[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125788-en":3,"doc-seo-125788-105":29,"detail-sidebar-cat-0-en-105":90},{"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":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},125788,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Deducing the EOS of dense neutron star matter with machine learning","Neutron star interiors provide an unparalleled astrophysical laboratory for probing matter at extreme densities and pressures. Direct simulation is not feasible, so equation-of-state (EOS) constraints are commonly inferred from X-ray spectra emitted by the stellar surface. Current approaches rely on piece-wise, simulation-based likelihoods that depend on theoretical assumptions and suffer systematic uncertainties. This work applies machine learning to infer stellar properties and EOS with improved uncertainty quantification and fewer assumptions, including direct EOS inference from high-dimensional simulated X-ray spectra with end-to-end uncertainty propagation.","UC Irvine  \nUC Irvine Previously Published Works  \nTitle  \nDeducing the EOS of dense neutron star matter with machine learning  \nPermalink  \n[https://escholarship.org/uc/item/6mv7z603](https://escholarship.org/uc/item/6mv7z603)  \nJournal  \nAstronomische Nachrichten, 344(1-2)  \nISSN  \n0004-6337  \nAuthors  \nFarrell, Delaney  \nBaldi, Pierre Ott, Jordan et al.  \nPublication Date  \n2023  \nDOI  \n10.1002/asna.20230009  \nCopyright Information  \nThis work is made available under the terms of a Creative Commons Attribution License, available at [https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)  \nPeer reviewed  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nReceived: 6 January 2023 Accepted: 8 January 2023 Published on: 1 February 2023  \nDOI: 10.1002/asna.20230009  \nPR OCEEDING  \nDeducing the EOS of dense neutron star matter with machine learning  \nDelaney Farrell1  Pierre Baldi2  Jordan Ott2  Aishik Ghosh3,4  Andrew W. Steiner5,6  Atharva Kavitkar7  Lee Lindblom8   \nDaniel Whiteson3  Fridolin Weber1,8  \n1 Department of Physics, San Diego State University, San Diego, California, USA  \n2 Department of Computer Science, University of California, Irvine, California, USA  \n3 Department of Physics and Astronomy, University of California, Irvine, California, USA  \n4 Physics Division, Lawrence Berkeley National Laboratory, Berkeley, California, USA  \n5 Department of Physics and Astronomy, University of Tennessee, Knoxville, Tennessee, USA  \n6 Physics Division, Oak Ridge National Laboratory, Tennessee, USA  \n7 Department of Computer Science, TU Kaiserslautern, Germany  \n8 Center for Astrophysics and Space Sciences, University of California, San Diego, California, USA  \nCorrespondence  \nDelaney Farrell, Department of Physics, San Diego State University, California, USA.  \n[Email:](Email: dfarrell@sdsu.edu)[ dfarrell@sdsu.edu](Email: dfarrell@sdsu.edu)  \nFunding information  \nNational Science Foundation,  \nGrant/Award Numbers: 2012857, AST 19-09490, PHY 21-16686, PHY-2012152;  \nU.S. Department of Energy  \nAbstract  \nThe interior of a neutron star is a unique astrophysical laboratory for studying matter at extreme densities and pressures beyond what is replicable in terrestrial experiments. While there is no direct way to simulate the interior of these stars, one promising avenue to learning more about the equation of state (EOS) of such matter is through X-rays emitted from the star’s surface. The current state-of-the-art method for inference of EOS from a star’s X-ray spectra uses piece-wise, simulation-based likelihoods that rely on theoretical assumptions complicated by systematic uncertainties. To reduce the dimensionality of the problem, this method infers macroscopic properties of the star (mass and radius) from emitted X-ray spectra, and from those quantities infers the EOS. This work approaches the same problem using machine learning techniques, demonstrating a series of enhancements to the current state-of-the-art by realistic uncertainty quantification and reducing the need for theoretical assumptions. We also demonstrate novel inference of the EOS directly from high-dimensional simulated X-ray spectra from neutron stars that negate the need for a piece-wise approach. This inference allows for a natural propagation of uncertainties from the X-ray spectra by conditioning the discussed networks on realistic sources of uncertainty for each star.  \nKEYW O RDS  \nmachine learning, neutron stars, nuclear equation of state, X-ray spectra, XSPEC  \nThis is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.  \n© 2023 The Authors. AstronomischeNachrichten published by Wiley-VCH GmbH.  \nAstron. Nachr. 2023;344:e230009 .  \n[https","cbCairQ0zzJUlvEd","https://ap.wps.com/l/cbCairQ0zzJUlvEd","pdf",1503990,1,"English","en",105,"# Introduction\n## Neutron stars as extreme laboratories\n## EOS and its link to observables\n## Challenges in inferring EOS from spectra","[{\"question\":\"Why are neutron star interiors important for studying the equation of state (EOS)?\",\"answer\":\"They allow investigation of matter at densities and pressures far beyond what can be reproduced on Earth, and the EOS summarizes the star’s internal relationship between pressure and energy density.\"},{\"question\":\"What limitation affects current EOS inference methods from X-ray spectra?\",\"answer\":\"State-of-the-art inference often uses piece-wise, simulation-based likelihoods that require theoretical assumptions and face systematic uncertainties.\"},{\"question\":\"How does the machine learning approach improve EOS inference in this work?\",\"answer\":\"It reduces reliance on theoretical assumptions, adds realistic uncertainty quantification, and demonstrates direct EOS inference from high-dimensional simulated X-ray spectra while naturally propagating uncertainties.\"}]","Deducing the EOS of dense neutron star matter with machine learning | PDF",1785901200,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"deducing-the-eos-of-dense-neutron-star-matter-with-machine-learning","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/deducing-the-eos-of-dense-neutron-star-matter-with-machine-learning/125788/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why are neutron star interiors important for studying the equation of state (EOS)?","Question",{"text":74,"@type":75},"They allow investigation of matter at densities and pressures far beyond what can be reproduced on Earth, and the EOS summarizes the star’s internal relationship between pressure and energy density.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What limitation affects current EOS inference methods from X-ray spectra?",{"text":79,"@type":75},"State-of-the-art inference often uses piece-wise, simulation-based likelihoods that require theoretical assumptions and face systematic uncertainties.",{"name":81,"@type":72,"acceptedAnswer":82},"How does the machine learning approach improve EOS inference in this work?",{"text":83,"@type":75},"It reduces reliance on theoretical assumptions, adds realistic uncertainty quantification, and demonstrates direct EOS inference from high-dimensional simulated X-ray spectra while naturally propagating uncertainties.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]