ML-test: a machine learning-based test for integer ambiguity validation

ML-test: a machine learning-based test for integer ambiguity validation | 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 ML-test: a machine learning-based test for integer ambiguity validation Yanqing Hou, Yining Shi, Xiaojun Duan, Xuan Chen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4912359/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 22 Jun, 2025 Read the published version in GPS Solutions → Version 1 posted 9 You are reading this latest preprint version Abstract The accurate resolution of integer ambiguity is crucial for Real-Time Kinematic (RTK) and Precise Point Positioning (PPP), with ambiguity validation serving as a pivotal stage. The ratio test based on a fixed threshold (RT) is currently the most widely used test for ambiguity validation. However, due to its inflexible characteristics of remaining a fixed threshold, it is challenging to guarantee availability and reliability simultaneously. The fixed failure rate ratio test (FFRT) addresses this by adjusting the threshold dynamically according to model strength. However, its reliability is compromised due to the detachment from real scenarios in Monte Carlo simulations and theoretical limitations. This paper contributes by proposing the ML-test, a machine learning (ML)-based test for ambiguity validation. ML-test aims to discover patterns influencing the correctness of ambiguity validation by utilizing a substantial amount of real data for ML. To verify the performance of ML-test, comparative experiments between ML-test, RT, and FFRT are conducted over multiple days and baselines. The results indicate that the total average fix rate of RT (with a fixed threshold of 3) is between 74% and 78%, FFRT (with a fixed failure rate of 0.001) is between 98% and 99%, and ML-test is between 89% and 96%. The total average conditional success rate of RT is nearly 100%, FFRT is between 96% and 98%, and ML-test is between 98% and 99%, generally higher than FFRT. It is evident that ML-test demonstrates advantages in balancing availability and reliability, with stable performance that ensures a high fix rate while maintaining a sufficiently high conditional success rate. Ambiguity resolution Ambiguity validation Ratio test Fixed failure rate Machine learning (ML) RTK Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 22 Jun, 2025 Read the published version in GPS Solutions → Version 1 posted Editorial decision: Revision requested 16 Mar, 2025 Reviews received at journal 02 Mar, 2025 Reviewers agreed at journal 14 Jan, 2025 Reviews received at journal 15 Oct, 2024 Reviewers agreed at journal 07 Sep, 2024 Reviewers invited by journal 06 Sep, 2024 Editor assigned by journal 06 Sep, 2024 Submission checks completed at journal 17 Aug, 2024 First submitted to journal 14 Aug, 2024 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-4912359","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":357426211,"identity":"63915761-7d44-4894-9d21-60a4457b2a26","order_by":0,"name":"Yanqing Hou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9klEQVRIiWNgGAWjYBACAzBZYcPAwMzcgCqIX8uZNKAWRlK0MLYdBpFEajFn7zGTeNt2Ppq/nbGB8WdbXWIDe/M2CYaaOzi1WPacMZOcc+527ozDjA3MvG2HExt4jpVJMBx7htthN3LMpHnKbuc2gLQwth1IbJDIMZNgbDhMQAvbudz5h2EOk39DjJa2A7kbgFoYeNuYgbbwENBy5lix5ZwzybkbgVoO85w7bNzGk1ZskXAMj5bjzRtvvKmwy513/vDBhz/K6mT72Q9vvPGhBrcWIGCR4IGyDjCyMTCwgVgJ+DQAo/0DD5z9B7/SUTAKRsEoGJkAAJR5WJ2Kc9RcAAAAAElFTkSuQmCC","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":true,"prefix":"","firstName":"Yanqing","middleName":"","lastName":"Hou","suffix":""},{"id":357426212,"identity":"18013420-d1c8-4dce-bc90-5140fd8b4348","order_by":1,"name":"Yining Shi","email":"","orcid":"","institution":"Sun Yat-sen University","correspondingAuthor":false,"prefix":"","firstName":"Yining","middleName":"","lastName":"Shi","suffix":""},{"id":357426213,"identity":"1d6430f2-df64-46de-b273-abeedb64ab3d","order_by":2,"name":"Xiaojun Duan","email":"","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Xiaojun","middleName":"","lastName":"Duan","suffix":""},{"id":357426214,"identity":"a6bedb04-891e-4081-bb57-bce034bd1765","order_by":3,"name":"Xuan Chen","email":"","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Xuan","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2024-08-14 09:10:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4912359/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4912359/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10291-025-01904-x","type":"published","date":"2025-06-22T15:57:53+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":85231492,"identity":"c30fcc2a-4a29-4f5b-8b2e-f38f3102448f","added_by":"auto","created_at":"2025-06-23 16:08:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1355524,"visible":true,"origin":"","legend":"","description":"","filename":"Houetal2024MLtest.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4912359/v1_covered_57a995a4-5340-403c-830c-35a11840b5b2.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"ML-test: a machine learning-based test for integer ambiguity validation","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"gps-solutions","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"gpss","sideBox":"Learn more about [GPS Solutions](http://link.springer.com/journal/10291)","snPcode":"10291","submissionUrl":"https://submission.nature.com/new-submission/10291/3","title":"GPS Solutions","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Ambiguity resolution, Ambiguity validation, Ratio test, Fixed failure rate, Machine learning (ML), RTK","lastPublishedDoi":"10.21203/rs.3.rs-4912359/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4912359/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The accurate resolution of integer ambiguity is crucial for Real-Time Kinematic (RTK) and Precise Point Positioning (PPP), with ambiguity validation serving as a pivotal stage. The ratio test based on a fixed threshold (RT) is currently the most widely used test for ambiguity validation. However, due to its inflexible characteristics of remaining a fixed threshold, it is challenging to guarantee availability and reliability simultaneously. The fixed failure rate ratio test (FFRT) addresses this by adjusting the threshold dynamically according to model strength. However, its reliability is compromised due to the detachment from real scenarios in Monte Carlo simulations and theoretical limitations. This paper contributes by proposing the ML-test, a machine learning (ML)-based test for ambiguity validation. ML-test aims to discover patterns influencing the correctness of ambiguity validation by utilizing a substantial amount of real data for ML. To verify the performance of ML-test, comparative experiments between ML-test, RT, and FFRT are conducted over multiple days and baselines. The results indicate that the total average fix rate of RT (with a fixed threshold of 3) is between 74% and 78%, FFRT (with a fixed failure rate of 0.001) is between 98% and 99%, and ML-test is between 89% and 96%. The total average conditional success rate of RT is nearly 100%, FFRT is between 96% and 98%, and ML-test is between 98% and 99%, generally higher than FFRT. It is evident that ML-test demonstrates advantages in balancing availability and reliability, with stable performance that ensures a high fix rate while maintaining a sufficiently high conditional success rate.","manuscriptTitle":"ML-test: a machine learning-based test for integer ambiguity validation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-10-10 10:09:58","doi":"10.21203/rs.3.rs-4912359/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-03-16T22:49:15+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-03-02T22:32:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"187271248487410966981923518916566375348","date":"2025-01-14T08:17:10+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-10-15T05:36:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"213505429119821684951177956240275003034","date":"2024-09-07T10:35:32+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-09-06T18:22:52+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-09-06T18:19:03+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-08-17T10:09:58+00:00","index":"","fulltext":""},{"type":"submitted","content":"GPS Solutions","date":"2024-08-14T09:09:03+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"gps-solutions","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"gpss","sideBox":"Learn more about [GPS Solutions](http://link.springer.com/journal/10291)","snPcode":"10291","submissionUrl":"https://submission.nature.com/new-submission/10291/3","title":"GPS Solutions","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"b441b3b4-e640-4a30-be8f-f772b5779cd0","owner":[],"postedDate":"October 10th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-06-23T16:05:14+00:00","versionOfRecord":{"articleIdentity":"rs-4912359","link":"https://doi.org/10.1007/s10291-025-01904-x","journal":{"identity":"gps-solutions","isVorOnly":false,"title":"GPS Solutions"},"publishedOn":"2025-06-22 15:57:53","publishedOnDateReadable":"June 22nd, 2025"},"versionCreatedAt":"2024-10-10 10:09:58","video":"","vorDoi":"10.1007/s10291-025-01904-x","vorDoiUrl":"https://doi.org/10.1007/s10291-025-01904-x","workflowStages":[]},"version":"v1","identity":"rs-4912359","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4912359","identity":"rs-4912359","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}