteBIRD [4]—will depend critically on our ability to separate the CMB from foreground signals. To separate them, it is common to use the fact that the different sources exhibit different frequency dependence, quantified through their spectral energy distributions (SEDs) . One can then observe the sky at multiple wave","cbCaiirhe9E9ENKe","https://ap.wps.com/l/cbCaiirhe9E9ENKe","pdf",4004835,2,1,22,"English","en",105,"# Introduction\n## Microwave sky signals and the need for separation\n## Blind multi-frequency methods and ILC optimality\n## Challenges from non-Gaussian and anisotropic foregrounds\n# Hybrid ML-ILC strategy","[{\"question\":\"为什么需要对微波天空信号进行成分分离？\",\"answer\":\"观测中同时包含CMB及多种银河与河外前景信号，必须利用不同频率行为将目标成分可靠隔离，否则会影响科学测量结果。\"},{\"question\":\"ILC 这类“盲法”在什么条件下是最优的？\",\"answer\":\"当数据中的相关成分表现为高斯且统计各向同性时，ILC通过最小化方差得到最优线性组合。\"},{\"question\":\"该文提出的混合机器学习方法如何降低分离误差？\",\"answer\":\"先用不含目标信号的数据组合训练ML预测前景，再与ILC解进行融合，从而利用前景的非高斯特征降低残差方差，同时保持目标信号无偏保留。\"}]","Signal-preserving CMB component separation with machine learning | PDF",1785942911,55,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"signal-preserving-cmb-component-separation-with-machine-learning","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/signal-preserving-cmb-component-separation-with-machine-learning/127912/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-27","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"为什么需要对微波天空信号进行成分分离？","Question",{"text":76,"@type":77},"观测中同时包含CMB及多种银河与河外前景信号，必须利用不同频率行为将目标成分可靠隔离，否则会影响科学测量结果。","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"ILC 这类“盲法”在什么条件下是最优的？",{"text":81,"@type":77},"当数据中的相关成分表现为高斯且统计各向同性时，ILC通过最小化方差得到最优线性组合。",{"name":83,"@type":74,"acceptedAnswer":84},"该文提出的混合机器学习方法如何降低分离误差？",{"text":85,"@type":77},"先用不含目标信号的数据组合训练ML预测前景，再与ILC解进行融合，从而利用前景的非高斯特征降低残差方差，同时保持目标信号无偏保留。","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]