Explainable timber geographic provenance using flame emission spectroscopy dynamics and a Transformer model

Explainable timber geographic provenance using flame emission spectroscopy dynamics and a Transformer model | 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 Explainable timber geographic provenance using flame emission spectroscopy dynamics and a Transformer model José I. Cifuentes, Cristopher Oñate, Matías Espinoza, Hugo Garcés, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9047305/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract The misrepresentation of timber provenance undermines global supply chain transparency and sustainable forest management practices. Although reference forensic approaches, such as stable isotope analysis and chemical and genetic approximations, are reliable, their high cost and complexity hinder their widespread adoption. This work evaluates the feasibility of a high-throughput framework for provenance classification that integrates VIS-NIR flame emission spectroscopy dynamics and an end-to-end deep learning model. Eucalyptus globulus samples were harvested from five distinct geographical sectors in Chile and subjected to controlled combustion. Combustion kinetic profiles were recorded using a VIS-NIR spectrophotometer and processed using Transformer architecture, benchmarked against Support Vector Machine (SVM) and XGBoost classifiers. The proposed model achieved a test accuracy and F1-score of 97.5%, significantly outperforming SVM (80.0%) and XGBoost (62.5%) baselines. Traditional models exhibited severe overfitting owing to static feature compression, whereas the Transformer successfully captured the transient temporal patterns of the combustion cycle. Interpretable feature attribution analysis using Shapley Additive exPlanations (SHAP) confirms that the classification relies on specific atomic emission lines (potassium doublet at 766.4 and 770.1 nm), validating the physico-chemical basis of the model. These findings confirm that treating wood provenance as a dynamic pattern recognition task yields superior robustness, providing a data-efficient basis for a compact optical sensor for traceability that complements existing timber tracing frameworks. wood tracing forestry spectroscopy explainable artificial intelligence deep learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 01 May, 2026 Reviews received at journal 01 May, 2026 Reviewers agreed at journal 23 Apr, 2026 Reviewers agreed at journal 23 Apr, 2026 Reviewers agreed at journal 10 Apr, 2026 Reviewers invited by journal 07 Apr, 2026 Editor assigned by journal 07 Apr, 2026 Submission checks completed at journal 09 Mar, 2026 First submitted to journal 06 Mar, 2026 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-9047305","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":620757823,"identity":"5169b14d-4035-48aa-ae61-af2587618fd9","order_by":0,"name":"José I. Cifuentes","email":"","orcid":"","institution":"University of Concepción","correspondingAuthor":false,"prefix":"","firstName":"José","middleName":"I.","lastName":"Cifuentes","suffix":""},{"id":620757824,"identity":"6a52059e-32cd-45d4-b2f4-ae1054b2f823","order_by":1,"name":"Cristopher Oñate","email":"","orcid":"","institution":"University of Concepción","correspondingAuthor":false,"prefix":"","firstName":"Cristopher","middleName":"","lastName":"Oñate","suffix":""},{"id":620757825,"identity":"50bcaa51-9bc7-4c5d-84bf-50f20cc522c4","order_by":2,"name":"Matías Espinoza","email":"","orcid":"","institution":"University of Concepción","correspondingAuthor":false,"prefix":"","firstName":"Matías","middleName":"","lastName":"Espinoza","suffix":""},{"id":620757826,"identity":"fb6eb71d-0e91-4d55-a36c-57ded900c53b","order_by":3,"name":"Hugo Garcés","email":"","orcid":"","institution":"University of Concepción","correspondingAuthor":false,"prefix":"","firstName":"Hugo","middleName":"","lastName":"Garcés","suffix":""},{"id":620757827,"identity":"dca0e0f7-9412-4c16-81c4-2e19910dbcc2","order_by":4,"name":"Nikolaos Salaris","email":"","orcid":"","institution":"University College London","correspondingAuthor":false,"prefix":"","firstName":"Nikolaos","middleName":"","lastName":"Salaris","suffix":""},{"id":620757828,"identity":"5118e2f9-257c-4d2b-9297-a3f0c866ba70","order_by":5,"name":"Rosario Castillo","email":"","orcid":"","institution":"University of Concepción","correspondingAuthor":false,"prefix":"","firstName":"Rosario","middleName":"","lastName":"Castillo","suffix":""},{"id":620757829,"identity":"abb46965-0bdd-4320-9aff-921045f263cb","order_by":6,"name":"Fernando Castillo","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0UlEQVRIiWNgGAWjYBAC9gYIzcPHzsD4gIENxGZuwKuF5wCYMuBhY2ZgNoBoYSROCwNQC5sEcVrYex9++PHnjwwbM/Oxap4yG3kG9oMEtPAcN5bsbQM5jC3tNs+5NMMGnkT8Wuwl0tgYeBtAWnjMbvO2HU5gkCDkMPlnbIx//kC0FPO2/SdCiwQbUDEbRAszb9sBIrTwpDFLy7YZg/ySLDnnXLJhGyG/8LAfY/z45o+cPT9788EPb8rs5PnZDx/AqwUTsJGofhSMglEwCkYBFgAAd00zAmgWhngAAAAASUVORK5CYII=","orcid":"","institution":"University of Concepción","correspondingAuthor":true,"prefix":"","firstName":"Fernando","middleName":"","lastName":"Castillo","suffix":""}],"badges":[],"createdAt":"2026-03-06 07:23:59","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9047305/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9047305/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106960882,"identity":"6bfa3947-4a75-40fc-8254-9a44758eaea6","added_by":"auto","created_at":"2026-04-15 09:23:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1562772,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerNatureLaTeXTemplate.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9047305/v1_covered_5eb52d05-0b2c-46a5-b358-dc5aac33f59f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Explainable timber geographic provenance using flame emission spectroscopy dynamics and a Transformer model","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"wood-science-and-technology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"wsat","sideBox":"Learn more about [Wood Science and Technology](http://link.springer.com/journal/226)","snPcode":"226","submissionUrl":"https://submission.nature.com/new-submission/226/3","title":"Wood Science and Technology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"wood tracing, forestry, spectroscopy, explainable artificial intelligence, deep learning","lastPublishedDoi":"10.21203/rs.3.rs-9047305/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9047305/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe misrepresentation of timber provenance undermines global supply chain transparency and sustainable forest management practices. Although reference forensic approaches, such as stable isotope analysis and chemical and genetic approximations, are reliable, their high cost and complexity hinder their widespread adoption. This work evaluates the feasibility of a high-throughput framework for provenance classification that integrates VIS-NIR flame emission spectroscopy dynamics and an end-to-end deep learning model. \u003cem\u003eEucalyptus globulus\u003c/em\u003e samples were harvested from five distinct geographical sectors in Chile and subjected to controlled combustion. Combustion kinetic profiles were recorded using a VIS-NIR spectrophotometer and processed using Transformer architecture, benchmarked against Support Vector Machine (SVM) and XGBoost classifiers. The proposed model achieved a test accuracy and F1-score of 97.5%, significantly outperforming SVM (80.0%) and XGBoost (62.5%) baselines. Traditional models exhibited severe overfitting owing to static feature compression, whereas the Transformer successfully captured the transient temporal patterns of the combustion cycle. Interpretable feature attribution analysis using Shapley Additive exPlanations (SHAP) confirms that the classification relies on specific atomic emission lines (potassium doublet at 766.4 and 770.1 nm), validating the physico-chemical basis of the model. These findings confirm that treating wood provenance as a dynamic pattern recognition task yields superior robustness, providing a data-efficient basis for a compact optical sensor for traceability that complements existing timber tracing frameworks.\u003c/p\u003e","manuscriptTitle":"Explainable timber geographic provenance using flame emission spectroscopy dynamics and a Transformer model","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-14 14:20:07","doi":"10.21203/rs.3.rs-9047305/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-01T18:05:52+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-01T13:45:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"224735436623111766102259556891679951","date":"2026-04-23T20:03:48+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"313679622118068048615098036925993650962","date":"2026-04-23T08:20:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"331536622351355130316742196870790341138","date":"2026-04-10T07:13:48+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-07T15:24:17+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-07T15:17:20+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-09T11:13:43+00:00","index":"","fulltext":""},{"type":"submitted","content":"Wood Science and Technology","date":"2026-03-06T07:09:20+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"wood-science-and-technology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"wsat","sideBox":"Learn more about [Wood Science and Technology](http://link.springer.com/journal/226)","snPcode":"226","submissionUrl":"https://submission.nature.com/new-submission/226/3","title":"Wood Science and Technology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"ffd8f1cd-7bde-4eea-8ca0-6703fe7ae667","owner":[],"postedDate":"April 14th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-01T18:05:52+00:00","index":20,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-01T13:45:12+00:00","index":19,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-14T14:20:07+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-14 14:20:07","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9047305","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9047305","identity":"rs-9047305","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}