Physics-Informed UMAP–KNN Framework for Interpretable and Physically Consistent ExoplanetHabitability Screening

Physics-Informed UMAP–KNN Framework for Interpretable and Physically Consistent ExoplanetHabitability Screening | 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 Research Article Physics-Informed UMAP–KNN Framework for Interpretable and Physically Consistent ExoplanetHabitability Screening Samuel Worku This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9622617/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 We present a physics-informed machine-learning framework for exoplanet habitability screening that combines nonlinearrepresentation learning, interpretable classification, and astrophysical consistency diagnostics. The framework integratesUniform Manifold Approximation and Projection (UMAP) with a K-Nearest Neighbours (KNN) classifier and introducesa Physics Violation Rate (PVR) metric to quantify consistency with habitable-zone constraints. Using the PlanetaryHabitability Laboratory (PHL) catalogue, it achieves 98.3 ± 0.4% accuracy for binary classification and 90.9 ± 6.9% accuracyfor conservative-versus-optimistic subclass discrimination, with the larger uncertainty in the latter reflecting the limited sizeof the habitable subset. The hybrid model reduces physically inconsistent predictions from 12% to 2% without materiallydegrading predictive performance. To assess robustness, we incorporate uncertainty estimates, class-imbalance-aware metrics,and sensitivity analyses with respect to key physical assumptions. Taken together, the results indicate that combiningrepresentation learning, interpretable models, and physics-based validation yields a reliable and scientifically groundedscreening tool for prioritising exoplanet candidates for observational follow-up. exoplanets habitability machine learning UMAP KNN Full Text Additional Declarations No competing interests reported. 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-9622617","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":636716329,"identity":"89961beb-6588-4221-85d1-b8965964e104","order_by":0,"name":"Samuel Worku","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA50lEQVRIiWNgGAWjYHACZgYGAxB9sPHBByDFxk60FsbDhw1ngLQwE6UFTB1Lk+ZB4uMEBsd7Hxv+KNgmZ852xtjY5tc2eT5mBsYPH3PwaDlz3DiZx+C2sWXPGcPHuX23DduYGZglZ27DrcXsRhrzYQaD24kbbgBtye25zQjUwsbMS0DLwR8gLfffmElb9ty2J0pLAg9IywGg9xl+3E4kqMX+zDFmY5BfDA4AA7m34XZyGzNjM16/SLa3MUv++HNbzuAAMCqBDNv57c0HP3zEowUVMLaByQZi1YPAH1IUj4JRMApGwUgBAPRzVersTp/QAAAAAElFTkSuQmCC","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Samuel","middleName":"","lastName":"Worku","suffix":""}],"badges":[],"createdAt":"2026-05-05 20:54:24","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9622617/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9622617/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109414487,"identity":"9283d23a-e304-4a52-b1a3-0575c648cafd","added_by":"auto","created_at":"2026-05-17 17:09:45","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1265923,"visible":true,"origin":"","legend":"","description":"","filename":"APhysicsInformedUMAPKNNFrameworkforInterpretableandPhysicallyConsistentExoplanet0AHabitabilityScreening.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9622617/v1_covered_a5d93bdc-f3f2-4bc4-a6f2-9e507d9fe2d6.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Physics-Informed UMAP–KNN Framework for Interpretable and Physically Consistent ExoplanetHabitability Screening","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":"exoplanets, habitability, machine learning, UMAP, KNN","lastPublishedDoi":"10.21203/rs.3.rs-9622617/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9622617/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"We present a physics-informed machine-learning framework for exoplanet habitability screening that combines nonlinearrepresentation learning, interpretable classification, and astrophysical consistency diagnostics. The framework integratesUniform Manifold Approximation and Projection (UMAP) with a K-Nearest Neighbours (KNN) classifier and introducesa Physics Violation Rate (PVR) metric to quantify consistency with habitable-zone constraints. Using the PlanetaryHabitability Laboratory (PHL) catalogue, it achieves 98.3 ± 0.4% accuracy for binary classification and 90.9 ± 6.9% accuracyfor conservative-versus-optimistic subclass discrimination, with the larger uncertainty in the latter reflecting the limited sizeof the habitable subset. The hybrid model reduces physically inconsistent predictions from 12% to 2% without materiallydegrading predictive performance. To assess robustness, we incorporate uncertainty estimates, class-imbalance-aware metrics,and sensitivity analyses with respect to key physical assumptions. Taken together, the results indicate that combiningrepresentation learning, interpretable models, and physics-based validation yields a reliable and scientifically groundedscreening tool for prioritising exoplanet candidates for observational follow-up.","manuscriptTitle":"Physics-Informed UMAP–KNN Framework for Interpretable and Physically Consistent ExoplanetHabitability Screening","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-12 03:29:58","doi":"10.21203/rs.3.rs-9622617/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":"7a97044f-2e60-48a8-b500-f8b371bbbe01","owner":[],"postedDate":"May 12th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Rejected","date":"2026-05-17T16:57:35+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-17T16:38:41+00:00","index":8,"fulltext":""},{"type":"reviewerAgreed","content":"102084586204352098336861781901203910415","date":"2026-05-17T14:43:01+00:00","index":7,"fulltext":""},{"type":"reviewersInvited","content":"1","date":"2026-05-17T14:32:30+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-16T07:12:09+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-05-08T08:26:27+00:00","index":"","fulltext":""},{"type":"submitted","content":"Astrophysics and Space Science","date":"2026-05-05T20:44:28+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-17T17:09:20+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-12 03:29:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9622617","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9622617","identity":"rs-9622617","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}