[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120068-en":3,"doc-seo-120068-105":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},120068,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","Enhancing Galaxy Surveys with Machine Learning","Machine learning and artificial intelligence are applied to galaxy surveys targeting the physical origin of cosmic acceleration and dark energy. The work updates two ML/AI efforts: graph neural networks to infer cosmological information beyond survey geometry by leveraging available supercomputing resources, and modern reinforcement learning methods to improve galaxy target selection for the Subaru Prime Focus Spectrograph survey. Results show substantial gains in both model performance and inference speed, with particular benefits for locating faint, high-redshift galaxies.","Apr 10th,2024-4:00 PM  \nEnhancing Galaxy Surveys with Machine Learning  \nSteven KarstMissouri University of Science and Technology  \nFollow this and additional works at:https://scholarsmine.mst.edu/ugrc  \nPart of the Computer Sciences Commons,and the Physics Commons  \nKarst,Steven,\"Enhancing Galaxy Surveys with Machine Learning\"(2024).Undergraduate ResearchConference at MissouriS&T.5.https://scholarsmine.mst.edu/ugrc/2024/sciences/5  \nThis Presentation is brought to you for free and open access by Scholars'Mine.It has been accepted for inclusionin Undergraduate Research Conference at MissouriS&T by an authorized administrator of Scholars'Mine.Thiswork is protected by U.S.Copyright Law.Unauthorized use including reproduction for redistribution requires thepermission of the copyright holder.For more information,please contact scholarsmine@mst.edu.  \nEnhancing Galaxy Surveys with Machine Learning  \nAuthor:Steven Karst  \nAdvisor:Dr.Shun Saito  \nDepartment:Physics  \nDate:April 1,2024  \n# Table of Contents\n\nAbstract  \nIntroduction  \nHypothesis  \nMethodology  \nResults  \nDiscussion  \nConclusion  \nNomenclature  \nAcknowledgments  \nReferences  \n3  \n4  \n6  \n7  \n8  \n11  \n12  \n13  \n14  \n15  \n# Abstract\n\nApplications of machine learning(ML)or artificial intelligence(AI)to problems in astrophysicsand cosmology have recently entered a golden era.In response,we have updated two of ourrecent ML/AI efforts that contribute to galaxy surveys whose main scientific target is to revealthe nature of the Cosmic Acceleration or Dark Energy.We first revised our effort to infercosmological information beyond the survey geometry using Graph Neural Networks(GNN)totake advantage of supercomputing resources on campus.We then updated our reinforcementlearning methods for galaxy target selection in the Subaru Prime Focus Spectrograph(PFS)survey with modern reinforcement learning techniques such as A2C.In both cases,we found thatthese techniques dramatically improved the performance and speed of the ML models,especiallywhen locating faint galaxies with high redshifts.  \n# Introduction\n\nAs research tools improve and more discoveries are made,astronomical andcosmological datasets are becoming too large and complex to be processed by humans withconventional means.An alternative approach that has gained popularity in recent years is knownas big data processing,which uses statistical and computational techniques designed to processlarge datasets efficiently and effectively [1].Machine learning in particular has been successfullyapplied to tasks such as optimizing galaxy redshift surveys and estimating cosmologicalparameters [2].Even outside of cosmology,machine learning has received a large amount ofattention and research for its use in tools such as ChatGPT.  \nOne example where this is helpful is in interpolating the density of galaxies in a region ofspace.Any cosmological observations are limited by the fact that we live in a single Universeand hence cannot access the information beyond the region we observe.However,recent studiesshow that we could potentially access such information simply due to the nature of gravity [3].Since gravity is nonlinear and the small-scale (less than 10 Mpc)cosmic structure is interactedwith and affected by the large-scale (greater than 1 Gpc)structure beyond the observable region,we could in principle infer the large-scale mode from the small-scale structure.There aretechnical issues in a conventional approach with higher-order clustering statistics for thispurpose,but since galaxy distributions can be represented as mathematical graphs,a GraphNeural Network(GNN)architecture may be useful instead.  \nAnother example of a setting where big data processing is helpful is research involvingdark energy,a mysterious energy component that is counteracting gravity and causing theexpansion of the Universe to accelerate over time.Surveys such as the Sloan Digital Sky Survey[4],Hobby-Eberly Telescope Dark Energy Experiment [5],the Dark Energy Spec","cbCais8Ui7E1LwOJ","https://ap.wps.com/l/cbCais8Ui7E1LwOJ","pdf",4761921,1,18,"English","en",105,"# Abstract\n# Introduction\n# Hypothesis\n# Methodology\n# Results\n# Discussion\n# Conclusion\n# Nomenclature\n# Acknowledgments\n# References","[{\"question\":\"这份报告的研究目标是什么？\",\"answer\":\"报告将机器学习与人工智能用于星系巡天，主要目标是揭示宇宙加速或暗能量的本质，并提升巡天相关任务的效率与效果。\"},{\"question\":\"图神经网络在这项工作中解决了什么问题？\",\"answer\":\"图神经网络用于从超出巡天几何范围的信息中推断更深层的宇宙学量，利用图结构表达来建模星系分布。\"},{\"question\":\"强化学习如何改进PFS巡天的目标选择？\",\"answer\":\"强化学习用于提升PFS巡天的星系目标选择策略，采用类似A2C的现代强化学习技术，从而提高模型性能与计算速度，尤其有利于高红移弱星系的定位。\"}]","Enhancing Galaxy Surveys with Machine Learning | PDF",1785727980,45,{"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},"enhancing-galaxy-surveys-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/enhancing-galaxy-surveys-with-machine-learning/120068/",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","2026-08-03",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},"这份报告的研究目标是什么？","Question",{"text":75,"@type":76},"报告将机器学习与人工智能用于星系巡天，主要目标是揭示宇宙加速或暗能量的本质，并提升巡天相关任务的效率与效果。","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"图神经网络在这项工作中解决了什么问题？",{"text":80,"@type":76},"图神经网络用于从超出巡天几何范围的信息中推断更深层的宇宙学量，利用图结构表达来建模星系分布。",{"name":82,"@type":73,"acceptedAnswer":83},"强化学习如何改进PFS巡天的目标选择？",{"text":84,"@type":76},"强化学习用于提升PFS巡天的星系目标选择策略，采用类似A2C的现代强化学习技术，从而提高模型性能与计算速度，尤其有利于高红移弱星系的定位。","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"]