Mission-capable satellite prediction method for ultra large remote-sensing satellite constellation based on BP neural network

Mission-capable satellite prediction method for ultra large remote-sensing satellite constellation based on BP neural network | 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 Mission-capable satellite prediction method for ultra large remote-sensing satellite constellation based on BP neural network yiqin cong, xiaohan mei, Tianxi Liu, gongshun Guan, Cheng Wei This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5351953/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 The number of satellites in the ultra large remote-sensing satellite constellation will be more than 10,000, and the amount of data under control will be huge. The ultra large remote-sensing satellite constellation is often used to deal with sudden, complex and time-sensitive tasks with time-sensitive missions. To accommodate time-sensitive mission requirements, a fast and relatively accurate method of predicting mission satellites is needed. The traditional method performs predicting mission satellites by traversing the satellites of constellation and forecasting satellite orbits. This method is accurate but time-consuming and does not guarantee the timeliness of decisions on the ultra large remote-sensing satellite constellation. In this paper, we propose a new method for predicting mission satellites that does not rely on forecasting satellite orbits. Direct fitting of relationships from satellite orbital parameters, mission initiation time and target position to the performance of an observation mission using a Back-Propagation (BP) neural network. Since there are only 1192 remote-sensing satellites in orbit, this paper generates a set of LEO satellite constellations with 28,800 satellites based on the characteristics of the existing LEO remote-sensing satellites, which are used to generate network training and testing samples. Considering that BP neural networks have residual errors even after optimising all parameters, a fault-tolerant mechanism and a one-vote veto mechanism is used to guarantee the credibility of mission-capable satellite prediction. The results show that for the prediction of mission-capable satellite and the prediction of optimal mission-metric satellite (optimal response time and optimal observation duration), the actual executable probability of the mission-capable satellite as well as the prediction error of the mission-metrics satisfy the requirements to some extent. In addition, since no satellite orbits forecasting is involved, the BP network has a high computational efficiency in the mission-capable satellite prediction, showing good application prospects. Ultra large constellation BP neural network Remote-sensing satellite Mission-capable satellite prediction 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-5351953","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":374371218,"identity":"9cda8a59-7a99-4bcb-b4c4-cc210f513d32","order_by":0,"name":"yiqin cong","email":"","orcid":"","institution":"Harbin Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"yiqin","middleName":"","lastName":"cong","suffix":""},{"id":374371221,"identity":"148896d6-cd9b-40ea-b533-d3cd84dd77cc","order_by":1,"name":"xiaohan mei","email":"","orcid":"","institution":"Harbin Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"xiaohan","middleName":"","lastName":"mei","suffix":""},{"id":374371224,"identity":"8c6f9575-7b7e-4e0b-bc6c-21775f8f5f8c","order_by":2,"name":"Tianxi Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA00lEQVRIiWNgGAWjYBACPmYgkQDEbOw9DAeANGMDIS1szEBFYC08ZxgOHCBKC1yRRA4DA3Fa2HnMHzyouZPYJ/n24OEPDDayGw4wP3uA32E8hg0Jx54Zs0nnJQAdlma84QCbuQFhLWyH5dikcwyAWg4nbjjAwyZBWMu/wzxskmdAWv4TqSWxDWiLBA9IywFitLAVzkjsO2zMxgN02BmDZOOZh9nM8Grh5z+84eOPb4cT57efMf5QUWEn23e8+RleLWgAFFTMJKgfBaNgFIyCUYAdAAB4AEcLlpXJzgAAAABJRU5ErkJggg==","orcid":"","institution":"Harbin Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Tianxi","middleName":"","lastName":"Liu","suffix":""},{"id":374371226,"identity":"46103921-9b5c-45bd-b21c-6ac1a48715df","order_by":3,"name":"gongshun Guan","email":"","orcid":"","institution":"Harbin Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"gongshun","middleName":"","lastName":"Guan","suffix":""},{"id":374371227,"identity":"275417a7-7704-44a1-af26-c06a7aa6495e","order_by":4,"name":"Cheng Wei","email":"","orcid":"","institution":"Harbin Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Cheng","middleName":"","lastName":"Wei","suffix":""}],"badges":[],"createdAt":"2024-10-29 07:23:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5351953/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5351953/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":73272960,"identity":"74e400c1-964d-4ef8-92e3-0d67fbc4a1c8","added_by":"auto","created_at":"2025-01-08 11:17:17","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1824289,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5351953/v1_covered_de9e9986-ddad-47f1-966a-fe9b2e048993.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Mission-capable satellite prediction method for ultra large remote-sensing satellite constellation based on BP neural network","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Ultra large constellation, BP neural network, Remote-sensing satellite, Mission-capable satellite prediction","lastPublishedDoi":"10.21203/rs.3.rs-5351953/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5351953/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe number of satellites in the ultra large remote-sensing satellite constellation will be more than 10,000, and the amount of data under control will be huge. The ultra large remote-sensing satellite constellation is often used to deal with sudden, complex and time-sensitive tasks with time-sensitive missions. To accommodate time-sensitive mission requirements, a fast and relatively accurate method of predicting mission satellites is needed. The traditional method performs predicting mission satellites by traversing the satellites of constellation and forecasting satellite orbits. This method is accurate but time-consuming and does not guarantee the timeliness of decisions on the ultra large remote-sensing satellite constellation. In this paper, we propose a new method for predicting mission satellites that does not rely on forecasting satellite orbits. Direct fitting of relationships from satellite orbital parameters, mission initiation time and target position to the performance of an observation mission using a Back-Propagation (BP) neural network. Since there are only 1192 remote-sensing satellites in orbit, this paper generates a set of LEO satellite constellations with 28,800 satellites based on the characteristics of the existing LEO remote-sensing satellites, which are used to generate network training and testing samples. Considering that BP neural networks have residual errors even after optimising all parameters, a fault-tolerant mechanism and a one-vote veto mechanism is used to guarantee the credibility of mission-capable satellite prediction. The results show that for the prediction of mission-capable satellite and the prediction of optimal mission-metric satellite\u0026nbsp;(optimal response time and optimal observation duration), the actual executable\u0026nbsp;probability of the mission-capable satellite as well as the prediction error of the\u0026nbsp;mission-metrics satisfy the requirements to some extent. In addition, since no\u0026nbsp;satellite orbits forecasting is involved, the BP network has a high computational\u0026nbsp;efficiency in the mission-capable satellite prediction, showing good application\u0026nbsp;prospects.\u003c/p\u003e","manuscriptTitle":"Mission-capable satellite prediction method for ultra large remote-sensing satellite constellation based on BP neural network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-11 02:45:04","doi":"10.21203/rs.3.rs-5351953/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":"65f58a8c-96a4-4a3d-92aa-36d88824c893","owner":[],"postedDate":"November 11th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-01-08T11:09:07+00:00","versionOfRecord":[],"versionCreatedAt":"2024-11-11 02:45:04","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5351953","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5351953","identity":"rs-5351953","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}