Enhancing Predictive Accuracy and Generalizability in Socio-Environmental Systems through Hyperparameter Optimization

Enhancing Predictive Accuracy and Generalizability in Socio-Environmental Systems through Hyperparameter Optimization | 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 Enhancing Predictive Accuracy and Generalizability in Socio-Environmental Systems through Hyperparameter Optimization Muhammad Sani Saleh, B Vijay Kumar, Karthik H.P, B Naresh kumar This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6284058/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 Environmental data is increasingly recognized as essential for informed decision-making and the promotion of sustainable practices. However, traditional methods like Ordinary Least Squares (OLS) are often susceptible to overfitting and poor generalization when analysing complex environmental datasets. This study employs Partial Least Squares (PLS) and Regularized Orthogonal Partial Least Squares (ROPLS) on 21 years of data from Nigeria, framed within the STIRPAT model. The transition from OLS to PLS and O-PLS reveals a significant enhancement in predictive power and generalizability, highlighting the importance of hyperparameter tuning and model optimization. The results show that O-PLS achieves the lowest root mean square error (RMSE) of 1,170,000, with a predictive accuracy of 0.687 based on grid searching for optimal hyperparameters. This study advocates for incorporating hyperparameter tuning in socio-environmental research to enhance predictive accuracy and model robustness. hyperparameter OPLS socio-environmental predictive accuracy generalizability STIRPAT Full Text Additional Declarations No competing interests reported. Supplementary Files DataSolidbiofls.xlsx 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-6284058","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":432832003,"identity":"6ac0f743-8a39-412c-946a-24884c685fab","order_by":0,"name":"Muhammad Sani Saleh","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7klEQVRIiWNgGAWjYFACHhAhwcDAzsDG8AHIZGMnWgszAxvjDJAWZuK0MIC1MPNAGPiB7ozcwx9+7rCw529mPvbY5tc2eT5mBsYPH3NwazG7kZcm2XtGInHGYbZ049y+24ZtzAzMkjO34dOSY8bA2yaRwHCYx0w6t+c2YxvIhbz4tRh//NsmYS9/mP+btGXPbXtitBhIA21h3HCYh02a4cftRMJazrwxk5Ztk0jceJjNTLK34XZyGzNjM36/HAc67G1bnb3c8eZnEj/+3Lad39588MNHPFpQAWMbmGwgVj0I/CFF8SgYBaNgFIwUAACfJEsCXqIU7wAAAABJRU5ErkJggg==","orcid":"","institution":"SR University","correspondingAuthor":true,"prefix":"","firstName":"Muhammad","middleName":"Sani","lastName":"Saleh","suffix":""},{"id":432832004,"identity":"4e9653ed-f805-4b98-a29e-9a5640f90b02","order_by":1,"name":"B Vijay Kumar","email":"","orcid":"","institution":"SR University","correspondingAuthor":false,"prefix":"","firstName":"B","middleName":"Vijay","lastName":"Kumar","suffix":""},{"id":432832005,"identity":"1f9eed65-e8e0-45ed-94bb-6306e588a840","order_by":2,"name":"Karthik H.P","email":"","orcid":"","institution":"SR University","correspondingAuthor":false,"prefix":"","firstName":"Karthik","middleName":"","lastName":"H.P","suffix":""},{"id":432832006,"identity":"10eccca9-a79e-46bd-965f-132a3620b859","order_by":3,"name":"B Naresh kumar","email":"","orcid":"","institution":"SR University","correspondingAuthor":false,"prefix":"","firstName":"B","middleName":"Naresh","lastName":"kumar","suffix":""}],"badges":[],"createdAt":"2025-03-22 14:08:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6284058/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6284058/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":80689809,"identity":"95f00d51-d0e2-4348-89d8-dbc31c0f6c1e","added_by":"auto","created_at":"2025-04-16 05:01:38","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":509222,"visible":true,"origin":"","legend":"","description":"","filename":"enhancingpredaccuracy.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6284058/v1_covered_8728a220-f35b-4f61-abcb-60aa7b44b05e.pdf"},{"id":79149865,"identity":"76cd7f0d-237c-447f-b756-54fc78ef071a","added_by":"auto","created_at":"2025-03-25 04:12:24","extension":"xlsx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":9979,"visible":true,"origin":"","legend":"","description":"","filename":"DataSolidbiofls.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-6284058/v1/f2c27def95e4d036e6ddf57d.xlsx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhancing Predictive Accuracy and Generalizability in Socio-Environmental Systems through Hyperparameter Optimization","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":"hyperparameter, OPLS, socio-environmental, predictive accuracy, generalizability, STIRPAT","lastPublishedDoi":"10.21203/rs.3.rs-6284058/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6284058/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eEnvironmental data is increasingly recognized as essential for informed decision-making and the promotion of sustainable practices. However, traditional methods like Ordinary Least Squares (OLS) are often susceptible to overfitting and poor generalization when analysing complex environmental datasets. This study employs Partial Least Squares (PLS) and Regularized Orthogonal Partial Least Squares (ROPLS) on 21 years of data from Nigeria, framed within the STIRPAT model. The transition from OLS to PLS and O-PLS reveals a significant enhancement in predictive power and generalizability, highlighting the importance of hyperparameter tuning and model optimization. The results show that O-PLS achieves the lowest root mean square error (RMSE) of 1,170,000, with a predictive accuracy of 0.687 based on grid searching for optimal hyperparameters. This study advocates for incorporating hyperparameter tuning in socio-environmental research to enhance predictive accuracy and model robustness.\u003c/p\u003e","manuscriptTitle":"Enhancing Predictive Accuracy and Generalizability in Socio-Environmental Systems through Hyperparameter Optimization","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-25 04:12:19","doi":"10.21203/rs.3.rs-6284058/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":"5250fe5a-85c4-45db-b779-640518d3976c","owner":[],"postedDate":"March 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-04-16T04:53:25+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-25 04:12:19","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6284058","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6284058","identity":"rs-6284058","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}