[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118269-en":3,"doc-seo-118269-105":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},118269,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","kSZ Pairwise Velocity Reconstruction with Machine Learning","kSZ pairwise peculiar velocity correlations for galaxy clusters can be reconstructed directly from the kinematic Sunyaev-Zel’dovich imprint in the CMB using a gradient boosting machine-learning model. The model learns from six to seven cluster features tied to CMB and large-scale structure observables, and is validated under realistic conditions including primary CMB contamination, detector noise, and uncertainties in cluster mass and center location. The resulting pairwise velocity statistics enable cosmological constraints on dark energy, modified gravity, and massive neutrinos with upcoming CMB and galaxy surveys.","kSZ Pairwise Velocity Reconstruction with Machine Learning  \narXiv :2403 .04664v2 [ astro-ph .CO] 14 Jun 2024  \nYulin Gong 1 and Rachel Bean 1  \n1 Department of Astronomy, Cornell University, Ithaca, NY 14853, USA  \nWe demonstrate that pairwise peculiar velocity correlations for galaxy clusters can be directly reconstructed from the kinematic Sunyaev-Zel’dovich (kSZ) signature imprinted in the CMB using a machine learning model with a gradient boosting algorithm trained on high-fidelity kSZ simulations. The machine learning model is trained using six to seven cluster features that are directly related to observables from CMB and large-scale structure surveys. We validate the capabilities of the approach in light of the presence of primary CMB, detector noise, and potential uncertainties in the cluster mass estimate and cluster center location. The pairwise velocity statistics extracted using the techniques developed here have the potential to elicit valuable cosmological constraints on dark energy, modified gravity models, and massive neutrinos with kSZ measurements from upcoming CMB surveys, including the Simons Observatory, CMB-S4 and CCAT, and the DESI and SDSS galaxy surveys.  \nI. INTRODUCTION  \nThe origin of accelerated cosmic expansion remains a critical outstanding problem in physics. Measurements ofthe cosmic microwave background (CMB) radiation [1–8], Baryon acoustic oscillations (BAO) (e.g. [9–14]) and type 1a supernovae (e.g. [15–18]) together provide exquisite constraints on the expansion history of the universe. This expansion history is consistent with the standard cosmological model, which assumes General Relativity (GR) and a cosmological constant,Λ, the simplest form of dark energy, as the component of the cosmic matter density proposed to explain the accelerated expansion of the universe (e.g. [19–22]) . Given the fine-tuning and coincidence problems [23–31] related to the discordance between the observed value of Λ and those naturally predicted from theory, modifications of gravity, beyond GR, have also been actively considered as alternative explanations for the accelerated expansion (e.g. see [32] for a review) . Such modifications can be developed to match a ΛCDM expansion history but concurrently predict differences in the growth and dynamical properties of inhomogeneities, probed through the clustering and dynamical properties of large-scale structure (LSS), galaxies and clusters of galaxies (e.g. [32–38]) .  \nIn the context of this paper, we focus on the use of the dynamics of galaxy clusters as a cosmological tracer of the underlying gravitational field. Galaxy clusters can be detected observationally through unique signatures left in CMB photons when they interact with the hot gas of a galaxy cluster, the Sunyaev-Zel’dovich (SZ) effect. The SZ effect occurs when CMB photons interact with electrons in galaxy clusters and can be separated into two principle components: the thermal Sunyaev-Zel’dovich effect (tSZ) and the kinematic SunyaevZel’dovich effect (kSZ) [39–41](and see reviews [42, 43]) . The tSZ is caused by the hot electrons with random velocities boosting the blackbody spectrum imprinting a characteristic frequency dependent-signature that facilitates its isolation from the CMB through multi-frequency measurements. The kSZ is produced by the peculiar (bulk) line of sight motion of a galaxy cluster creating a Doppler shift of the CMB spectrum, and is one order of magnitude smaller than the tSZ effect and largely frequency-independent making it harder to extract.  \nThe kSZ signature is an observational tracer of the underly-  \ning peculiar velocities of clusters and, in turn, the gravitational potential [44–47] . The gravitational attraction between pairs of clusters creates inherent in-fall towards each other. This gravitational attraction leads to a pairwise correlation statistic that can provide a potentially sensitive measurement of the large-scale velocity field [48–51] .  \nDespite the com","cbCaijJYX2O7hbOP","https://ap.wps.com/l/cbCaijJYX2O7hbOP","pdf",727168,1,17,"English","en",105,"# Introduction\n## Accelerated expansion and cosmological probes\n## SZ effect and the origin of kSZ\n## Pairwise velocity statistics from cluster dynamics\n## Existing kSZ extraction and related techniques\n## Optical depth and sampling considerations","[{\"question\":\"What problem does the paper address?\",\"answer\":\"It proposes a machine-learning approach to reconstruct pairwise velocities using features linked to CMB and large-scale structure observables.\"},{\"question\":\"How is the machine learning model trained and what inputs does it use?\",\"answer\":\"This training teaches the mapping from measured kSZ-imprinted information to pairwise velocity correlations.\"},{\"question\":\"What challenges are considered when validating the method?\",\"answer\":\"These factors test whether the reconstruction remains reliable under realistic observational conditions.\"}]","kSZ Pairwise Velocity Reconstruction with Machine Learning | PDF",1785682735,43,{"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},"ksz-pairwise-velocity-reconstruction-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/ksz-pairwise-velocity-reconstruction-with-machine-learning/118269/",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","2026-08-02",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?","Question",{"text":75,"@type":76},"It proposes a machine-learning approach to reconstruct pairwise velocities using features linked to CMB and large-scale structure observables.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the machine learning model trained and what inputs does it use?",{"text":80,"@type":76},"This training teaches the mapping from measured kSZ-imprinted information to pairwise velocity correlations.",{"name":82,"@type":73,"acceptedAnswer":83},"What challenges are considered when validating the method?",{"text":84,"@type":76},"These factors test whether the reconstruction remains reliable under realistic observational conditions.","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"]