Comparative Analysis of Linear Regression and Machine Learning Models for Dead Fuel Moisture Content Prediction in Golestan Province Forests, NE Iran

Comparative Analysis of Linear Regression and Machine Learning Models for Dead Fuel Moisture Content Prediction in Golestan Province Forests, NE Iran | 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 Comparative Analysis of Linear Regression and Machine Learning Models for Dead Fuel Moisture Content Prediction in Golestan Province Forests, NE Iran Mhd. Wathek Alhaj-Khalaf, Shaban Shataee Jouibary, Roghayeh Jahdi, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5093197/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 Aim of Study : This study evaluates the performance of machine learning models versus linear regression models in predicting Fuel Moisture Content (FMC) for different time-lag fuel classes (1-hr, 10-hr, and litter) in Golestan province, NE Iran. Area of Study : The study was conducted across Golestan province, NE, Iran. Material and Methods : The FMC data are collected from 235 plots, and The models of Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting (GBoost), and Convolutional Neural Network (CNN) have been employed in predicting FMC using meteorological variables and topographic features. Main Results : Multivariable machine learning models outperformed univariate models. RF achieved the highest accuracy with an R²adj of 97.08 and a relative RMSE of 5.93% on training data and an R²adj of 87.99 with a relative RMSE of 10.44% on test data. SVM also performed well, with R²adj values of 85.40 for training data and 86.86 for test data. In contrast, linear regression models showed lower accuracy, with RH as the best univariate model, achieving an R²_adj of 66.70 and a relative RMSE of 18.90%. Multivariable regression models improved performance but still fell short of machine learning models. Research Highlights : RH and VPD were identified as the most important variables for FMC prediction, particularly in fine fuels. Machine learning models demonstrated superior performance due to their ability to describe nonlinear relationships and handle high-dimensional data. Further research should explore incorporating additional environmental variables and expanding the study to other regions and fuel types to refine model accuracy. Forestry Environmental variables FMC Machin Learning Regression model Full Text Additional Declarations The authors declare no competing interests. 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-5093197","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":354294906,"identity":"4562a481-99f6-438d-ac16-57054ca0f4e2","order_by":0,"name":"Mhd. Wathek Alhaj-Khalaf","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA70lEQVRIiWNgGAWjYDACCQYDEJXAwMN88MEHIIuNnTgtBkAtbMmGM0BamInXwmMmzQMSIaRFd3bzBmaemj95/DxnDKRtfm2T52NmYPzwMQe3FrM7xwqYeY4ZFEv2thUY5/bdNmxjZmCWnLkNj5YbOQbMOWwGiRvOM29Izu25zQjUwsbMS1DLP4PE/ecZDA5b9ty2J05LbhvQFt4Ww2aGH7cTidCSVnD4b59x4owzx5IZextuJ7cxMzYT8Evyxoczvskl9vckH//x489t2/ntzQc/fMSjBQQOwFmMbWCyAb96VPCHFMWjYBSMglEwUgAAM3lTiDATq0QAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0003-4091-4598","institution":"Faculty of Forest Sciences, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran.","correspondingAuthor":true,"prefix":"","firstName":"Mhd.","middleName":"Wathek","lastName":"Alhaj-Khalaf","suffix":""},{"id":354295002,"identity":"b4f25b21-a3b6-4991-9fbd-99dc3c2a9f2c","order_by":1,"name":"Shaban Shataee Jouibary","email":"","orcid":"https://orcid.org/0000-0002-3868-8475","institution":"Faculty of Forest Sciences, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran.","correspondingAuthor":false,"prefix":"","firstName":"Shaban","middleName":"Shataee","lastName":"Jouibary","suffix":""},{"id":354295078,"identity":"987ed3fb-3519-47c1-bbb2-6496b4bc5f5e","order_by":2,"name":"Roghayeh Jahdi","email":"","orcid":"https://orcid.org/0000-0002-9461-9511","institution":"Faculty of Agriculture and Natural Resources, University of Mohaghegh Ardabili, Ardabil, Iran.","correspondingAuthor":false,"prefix":"","firstName":"Roghayeh","middleName":"","lastName":"Jahdi","suffix":""},{"id":354295079,"identity":"27e20f42-b41e-44ea-a65d-70a676b8cc67","order_by":3,"name":"William M. Jolly","email":"","orcid":"https://orcid.org/0000-0002-0457-6563","institution":"The United States Forest Service (USFS), Rocky Mountain Research Station, Missoula Fire Sciences Laboratory","correspondingAuthor":false,"prefix":"","firstName":"William","middleName":"M.","lastName":"Jolly","suffix":""}],"badges":[],"createdAt":"2024-09-15 14:51:31","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false,"coiExplicitlySet":false},"doi":"10.21203/rs.3.rs-5093197/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5093197/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":64649607,"identity":"7a84454f-6a5c-42d2-8d2e-8650ab313703","added_by":"auto","created_at":"2024-09-17 05:03:23","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":948775,"visible":true,"origin":"","legend":"","description":"","filename":"FS.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5093197/v1_covered_b210ae1e-f282-439c-9da2-6ef7c792dab9.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eComparative Analysis of Linear Regression and Machine Learning Models for Dead Fuel Moisture Content Prediction in Golestan Province Forests, NE Iran\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Gorgan University of Agricultural Sciences and Natural Resources","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":"Environmental variables, FMC, Machin Learning, Regression model","lastPublishedDoi":"10.21203/rs.3.rs-5093197/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5093197/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cem\u003e\u003cstrong\u003eAim of Study\u003c/strong\u003e\u003c/em\u003e\u003cem\u003e: \u003c/em\u003eThis study evaluates the performance of machine learning models versus linear regression models in predicting Fuel Moisture Content (FMC) for different time-lag fuel classes (1-hr, 10-hr, and litter) in Golestan province, NE Iran.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e\u003cstrong\u003eArea of Study\u003c/strong\u003e\u003c/em\u003e\u003cem\u003e: \u003c/em\u003eThe study was conducted across Golestan province, NE, Iran.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e\u003cstrong\u003eMaterial and Methods\u003c/strong\u003e\u003c/em\u003e\u003cem\u003e: \u003c/em\u003eThe FMC data are collected from 235 plots, and The models of Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting (GBoost), and Convolutional Neural Network (CNN) have been employed in predicting FMC using meteorological variables and topographic features.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e\u003cstrong\u003eMain Results\u003c/strong\u003e\u003c/em\u003e\u003cem\u003e: \u003c/em\u003eMultivariable machine learning models outperformed univariate models. RF achieved the highest accuracy with an R²adj of 97.08 and a relative RMSE of 5.93% on training data and an R²adj of 87.99 with a relative RMSE of 10.44% on test data. SVM also performed well, with R²adj values of 85.40 for training data and 86.86 for test data. In contrast, linear regression models showed lower accuracy, with RH as the best univariate model, achieving an R²_adj of 66.70 and a relative RMSE of 18.90%. Multivariable regression models improved performance but still fell short of machine learning models.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e\u003cstrong\u003eResearch Highlights\u003c/strong\u003e\u003c/em\u003e\u003cem\u003e: \u003c/em\u003eRH and VPD were identified as the most important variables for FMC prediction, particularly in fine fuels. Machine learning models demonstrated superior performance due to their ability to describe nonlinear relationships and handle high-dimensional data. Further research should explore incorporating additional environmental variables and expanding the study to other regions and fuel types to refine model accuracy.\u003c/p\u003e","manuscriptTitle":"Comparative Analysis of Linear Regression and Machine Learning Models for Dead Fuel Moisture Content Prediction in Golestan Province Forests, NE Iran","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-17 04:55:15","doi":"10.21203/rs.3.rs-5093197/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":"490373f2-b62d-468b-9644-d8dc31b1be55","owner":[],"postedDate":"September 17th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":37651489,"name":"Forestry"}],"tags":[],"updatedAt":"2024-09-17T04:55:16+00:00","versionOfRecord":[],"versionCreatedAt":"2024-09-17 04:55:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5093197","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5093197","identity":"rs-5093197","version":["v1"]},"buildId":"_2-kVJe1T_tPrBINL-cwx","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}