[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121643-en":3,"doc-seo-121643-105":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},121643,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?x-image-process=image/resize,m_fixed,w_180,h_180&k=1784791008015729253",8,"Research & Report","Fast emulation of cosmological density fields based on dimensionality reduction and supervised machine-learning","N-body simulations provide the most accurate description of non-linear large-scale structure but are too computationally expensive for exhaustive exploration of cosmological parameter spaces. This work presents fast dark matter density field emulation with competitive accuracy using dimensionality reduction and supervised machine-learning regression. A projected simulation grid is learned in coefficient space, enabling estimation of new density cubes without rerunning N-body simulations. The emulator matches N-body density distributions at non-linear scales within a few percent, reproducing the power spectrum and bispectrum with target error levels while reducing CPU runtime by orders of magnitude.","Astronomy & Astrophysics manuscript no. main ©ESO 2023  \nApril 14, 2023  \n[ astro-ph .CO] 12 Apr 2023  \nFast emulation of cosmological density fields based on dimensionality reduction and supervised machine-learning  \nMiguel Conceição 1; 2 , Alberto Krone-Martins3; 4 , Antonio da Silva 1; 2 , and Ángeles Moliné5  \n1 Departamento de Física, Faculdade de Ciências, Universidade de Lisboa, Campo Grande, 1749-016 Lisboa, Portugal  \n2 Instituto de Astrofísica e Ciências do Espacço, Faculdade de Ciências, Universidade de Lisboa, Campo Grande, 1749-016 Lisboa, Portugal  \n3 Donald Bren School of Information and Computer Sciences, University of California, Irvine, Irvine CA 92697, USA  \n4 CENTRA, Faculdade de Ciências, Universidade de Lisboa, 1749-016 Lisboa, Portugal  \n5 Departamento de Física, ETSI Navales, Universidad Politécnica de Madrid, Avda. de la Memoria, 4, 28040 Madrid, Spain  \nApril 14, 2023  \nABSTRACT  \nN-body simulations are the most powerful method to study the non-linear evolution of large-scale structure. However, they require large amounts of computational resources, making unfeasible their direct adoption in scenarios that require broad explorations of parameter spaces. In this work we show that it is possible to perform fast dark matter density field emulations with competitive accuracy using simple machine-learning approaches. We build an emulator based on dimensionality reduction and machine learning regression combining simple Principal Component Analysis and supervised learning methods. For the estimations with a single free parameter, we train on the dark matter density parameter, 􀀊m , while for emulations with two free parameters, we train on a range of 􀀊m and redshift. The method first adopts a projection of a grid of simulations on a given basis; then, a machine learning regression is trained on this projected grid. Finally, new density cubes for di􀀋erent cosmological parameters can be estimated without relying directly on new N-body simulations by predicting and de-projecting the basis coe􀀎cients. We show that the proposed emulator can generate density cubes at non-linear cosmological scales with density distributions within a few percent compared to the corresponding N-body simulations. The method enables gains of three orders of magnitude in CPU run times compared to performing a full N-body simulation while reproducing the power spectrum and bispectrum within 􀀘 1% and 􀀘 3%, respectively, for the single free parameter emulation and 􀀘 5% and 􀀘 15% for two free parameters. This can significantly accelerate the generation of density cubes for a wide variety of cosmological models, opening the doors to previously unfeasible applications, as parameter and model inferences at full survey scales as the ESA/NASA Euclid mission.  \nKey words. Cosmology: large-scale structure of Universe; Methods: numerical; N-body simulations; Machine Learning  \narXiv :2304 .06099v1  \n1. Introduction  \nNumerical N-body simulations are arguably the most powerful method to describe the formation and evolution of cosmological structure, especially at late times when the growth of perturbations, driven by gravitational collapse, becomes highly non-linear. They provide high-accuracy predictions on how the dark matter (DM) density and velocity fields evolve, allowing the identification of model signatures and observables that can be compared against observations. This process often requires the generation of a very large number of computationally intensive simulation runs, posing a prohibitive bottleneck on the number of simulated models that can be explored in the preparation and scientific exploitation of modern cosmological surveys. This penalizes model inference studies, specially using Bayesian methods considering the shear data volume of modern sky-surveys such as ESA/Gaia (Gaia Collaboration et al. 2016, 2022), ESA/Euclid (Laureijs et al. 2011 ; Euclid Collaboration et al. 2022) and time-resolved surveys as Zwicky Transient Facility (Bell","cbCaiaF9cRoXA0VI","https://ap.wps.com/l/cbCaiaF9cRoXA0VI","pdf",1428301,1,10,"English","en",105,"# Abstract\n# Introduction\n## Motivation: computational bottlenecks in N-body simulations\n## Emulation methods: from Gaussian Processes to machine learning\n## Related work on deep learning emulation\n# Proposed approach and training strategy\n## Dimensionality reduction with PCA\n## Supervised regression for parameter-dependent emulation\n# Results and performance\n## Accuracy against N-body simulations\n## Power spectrum and bispectrum reproduction\n# Applications and impact\n## Accelerating parameter/model inference for large surveys","[{\"question\":\"Why do large-scale N-body simulations become a bottleneck for cosmological studies?\",\"answer\":\"They require massive computational resources, making it impractical to run enough simulations to explore broad parameter spaces for modern survey analyses.\"},{\"question\":\"How does the proposed emulator generate dark matter density cubes without new N-body runs?\",\"answer\":\"It projects simulation outputs onto a basis using dimensionality reduction, trains supervised regression on the projected grid, then predicts and de-projects basis coefficients for new cosmological parameters.\"},{\"question\":\"What accuracy and speed improvements does the emulator achieve?\",\"answer\":\"It produces density cubes with density distributions within a few percent of corresponding N-body simulations and reproduces the power spectrum and bispectrum with percent-level errors, while cutting CPU runtime by about three orders of magnitude.\"}]","Fast emulation of cosmological density fields based on dimensionality reduction and supervised machine-learning | PDF",1785805886,25,{"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},"fast-emulation-of-cosmological-density-fields-based-on-dimensionality-reduction-and-supervised-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/fast-emulation-of-cosmological-density-fields-based-on-dimensionality-reduction-and-supervised-machine-learning/121643/",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},"Why do large-scale N-body simulations become a bottleneck for cosmological studies?","Question",{"text":75,"@type":76},"They require massive computational resources, making it impractical to run enough simulations to explore broad parameter spaces for modern survey analyses.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed emulator generate dark matter density cubes without new N-body runs?",{"text":80,"@type":76},"It projects simulation outputs onto a basis using dimensionality reduction, trains supervised regression on the projected grid, then predicts and de-projects basis coefficients for new cosmological parameters.",{"name":82,"@type":73,"acceptedAnswer":83},"What accuracy and speed improvements does the emulator achieve?",{"text":84,"@type":76},"It produces density cubes with density distributions within a few percent of corresponding N-body simulations and reproduces the power spectrum and bispectrum with percent-level errors, while cutting CPU runtime by about three orders of magnitude.","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},[93,97,101,105,110,115,120,123,128,131,134],{"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":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":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]