Precision forage-yield estimation in wetland rangelands through Multi-sensor satellite data fusion and machine learning

Precision forage-yield estimation in wetland rangelands through Multi-sensor satellite data fusion and machine learning | 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 Precision forage-yield estimation in wetland rangelands through Multi-sensor satellite data fusion and machine learning Sebahattin Albayrak, Mustafa Güler This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8882230/v2 This work is licensed under a CC BY 4.0 License Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Abstract Context: In wetland meadow–rangeland ecosystems such as the Kızılırmak Delta (Türkiye), which is listed on the UNESCO World Heritage Tentative List, forage yield can shift rapidly across space and time due to hydrological fluctuations, climate variability, and grazing pressure. This dynamism complicates grazing planning and carrying-capacity assessments while maintaining a conservation–use balance. Objectives To (i) compare how Sentinel-2, Landsat-8/9, and multi-sensor fusion (Combined) approaches influence the accuracy of forage-yield prediction, and (ii) translate within-season yield dynamics into spatial products suitable for monitoring and decision support in wetland rangeland management. Methods Forage yield measured during the 2022–2023 growing seasons (June–November; n = 411) was linked to cloud-masked surface reflectance products processed in Google Earth Engine. For Sentinel-2 (10 m), Landsat-8/9 (30 m), and Combined scenarios, predictors included NDVI, NDRE, GNDVI, and OSAVI; SWIR bands; phenological timing (day of year, DOY); and 30-day lagged variables (lag_NDVI and lag_precip from CHIRPS). Random Forest (RF), Gradient Boosting Regressor (GBR), and Extreme Gradient Boosting (XGB) models were trained using an 80% training set and a 20% independent test set, and evaluated with r , R², RMSE, nRMSE, MAE, and MBE. Monthly yield maps and pixel-wise trend analysis were further used to characterize within-season spatial variability. Key results: Model performance ranged from R² = 0.14–0.26 for Sentinel-2, R² = 0.46–0.54 for Landsat-8/9, and R² = 0.56–0.68 for the Combined scenario. The best performance was achieved by Combined + XGB (R² = 0.676; RMSE = 142.1 kg ha⁻¹; MAE = 109.7 kg ha⁻¹; nRMSE = 28.82%). Alongside SWIR and NDVI/OSAVI, DOY and lagged predictors made meaningful contributions to prediction skill. Conclusion Multi-sensor fusion coupled with boosting-based models substantially improves forage-yield prediction in wetland rangelands and enables robust spatial products for within-season monitoring. Implications and impacts: The resulting maps and trend indicators provide an actionable decision-support backbone for UNESCO-sensitive wetland landscapes, helping to guide grazing intensity, rotation/resting strategies, and adaptive management under hydrological and climatic variability while safeguarding the conservation–use balance. Ecological Modeling Agronomy precision grazing wetland meadow forage yield multi-sensor fusion machine learning Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 2 posted You are reading this latest preprint version Show more versions 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-8882230","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":592764123,"identity":"d3721d82-0e44-4dec-a442-044fe5b071db","order_by":0,"name":"Sebahattin Albayrak","email":"data:image/png;base64,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","orcid":"https://orcid.org/0009-0007-7163-2944","institution":"ondokuz mayıs university","correspondingAuthor":true,"prefix":"","firstName":"Sebahattin","middleName":"","lastName":"Albayrak","suffix":""},{"id":615099650,"identity":"beee9d15-d647-44ba-acc2-483f5a90feb1","order_by":1,"name":"Mustafa Güler","email":"","orcid":"https://orcid.org/0009-0003-6357-5717","institution":"ondokuz mayıs university","correspondingAuthor":false,"prefix":"","firstName":"Mustafa","middleName":"","lastName":"Güler","suffix":""}],"badges":[],"createdAt":"2026-02-14 19:26:38","currentVersionCode":2,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8882230/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-8882230/v2","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105905384,"identity":"8b7b6d04-ddb8-4062-90b5-4e9e1e02f650","added_by":"auto","created_at":"2026-04-01 10:11:58","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1932257,"visible":true,"origin":"","legend":"","description":"","filename":"8882230.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8882230/v2_covered_01a68558-113f-41c3-b119-4a3502873793.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"Precision forage-yield estimation in wetland rangelands through\nMulti-sensor satellite data fusion and machine learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Ondokuz Mayıs University","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"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":"precision grazing, wetland meadow, forage yield, multi-sensor fusion, machine learning","lastPublishedDoi":"10.21203/rs.3.rs-8882230/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8882230/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cdiv id=\"ASec1\" class=\"AbstractSection\"\u003e \u003cdiv class=\"Heading\"\u003eContext:\u003c/div\u003e \u003cp\u003eIn wetland meadow\u0026ndash;rangeland ecosystems such as the Kızılırmak Delta (T\u0026uuml;rkiye), which is listed on the UNESCO World Heritage Tentative List, forage yield can shift rapidly across space and time due to hydrological fluctuations, climate variability, and grazing pressure. This dynamism complicates grazing planning and carrying-capacity assessments while maintaining a conservation\u0026ndash;use balance.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"ASec2\" class=\"AbstractSection\"\u003e \u003cdiv class=\"Heading\"\u003eObjectives\u003c/div\u003e \u003cp\u003eTo (i) compare how Sentinel-2, Landsat-8/9, and multi-sensor fusion (Combined) approaches influence the accuracy of forage-yield prediction, and (ii) translate within-season yield dynamics into spatial products suitable for monitoring and decision support in wetland rangeland management.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"ASec3\" class=\"AbstractSection\"\u003e \u003cdiv class=\"Heading\"\u003eMethods\u003c/div\u003e \u003cp\u003eForage yield measured during the 2022\u0026ndash;2023 growing seasons (June\u0026ndash;November; \u003cem\u003en\u003c/em\u003e\u0026thinsp;=\u0026thinsp;411) was linked to cloud-masked surface reflectance products processed in Google Earth Engine. For Sentinel-2 (10 m), Landsat-8/9 (30 m), and Combined scenarios, predictors included NDVI, NDRE, GNDVI, and OSAVI; SWIR bands; phenological timing (day of year, DOY); and 30-day lagged variables (lag_NDVI and lag_precip from CHIRPS). Random Forest (RF), Gradient Boosting Regressor (GBR), and Extreme Gradient Boosting (XGB) models were trained using an 80% training set and a 20% independent test set, and evaluated with \u003cem\u003er\u003c/em\u003e, R\u0026sup2;, RMSE, nRMSE, MAE, and MBE. Monthly yield maps and pixel-wise trend analysis were further used to characterize within-season spatial variability.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"ASec4\" class=\"AbstractSection\"\u003e \u003cdiv class=\"Heading\"\u003eKey results:\u003c/div\u003e \u003cp\u003eModel performance ranged from R\u0026sup2; = 0.14\u0026ndash;0.26 for Sentinel-2, R\u0026sup2; = 0.46\u0026ndash;0.54 for Landsat-8/9, and R\u0026sup2; = 0.56\u0026ndash;0.68 for the Combined scenario. The best performance was achieved by Combined\u0026thinsp;+\u0026thinsp;XGB (R\u0026sup2; = 0.676; RMSE\u0026thinsp;=\u0026thinsp;142.1 kg ha⁻\u0026sup1;; MAE\u0026thinsp;=\u0026thinsp;109.7 kg ha⁻\u0026sup1;; nRMSE\u0026thinsp;=\u0026thinsp;28.82%). Alongside SWIR and NDVI/OSAVI, DOY and lagged predictors made meaningful contributions to prediction skill.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"ASec5\" class=\"AbstractSection\"\u003e \u003cdiv class=\"Heading\"\u003eConclusion\u003c/div\u003e \u003cp\u003eMulti-sensor fusion coupled with boosting-based models substantially improves forage-yield prediction in wetland rangelands and enables robust spatial products for within-season monitoring.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"ASec6\" class=\"AbstractSection\"\u003e \u003cdiv class=\"Heading\"\u003eImplications and impacts:\u003c/div\u003e \u003cp\u003eThe resulting maps and trend indicators provide an actionable decision-support backbone for UNESCO-sensitive wetland landscapes, helping to guide grazing intensity, rotation/resting strategies, and adaptive management under hydrological and climatic variability while safeguarding the conservation\u0026ndash;use balance.\u003c/p\u003e \u003c/div\u003e","manuscriptTitle":"Precision forage-yield estimation in wetland rangelands through\nMulti-sensor satellite data fusion and machine learning","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2026-03-31 18:45:46","doi":"10.21203/rs.3.rs-8882230/v2","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}},{"code":1,"date":"2026-02-17 13:32:30","doi":"10.21203/rs.3.rs-8882230/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":"8f2cf1c9-d183-4ba8-a0ff-5be3eabff866","owner":[],"postedDate":"March 31st, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":63073266,"name":"Ecological Modeling"},{"id":63073267,"name":"Agronomy"}],"tags":[],"updatedAt":"2026-02-17T13:32:30+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-31 18:45:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v2","identity":"rs-8882230","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8882230","identity":"rs-8882230","version":["v2"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}