KM-UNet: A KAN-Mamba Hybrid Network with Direction-Sensitive Attention and Multi-Scale Fusion for Cloud Mask Nowcasting

KM-UNet: A KAN-Mamba Hybrid Network with Direction-Sensitive Attention and Multi-Scale Fusion for Cloud Mask Nowcasting | 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 KM-UNet: A KAN-Mamba Hybrid Network with Direction-Sensitive Attention and Multi-Scale Fusion for Cloud Mask Nowcasting Jian Zhou, Xiaohui Huang, Fu Wang, Xiaofei Yang, Yifang Ban This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8556402/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Cloud mask nowcasting is a critical yet challenging task in meteorological prediction, which is the prerequisite for precipitation forecasting. Although existing methods have considerably improved prediction accuracy for extensive regions of thin clouds, these methods struggle to maintain comparable accuracy for localized, small-scale, optically thick cloud regions. To address this challenge, We propose a deep learning model called KM-UNet based on the KAN-Mamba hybrid network for heavy cloud mask nowcasting. Specifically, we adapt the KAN Convolution module to enhance the local feature extraction capability on local heavy cloud areas, and introduced the three-dimensional Enhanced ViM module for joint modeling of spatial and channel information to capture the global features on large-scale thin cloud areas. Additionally, we propose the Multi-Scale Fusion and Hybrid Loss function to optimize feature learning. Extensive experiments on two real-world meteorological datasets shown that our model outperforms existing models. Cloud Mask Nowcasting Kolmogorov-Arnold network Vision Mamba U-Net Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 16 May, 2026 Reviewers agreed at journal 10 May, 2026 Reviewers agreed at journal 12 Feb, 2026 Reviewers invited by journal 12 Feb, 2026 Editor assigned by journal 12 Feb, 2026 Submission checks completed at journal 12 Jan, 2026 First submitted to journal 08 Jan, 2026 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-8556402","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":590213200,"identity":"7873ce2b-9299-4872-a443-1cc192564248","order_by":0,"name":"Jian Zhou","email":"","orcid":"","institution":"East China Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Jian","middleName":"","lastName":"Zhou","suffix":""},{"id":590213203,"identity":"54fa706f-e4c2-4308-bcf3-7e8ec6aea056","order_by":1,"name":"Xiaohui Huang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBklEQVRIiWNgGAWjYBACAwglAUYHPjAwMIP5PMRqOTgDqIWHSC0QXWDlBLWYSyQ/e/i1zUKeX7rH8LBNhR27vUQC44O3bQzy5ji0WM5IMzeWOSNhOHPOGYPDOWeSmXkkEpgN57YxGO5swOGwGwlm0hIVEowbbuQYHM5tOwDSwibN28aQYHAAl5b0b9ISBhL2YC2W/8Ba2H/j15JjJvmhQiIRrIWxAWILM14tZ96USTOckUieOSOt4GDPMaBfzjxslpxzTsJwAy4tx9O3Sf5sq7Ptl0je/OFHjV0ye3vywQ9vymzkcdkCAszIsZDMwMDYwACOJjyA8QcSxw6v0lEwCkbBKBiRAADya1b8FchcrAAAAABJRU5ErkJggg==","orcid":"","institution":"East China Jiaotong University","correspondingAuthor":true,"prefix":"","firstName":"Xiaohui","middleName":"","lastName":"Huang","suffix":""},{"id":590213204,"identity":"3944758a-f2d5-4c3c-91f9-b6fbdf5c2fa8","order_by":2,"name":"Fu Wang","email":"","orcid":"","institution":"CMA","correspondingAuthor":false,"prefix":"","firstName":"Fu","middleName":"","lastName":"Wang","suffix":""},{"id":590213205,"identity":"94e9a76e-bba8-4312-9822-cda2354a15fb","order_by":3,"name":"Xiaofei Yang","email":"","orcid":"","institution":"Guangzhou University","correspondingAuthor":false,"prefix":"","firstName":"Xiaofei","middleName":"","lastName":"Yang","suffix":""},{"id":590213206,"identity":"a57be277-cd9f-4214-b012-f6bbf253b68a","order_by":4,"name":"Yifang Ban","email":"","orcid":"","institution":"KTH Royal Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Yifang","middleName":"","lastName":"Ban","suffix":""}],"badges":[],"createdAt":"2026-01-09 03:38:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8556402/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8556402/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102963264,"identity":"42febf89-2abb-49b0-bc64-aa8549d7405f","added_by":"auto","created_at":"2026-02-19 04:14:56","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2221181,"visible":true,"origin":"","legend":"","description":"","filename":"KMUNet2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8556402/v1_covered_fd81957b-2c43-4198-aaa7-7bdba092ee1d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"KM-UNet: A KAN-Mamba Hybrid Network with Direction-Sensitive Attention and Multi-Scale Fusion for Cloud Mask Nowcasting","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"cluster-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Cluster Computing](https://www.springer.com/journal/10586)","snPcode":"10586","submissionUrl":"https://submission.nature.com/new-submission/10586/3","title":"Cluster Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Cloud Mask Nowcasting, Kolmogorov-Arnold network, Vision Mamba, U-Net","lastPublishedDoi":"10.21203/rs.3.rs-8556402/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8556402/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eCloud mask nowcasting is a critical yet challenging task in meteorological prediction, which is the prerequisite for precipitation forecasting. Although existing methods have considerably improved prediction accuracy for extensive regions of thin clouds, these methods struggle to maintain comparable accuracy for localized, small-scale, optically thick cloud regions. To address this challenge, We propose a deep learning model called KM-UNet based on the KAN-Mamba hybrid network for heavy cloud mask nowcasting. Specifically, we adapt the KAN Convolution module to enhance the local feature extraction capability on local heavy cloud areas, and introduced the three-dimensional Enhanced ViM module for joint modeling of spatial and channel information to capture the global features on large-scale thin cloud areas. Additionally, we propose the Multi-Scale Fusion and Hybrid Loss function to optimize feature learning. Extensive experiments on two real-world meteorological datasets shown that our model outperforms existing models.\u003c/p\u003e","manuscriptTitle":"KM-UNet: A KAN-Mamba Hybrid Network with Direction-Sensitive Attention and Multi-Scale Fusion for Cloud Mask Nowcasting","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-17 06:29:11","doi":"10.21203/rs.3.rs-8556402/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-16T13:10:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"23017734037112079400668463270061437448","date":"2026-05-10T12:12:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"165944210207816628333860015162091186512","date":"2026-02-12T10:57:13+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-12T08:00:03+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-12T07:52:41+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-13T04:14:18+00:00","index":"","fulltext":""},{"type":"submitted","content":"Cluster Computing","date":"2026-01-09T03:35:18+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"cluster-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Cluster Computing](https://www.springer.com/journal/10586)","snPcode":"10586","submissionUrl":"https://submission.nature.com/new-submission/10586/3","title":"Cluster Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"5889938a-e544-456e-91b6-904fae8e100c","owner":[],"postedDate":"February 17th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-16T13:10:01+00:00","index":31,"fulltext":""},{"type":"reviewerAgreed","content":"23017734037112079400668463270061437448","date":"2026-05-10T12:12:23+00:00","index":29,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-02-17T06:29:11+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-17 06:29:11","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8556402","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8556402","identity":"rs-8556402","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}