Imaging physics-driven artificial intelligence makes ground-based telescope resolve deep field universe

Imaging physics-driven artificial intelligence makes ground-based telescope resolve deep field universe | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Physical Sciences - Article Imaging physics-driven artificial intelligence makes ground-based telescope resolve deep field universe Wanli Ouyang, Yan Lu, Hao Du, Jiaze Li, Kuo-cheng Wu, Zhen Wan, and 9 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8068579/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Astronomical observations are constrained by a long-standing trade-off: ground-based telescopes offer wide-field access at a low cost but suffer from atmospheric distortions, whereas space telescopes provide diffraction-limited clarity at the expense of narrow coverage and high cost. This paper presents StelLens, a physics-driven artificial intelligence model that brings ground-telescope imaging data to the level of space-telescope imaging quality by jointly learning the ground imaging prior, the space imaging prior, and the highly non-linear relationship between ground and space images. Applied to Sloan Digital Sky Survey (SDSS) observations and benchmarked with Hubble Space Telescope (HST) optical images, StelLens achieves a 13× improvement in the median image-quality metric, reduces spurious detections by ~50%, enables 295% more detectable sources, and improves the limiting magnitude by 4.37 magnitude. Extensive experiments also demonstrate accurate reconstruction of geometric properties, such as axis ratios and characteristic sizes. Leveraging this approach, the SDSS archive effectively becomes a wide-field survey with space-telescope-like quality, covering ~14,000 square degrees, nearly 300× the area accessible to HST, without additional cost on the telescope. Our StelLens establishes a new paradigm for astronomical surveys, demonstrating that AI can bridge the gap between ground and space observations, enabling clearer and deeper exploration of the universe at scale. Physical sciences/Astronomy and planetary science/Astronomy and astrophysics/Computational astrophysics Physical sciences/Mathematics and computing/Computational science Full Text Additional Declarations There is NO Competing Interest. Supplementary Files 3.supplementary.pdf Extended Data 1~7 Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8068579","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Physical Sciences - Article","associatedPublications":[],"authors":[{"id":548841542,"identity":"e98ba604-1977-4149-b84f-c80980717ed5","order_by":0,"name":"Wanli Ouyang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABB0lEQVRIie3RsUrDQBzH8d+fg8ThStcrKfQVLgSsoG2fJRw4BakURHCJHMQlOFd8iYCDZCsE9BWELHVxVuoQtKAX6poQN8H78uf4L5/hzwE225/Opcs1+AFkd8JIS3DxKwJHAB1IX0T+Zv5RjMaMJRfzoRiNwR7e3jE9aSKDZRR4N9eFn2tKyiUXfh476nYItWgi8imSXi8tKSsM4VxQtuIBE1iFcTMJPg2Z1WRhyKwL2fd4VYY1YYaENaHXFjJIX84Oe/GXMkR75haVa0cxSNVI+q66K/n2eJI9Xj1vTtOjyb2rC6rOp40E2JOgZLcySuvXDG/9HXcNbH8Iqt1CVZuw2Wy2/9Y31FJTqjGSCeAAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-9163-2761","institution":"Shanghai AI Laboratory","correspondingAuthor":true,"prefix":"","firstName":"Wanli","middleName":"","lastName":"Ouyang","suffix":""},{"id":548841543,"identity":"5bcd8b19-2333-4e91-bab9-abb8a5225c30","order_by":1,"name":"Yan Lu","email":"","orcid":"","institution":"Shanghai AI Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Yan","middleName":"","lastName":"Lu","suffix":""},{"id":548841544,"identity":"5dc5aa1d-7ca6-4c35-8336-c1bdb50e51ad","order_by":2,"name":"Hao Du","email":"","orcid":"","institution":"Shanghai Artificial Intelligence Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Hao","middleName":"","lastName":"Du","suffix":""},{"id":548841545,"identity":"5e932b32-89cf-4cdc-a959-01d2a483ac3a","order_by":3,"name":"Jiaze Li","email":"","orcid":"","institution":"Shanghai AI Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Jiaze","middleName":"","lastName":"Li","suffix":""},{"id":548841546,"identity":"7ebbe8b9-8d37-4b2b-beab-f11dd063cadb","order_by":4,"name":"Kuo-cheng Wu","email":"","orcid":"","institution":"Shanghai AI Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Kuo-cheng","middleName":"","lastName":"Wu","suffix":""},{"id":548841547,"identity":"56ecd06b-5979-4a17-89cf-4c2012f173be","order_by":5,"name":"Zhen Wan","email":"","orcid":"","institution":"University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Zhen","middleName":"","lastName":"Wan","suffix":""},{"id":548841548,"identity":"0ab902ee-0bcc-414e-8477-ff8f3c412b1a","order_by":6,"name":"Guohang Zhuang","email":"","orcid":"","institution":"Shanghai AI Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Guohang","middleName":"","lastName":"Zhuang","suffix":""},{"id":548841549,"identity":"dd8f8a17-533a-4047-991b-11275535fe70","order_by":7,"name":"Yating Liu","email":"","orcid":"https://orcid.org/0009-0008-4858-1410","institution":"Shanghai AI Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Yating","middleName":"","lastName":"Liu","suffix":""},{"id":548841550,"identity":"94462cd8-abbe-495a-aa19-4e8bb85e6b67","order_by":8,"name":"Shixiang Tang","email":"","orcid":"","institution":"Shanghai AI Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Shixiang","middleName":"","lastName":"Tang","suffix":""},{"id":548841551,"identity":"d0843a8f-30b0-4b77-add4-1f3f3403f13e","order_by":9,"name":"Lei Bai","email":"","orcid":"https://orcid.org/0000-0003-3378-7201","institution":"Shanghai AI Laboratory","correspondingAuthor":false,"prefix":"","firstName":"Lei","middleName":"","lastName":"Bai","suffix":""},{"id":548841552,"identity":"78684dec-702a-47ef-af6d-d10998d8b5d3","order_by":10,"name":"Bin Liu","email":"","orcid":"","institution":"University of Science and Technology of China","correspondingAuthor":false,"prefix":"","firstName":"Bin","middleName":"","lastName":"Liu","suffix":""},{"id":548841553,"identity":"4a4213d1-8846-496d-a0f7-496e8c3f9e8a","order_by":11,"name":"Zhijian Luo","email":"","orcid":"","institution":"Shanghai Normal University","correspondingAuthor":false,"prefix":"","firstName":"Zhijian","middleName":"","lastName":"Luo","suffix":""},{"id":548841554,"identity":"01183f8f-7ac1-43f8-88ef-79f3c6a5eab3","order_by":12,"name":"Zhu Chen","email":"","orcid":"","institution":"Shanghai Normal University","correspondingAuthor":false,"prefix":"","firstName":"Zhu","middleName":"","lastName":"Chen","suffix":""},{"id":548841555,"identity":"cd0051cc-249c-4e36-8922-17442fd2a16a","order_by":13,"name":"Shiyin Shen","email":"","orcid":"","institution":"Shanghai Astronomical Observatory","correspondingAuthor":false,"prefix":"","firstName":"Shiyin","middleName":"","lastName":"Shen","suffix":""},{"id":548841556,"identity":"8b7a99b3-c26e-4f6b-aacb-f03458eb231e","order_by":14,"name":"Renhao Ye","email":"","orcid":"","institution":"Shanghai Astronomical Observatory","correspondingAuthor":false,"prefix":"","firstName":"Renhao","middleName":"","lastName":"Ye","suffix":""}],"badges":[],"createdAt":"2025-11-09 11:05:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8068579/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8068579/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100356642,"identity":"efd12649-ee7e-4549-b5aa-1b838d58c755","added_by":"auto","created_at":"2026-01-16 07:16:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":12797697,"visible":true,"origin":"","legend":"Article File","description":"","filename":"2.maintext.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8068579/v1_covered_405cb324-b6f2-4663-914b-5c12da1e2344.pdf"},{"id":96686747,"identity":"d455a4ed-8988-4197-81bb-c0f8208471ba","added_by":"auto","created_at":"2025-11-25 05:34:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":64013219,"visible":true,"origin":"","legend":"Extended Data 1~7","description":"","filename":"3.supplementary.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8068579/v1/770e1dee4f018c4515d2642d.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Imaging physics-driven artificial intelligence makes ground-based telescope resolve deep field universe","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-8068579/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8068579/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Astronomical observations are constrained by a long-standing trade-off: ground-based telescopes offer wide-field access at a low cost but suffer from atmospheric distortions, whereas space telescopes provide diffraction-limited clarity at the expense of narrow coverage and high cost. This paper presents StelLens, a physics-driven artificial intelligence model that brings ground-telescope imaging data to the level of space-telescope imaging quality by jointly learning the ground imaging prior, the space imaging prior, and the highly non-linear relationship between ground and space images.\r\nApplied to Sloan Digital Sky Survey (SDSS) observations and benchmarked with Hubble Space Telescope (HST) optical images, StelLens achieves a 13× improvement in the median image-quality metric, reduces spurious detections by ~50%, enables 295% more detectable sources, and improves the limiting magnitude by 4.37 magnitude. Extensive experiments also demonstrate accurate reconstruction of geometric properties, such as axis ratios and characteristic sizes. Leveraging this approach, the SDSS archive effectively becomes a wide-field survey with space-telescope-like quality, covering ~14,000 square degrees, nearly 300× the area accessible to HST, without additional cost on the telescope.\r\nOur StelLens establishes a new paradigm for astronomical surveys, demonstrating that AI can bridge the gap between ground and space observations, enabling clearer and deeper exploration of the universe at scale.","manuscriptTitle":"Imaging physics-driven artificial intelligence makes ground-based telescope resolve deep field universe","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-25 05:34:44","doi":"10.21203/rs.3.rs-8068579/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"c17d9773-2c4a-46d2-aed3-782d4edd8140","owner":[],"postedDate":"November 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":58405027,"name":"Physical sciences/Astronomy and planetary science/Astronomy and astrophysics/Computational astrophysics"},{"id":58405028,"name":"Physical sciences/Mathematics and computing/Computational science"}],"tags":[],"updatedAt":"2026-01-08T15:36:08+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-25 05:34:44","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8068579","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8068579","identity":"rs-8068579","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}