[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128397-en":3,"doc-seo-128397-105":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},128397,962085564807,"Aurelia","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Machine learning of the cosmic 21-cm signal - 学位论文摘要","Current radio telescopes can only place upper limits on the statistical detection of the 21-cm signal, while upcoming facilities like SKA will enable both statistical detection and image-space reconstruction. As a probe of the Universe’s first billion years, the 21-cm signal motivates new modeling and inference strategies. This thesis applies advances in machine learning to Bayesian inference, building a realistic SKA pipeline, optimizing signal encoding, testing simulation-based inference, diagnosing biased posteriors from Gaussian assumptions, and introducing an information-metric to evaluate summary informativeness.","Classe di Scienze Corso di perfezionamento in Fisica  \nXXXV ciclo  \nMachine learning of the cosmic 21-cm signal  \nSettore Scientifico Disciplinare FIS/05  \nCandidato  \ndr. David PRELOGOVIĆ  \nRelatore  \nProf. Andrei Albert MESINGER  \nAnno accademico 2023/2024  \nMachine learning of the cosmic  \n21-cm signal  \nDavid Prelogovi´c Scuola Normale Superiore  \nJanuary 2024  \nii  \nAcknowledgments  \nI would first like to thank my supervisor, Andrei Mesinger, for all the effort he has put into guiding me throughout my Ph.D. and for instilling in me the scientific rigor of the highest standard. Moreover, he taught me to reflect such an attitude to all other aspects of life, especially when it comes to wines. I am thankful and truly honored for the opportunity to have such a mentor.  \nThis thesis would not exist without the love and support of my Sarah. She made all my doubts crystal clear; all obstacles to disappear. Listened to my explanations with the utmost attention; even when I doubted their comprehension. She guided me to see the bigger picture of my career; and helped the vision of my future become clear. I would also like to thank my parents for their support throughout my scientific career.  \nSpecial thanks to my officemate Ivan, who helped me solve my problems when he was tired of his, and vice versa. To Lollo, for teaching me many Italian proverbs, especially “Amico mio, avanti tutta”. To Tommy, for shortening my productive hours by a factor of two. To Zip and Laura, for bringing my attention to the importance of the word “distribucija”. To James, for making our lives so much better with Australian cookies and other perks. To Manzo and Anna, for introducing me to the wonders of the real, proper pesto. To Franka, for cooking amazing Iranian dishes for us. To all other colleagues in Pisa, who made this time of my life a wonderful experience.  \niv  \nAbstract  \nWith current radio telescopes establishing upper limits on the statistical detection of the 21-cm signal and with the construction of future telescopes, the 21-cm signal will emerge as an additional probe in datadriven cosmology. The Square Kilometre Array (SKA) radio telescope promises not only the statistical detection, but also image-space reconstruction. As a powerful probe into the first billion years of the Universe’s evolution, its potential for new discoveries in the cosmology and astrophysics of the first stars and galaxies, is enormous. With these advances, the challenges in modeling the signal and inferring from the 21-cm observations have grown, necessitating novel methodologies. Building on significant advancements in machine learning, this work implements analogous methods for the problem of Bayesian inference from the 21-cm signal. With the creation of a realistic SKA observational pipeline, we firstly deal with the problem of optimal encoding of the signal. It was found that, due to the local sky-plane correlations and time evolution along the frequencies of the signal, a convolutional recurrent neural network is the most effective architecture, yielding the tightest parameter constraints. Furthermore, we test classical inference algorithms against the novel Simulation-based inference based on neural density estimators. We find that common assumptions on the Gaussian likelihood of the 21-cm power spectrum lead to biased and over(under)-confident posteriors. Finally, we develop a Fisher information-based metric to assess how informative different summaries of the 21-cm signal are. We introduce the Information Maximizing Neural Networks in the field of 21-cm, which paired with the 2D power spectrum provides the most informative summary. We also draw attention to common pitfalls in Fisher forecasts involving summaries of the 21-cm signal.  \nvi  \nContents  \n1 Introduction 1  \n1.1 Physical cosmology ....................... 2  \n1.1.1 Homogeneous Universe ................ 5  \n1.1.2 Structure Formation .................. 7  \n1.2 21-cm probing cosmology and astrophysics ......... ","cbCaiafAXB3RYxxH","https://ap.wps.com/l/cbCaiafAXB3RYxxH","pdf",25040226,2,1,213,"English","en",105,"# Introduction\n## Physical cosmology\n## 21-cm probing cosmology and astrophysics\n## Bayesian inference\n## Data revolution in cosmology\n## Thesis overview\n# Machine learning astrophysics from 21-cm lightcones\n## Databases of mock 21 cm images\n## Network Architectures\n## Training\n## Parameter recovery\n# Exploring the likelihood of the 21-cm PS with SBI\n## Simulating 21-cm observations\n## Choosing a likelihood function\n## Results\n## Conclusions","[{\"question\":\"为什么21-cm信号会成为数据驱动宇宙学中的重要探针？\",\"answer\":\"随着未来望远镜的建设，21-cm信号有望在统计检测与图像空间重建中发挥作用，使其成为研究宇宙前一段时期演化的额外探针。\"},{\"question\":\"论文如何利用机器学习进行基于21-cm信号的贝叶斯推断？\",\"answer\":\"工作在真实SKA观测流程基础上，采用机器学习方法解决信号的最优编码，并把类似方法用于从21-cm信号进行贝叶斯推断。\"},{\"question\":\"作者如何评估不同摘要对21-cm观测的“信息量”贡献？\",\"answer\":\"论文提出基于Fisher信息的度量，用于衡量不同21-cm信号摘要的可信息性，并讨论与Fisher预测相关的常见陷阱。\"}]","Machine learning of the cosmic 21-cm signal - 学位论文摘要 | PDF",1785947287,537,{"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},"machine-learning-of-the-cosmic-21-cm-signal-thesis-abstract","",{"@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/machine-learning-of-the-cosmic-21-cm-signal-thesis-abstract/128397/",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","2026-08-29","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21-cm信号会成为数据驱动宇宙学中的重要探针？","Question",{"text":76,"@type":77},"随着未来望远镜的建设，21-cm信号有望在统计检测与图像空间重建中发挥作用，使其成为研究宇宙前一段时期演化的额外探针。","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"论文如何利用机器学习进行基于21-cm信号的贝叶斯推断？",{"text":81,"@type":77},"工作在真实SKA观测流程基础上，采用机器学习方法解决信号的最优编码，并把类似方法用于从21-cm信号进行贝叶斯推断。",{"name":83,"@type":74,"acceptedAnswer":84},"作者如何评估不同摘要对21-cm观测的“信息量”贡献？",{"text":85,"@type":77},"论文提出基于Fisher信息的度量，用于衡量不同21-cm信号摘要的可信息性，并讨论与Fisher预测相关的常见陷阱。","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"]