Multi-Sensor Remote Sensing and Machine Learning Integration for assessing Interannual Variability of Biomass Resources in a Sahelian Ecosystem

Multi-Sensor Remote Sensing and Machine Learning Integration for assessing Interannual Variability of Biomass Resources in a Sahelian Ecosystem | 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 Multi-Sensor Remote Sensing and Machine Learning Integration for assessing Interannual Variability of Biomass Resources in a Sahelian Ecosystem Mohamed Mounton, Abdoul Aziz Diouf This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9599606/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 Strengthening feed security in Sahelian rangelands is essential under increasing climatic variability and growing pressure on natural resources. The dry season represents the most critical period for livestock, yet it remains insufficiently monitored. This study aims to assess dry-season forage availability in Senegal using multi-sensor remote sensing and machine learning approaches. Field measurements of herbaceous dry mass (BH) and total forage dry mass (BT) were collected at 30 monitoring sites between 2023 and 2025. A total of 5 radar indices and 29 spectral indices derived from Sentinel-1, Sentinel-2, and Sentinel-3 data were evaluated. Relevant predictors were selected using Recursive Feature Elimination and multicollinearity analysis. Three modeling approaches were tested: multiple linear regression, Random Forest, and Gradient Boosting Machines. Results indicate that Sentinel-2 consistently provides the best performance. For the most favorable configurations, BH estimation reached coefficients of determination (R²) up to 0.79 with a root mean square error (RMSE) of approximately 380 kg DM ha⁻¹, while BT estimation achieved R² values up to 0.62 with an RMSE of approximately 930 kg DM ha⁻¹. Model performance varied across years, with non-linear models better capturing highly variable conditions. The inclusion of year as a categorical variable substantially improved model accuracy, increasing R² up to 0.64 for BH and 0.65 for BT in multi-year analyses. Spatial extrapolation demonstrated that the selected models reliably capture the spatial distribution of dry-season forage resources. These findings highlight the importance of combining spectral information and temporal variability to improve biomass estimation and support early warning systems for pastoral management in Sahelian ecosystems. Dry season biomass monitoring Multi-sensor remote sensing Machine learning Interannual variability Sahelian rangelands Full Text Additional Declarations The authors declare no competing interests. Supplementary Files DataSheet.docx 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-9599606","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":633601535,"identity":"ff6530c3-625d-4248-ab9a-eaaaada2facd","order_by":0,"name":"Mohamed Mounton","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAtklEQVRIiWNgGAWjYDADfhCRUEC0+gQGBskGEG1AihaDAyAGMVp0px0+Jl34wybP+PzqxA8PDBjk+cUO4NdidjstTXpGQlqx2Y23myWADjOcOTuBkJYcM2mehMOJ226c3QDSkmBwm1gtm2ec3fyDNC0b+Hu3EWtLWrI1T1pa4owbvNssEgwkiPFL8sHbPDY2if39Zzff/FFhI88vTUALAkiAVUoQqxwE+A+QonoUjIJRMApGEgAAhwZDyhfSY2YAAAAASUVORK5CYII=","orcid":"","institution":"University of Yaounde 1","correspondingAuthor":true,"prefix":"","firstName":"Mohamed","middleName":"","lastName":"Mounton","suffix":""},{"id":633601625,"identity":"9fea9601-0de0-4f19-8f7a-0f1827f6db65","order_by":1,"name":"Abdoul Aziz Diouf","email":"","orcid":"","institution":"CSE","correspondingAuthor":false,"prefix":"","firstName":"Abdoul","middleName":"Aziz","lastName":"Diouf","suffix":""}],"badges":[],"createdAt":"2026-05-03 11:52:35","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-9599606/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9599606/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108803959,"identity":"5e5d0243-b587-4228-9204-65a0c62afc21","added_by":"auto","created_at":"2026-05-08 15:12:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":532377,"visible":true,"origin":"","legend":"","description":"","filename":"OriginalArticleManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9599606/v1_covered_9d94db62-7ecd-4802-860b-3fbef8cd41ac.pdf"},{"id":108476848,"identity":"1e665e39-c812-4f85-8e03-42bd8f2970ce","added_by":"auto","created_at":"2026-05-05 07:07:00","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":57271,"visible":true,"origin":"","legend":"","description":"","filename":"DataSheet.docx","url":"https://assets-eu.researchsquare.com/files/rs-9599606/v1/25ff9182b12ca0a88a53653f.docx"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eMulti-Sensor Remote Sensing and Machine Learning Integration for assessing Interannual Variability of Biomass Resources in a Sahelian Ecosystem\u003c/strong\u003e\u003c/p\u003e","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":"Dry season biomass monitoring, Multi-sensor remote sensing, Machine learning, Interannual variability, Sahelian rangelands","lastPublishedDoi":"10.21203/rs.3.rs-9599606/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9599606/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eStrengthening feed security in Sahelian rangelands is essential under increasing climatic variability and growing pressure on natural resources. The dry season represents the most critical period for livestock, yet it remains insufficiently monitored. This study aims to assess dry-season forage availability in Senegal using multi-sensor remote sensing and machine learning approaches. Field measurements of herbaceous dry mass (BH) and total forage dry mass (BT) were collected at 30 monitoring sites between 2023 and 2025. A total of 5 radar indices and 29 spectral indices derived from Sentinel-1, Sentinel-2, and Sentinel-3 data were evaluated. Relevant predictors were selected using Recursive Feature Elimination and multicollinearity analysis. Three modeling approaches were tested: multiple linear regression, Random Forest, and Gradient Boosting Machines. Results indicate that Sentinel-2 consistently provides the best performance. For the most favorable configurations, BH estimation reached coefficients of determination (R\u0026sup2;) up to 0.79 with a root mean square error (RMSE) of approximately 380 kg DM ha⁻\u0026sup1;, while BT estimation achieved R\u0026sup2; values up to 0.62 with an RMSE of approximately 930 kg DM ha⁻\u0026sup1;. Model performance varied across years, with non-linear models better capturing highly variable conditions. The inclusion of year as a categorical variable substantially improved model accuracy, increasing R\u0026sup2; up to 0.64 for BH and 0.65 for BT in multi-year analyses. Spatial extrapolation demonstrated that the selected models reliably capture the spatial distribution of dry-season forage resources. These findings highlight the importance of combining spectral information and temporal variability to improve biomass estimation and support early warning systems for pastoral management in Sahelian ecosystems.\u003c/p\u003e","manuscriptTitle":"Multi-Sensor Remote Sensing and Machine Learning Integration for assessing Interannual Variability of Biomass Resources in a Sahelian Ecosystem","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-05 07:06:56","doi":"10.21203/rs.3.rs-9599606/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":"8d8eaac7-c9e4-4438-9e8c-5b0898cc2c17","owner":[],"postedDate":"May 5th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-05T07:06:56+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-05 07:06:56","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9599606","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9599606","identity":"rs-9599606","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}