Methodological approach to response surfaces and Bayesian optimization using the Gaussian process as predictive tools for lignin extraction from Pterocarpus tinctorius

Methodological approach to response surfaces and Bayesian optimization using the Gaussian process as predictive tools for lignin extraction from Pterocarpus tinctorius | 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 Methodological approach to response surfaces and Bayesian optimization using the Gaussian process as predictive tools for lignin extraction from Pterocarpus tinctorius Njouond Kamdem Donald, Kenmogne Sidonie Beatrice, Wansi Jean Duplex This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8781383/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 An annual yield of wood dust is produced, with a notable contribution arising from African padauk ( Pterocarpus tinctorius ). This wood species, a by-product of the forestry industry, has heretofore been underutilized. The objective of this study was to optimize the conditions for alkaline hydrolysis for the extraction of lignin from Pterocarpus tinctorius using two different approaches: response surface methodology (RSM) and Bayesian methodology using the Gaussian process (GP). A comprehensive general design was employed to evaluate the influence of five key factors in the process of lignin extraction by basic hydrolysis. These factors were as follows: the concentration of the NaOH solution (X1: 3 to 7% w/v), the stirring speed of the medium (X2: 150 to 250 rpm), the solid/liquid ratio (X3: 0.05 to 0.1% w/v), the temperature (X4: 60 to 100°C) and the duration (X5: 2 to 6 hours). The objective was to maximize lignin yield. The models were evaluated using a range of coefficient of determination (R²), mean square error (MSE), mean absolute error (MAE) and Pearson's X² metrics. The results indicated that Bayesian Optimization (BO) demonstrated superior performance in comparison to the response surface model (RSM) (R²=99.962; MSE = 0.049; MAE = 0.051; and X²=0.078). The BO model exhibited a significantly higher R² value (99.962%) compared to the RSM (R 2 = 97.014%), as well as a lower MSE (0.049) and MAE (0.051). Additionally, the BO model exhibited a lower X² value (0.078) in comparison to the RSM (5.756). The disparities observed between the various validation coefficients are sufficiently pronounced to substantiate the conclusion that BO is by far the most suitable method for this process. In accordance with the predictions made by the BO, the optimal conditions were determined as follows: The experimental conditions comprised a soda percentage of 5%, a rotation speed of 178 rpm, a solid/liquid ratio of 0.074, a temperature of 72.8°C and a duration of 4 hours and 36 minutes. These conditions were optimized to maximize lignin yield, which corresponded to a polyphenolic content of 182.065 mg gallic acid equivalent/g extract with a desirability of 98.29%. The analysis of the functional groups present in the sample was carried out by Fourier transform infrared spectroscopy (FTIR). This analysis revealed the presence of lignin and clearly distinguished the FTIR spectrum of sawdust from that of lignin. X-ray fluorescence spectroscopy was utilized to ascertain the presence of oxides, including Na2O, K2O, Al2O3, SiO2, CaO, MgO, Fe2O3, SO3, P2O5, TiO2, MnO, and ZrO2, with a content of 1.20%, which was found to be proximate to the ash content of 1.76%. X-ray diffraction analysis was performed in order to ascertain the crystalline nature of the sawdust (CrI = 57.56%) and the amorphous nature of the lignin obtained, with an average nanoparticle size of 0.53 nm. Morphological analysis by EDX revealed a highly porous structure of Pterocarpus tinctorius sawdust (which explains the efficiency of the extraction) and an irregular and compact structure of the lignin obtained. This work contributes to the optimization of environmentally friendly extraction techniques and provides a basis for the potential valorization of lignin in the pharmaceutical, cosmetics and coating materials industries. Subsequent research will concentrate on its utilization in sustainable (bio-based) epoxy resin synthesis systems. Response surface methodology Bayesian optimization Pterocarpus tinctorius lignin alkaline hydrolysis Full Text Additional Declarations No competing interests reported. Table 1 to 6 are available in the Supplementary Files section. Supplementary Files Tables.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-8781383","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":587394266,"identity":"2fa10659-8664-447e-8b24-b490403c5a23","order_by":0,"name":"Njouond Kamdem Donald","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+ElEQVRIiWNgGAWjYDCCA0D8gC0BSALxhwogzczcQFhLAlQL44wzIC2MJGhh5mwDCRHQwne89+CHhLI0ed325KObGefVRvO3A7X8qNiGU4vkmXPJEgnncgy3nXmWdrtw2/HcGYcZGxh7ztzGqcXgRo6BRGJbBeO2Gzlmt2duO5bbANTCzNiGV4vxD6AW+2038r/d5p1zLHc+EVrMgLbkJAJtYbvN21CTu4GQFskzZ8wsEs6lJQP9YnZzxrEDuRuBWg7i8wvf8R7jGx/Kkm23HU9+duNDTV3uvPOHDz74UYFbCzo4DCYPEK0eCOpIUTwKRsEoGAUjBAAAVi9qgWeXfKQAAAAASUVORK5CYII=","orcid":"","institution":"University of Douala","correspondingAuthor":true,"prefix":"","firstName":"Njouond","middleName":"Kamdem","lastName":"Donald","suffix":""},{"id":587394267,"identity":"f6f50b5f-e13a-4531-bd0e-18c7593d35d2","order_by":1,"name":"Kenmogne Sidonie Beatrice","email":"","orcid":"","institution":"University of Douala","correspondingAuthor":false,"prefix":"","firstName":"Kenmogne","middleName":"Sidonie","lastName":"Beatrice","suffix":""},{"id":587394268,"identity":"4fd0ea68-a651-4574-bcf1-71a490d1cfa9","order_by":2,"name":"Wansi Jean Duplex","email":"","orcid":"","institution":"University of Douala","correspondingAuthor":false,"prefix":"","firstName":"Wansi","middleName":"Jean","lastName":"Duplex","suffix":""}],"badges":[],"createdAt":"2026-02-04 03:39:06","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8781383/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8781383/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102297438,"identity":"510490f5-87c2-4674-a17f-2457b5a35dc6","added_by":"auto","created_at":"2026-02-10 10:27:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":958295,"visible":true,"origin":"","legend":"","description":"","filename":"Methodologicalapproach3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8781383/v1_covered_216711cf-bd09-4090-95c9-5546e9c8f6ab.pdf"},{"id":102216879,"identity":"01fad6f8-439a-40c4-9530-8f3f9b90cbd3","added_by":"auto","created_at":"2026-02-09 13:00:56","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":34698,"visible":true,"origin":"","legend":"","description":"","filename":"Tables.docx","url":"https://assets-eu.researchsquare.com/files/rs-8781383/v1/329aed69eba76b7e25c57c8d.docx"}],"financialInterests":"\u003cp\u003eNo competing interests reported.\u003c/p\u003e\n\u003cp\u003eTable 1 to 6 are available in the Supplementary Files section.\u003c/p\u003e","formattedTitle":"Methodological approach to response surfaces and Bayesian optimization using the Gaussian process as predictive tools for lignin extraction from Pterocarpus tinctorius","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":"Response surface methodology, Bayesian optimization, Pterocarpus tinctorius, lignin, alkaline hydrolysis","lastPublishedDoi":"10.21203/rs.3.rs-8781383/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8781383/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAn annual yield of wood dust is produced, with a notable contribution arising from African padauk (\u003cem\u003ePterocarpus tinctorius\u003c/em\u003e). This wood species, a by-product of the forestry industry, has heretofore been underutilized. The objective of this study was to optimize the conditions for alkaline hydrolysis for the extraction of lignin from \u003cem\u003ePterocarpus tinctorius\u003c/em\u003e using two different approaches: response surface methodology (RSM) and Bayesian methodology using the Gaussian process (GP). A comprehensive general design was employed to evaluate the influence of five key factors in the process of lignin extraction by basic hydrolysis. These factors were as follows: the concentration of the NaOH solution (X1: 3 to 7% w/v), the stirring speed of the medium (X2: 150 to 250 rpm), the solid/liquid ratio (X3: 0.05 to 0.1% w/v), the temperature (X4: 60 to 100\u0026deg;C) and the duration (X5: 2 to 6 hours). The objective was to maximize lignin yield. The models were evaluated using a range of coefficient of determination (R\u0026sup2;), mean square error (MSE), mean absolute error (MAE) and Pearson's X\u0026sup2; metrics. The results indicated that Bayesian Optimization (BO) demonstrated superior performance in comparison to the response surface model (RSM) (R\u0026sup2;=99.962; MSE\u0026thinsp;=\u0026thinsp;0.049; MAE\u0026thinsp;=\u0026thinsp;0.051; and X\u0026sup2;=0.078). The BO model exhibited a significantly higher R\u0026sup2; value (99.962%) compared to the RSM (R\u003csup\u003e2\u003c/sup\u003e\u0026thinsp;=\u0026thinsp;97.014%), as well as a lower MSE (0.049) and MAE (0.051). Additionally, the BO model exhibited a lower X\u0026sup2; value (0.078) in comparison to the RSM (5.756). The disparities observed between the various validation coefficients are sufficiently pronounced to substantiate the conclusion that BO is by far the most suitable method for this process. In accordance with the predictions made by the BO, the optimal conditions were determined as follows: The experimental conditions comprised a soda percentage of 5%, a rotation speed of 178 rpm, a solid/liquid ratio of 0.074, a temperature of 72.8\u0026deg;C and a duration of 4 hours and 36 minutes. These conditions were optimized to maximize lignin yield, which corresponded to a polyphenolic content of 182.065 mg gallic acid equivalent/g extract with a desirability of 98.29%. The analysis of the functional groups present in the sample was carried out by Fourier transform infrared spectroscopy (FTIR). This analysis revealed the presence of lignin and clearly distinguished the FTIR spectrum of sawdust from that of lignin. X-ray fluorescence spectroscopy was utilized to ascertain the presence of oxides, including Na2O, K2O, Al2O3, SiO2, CaO, MgO, Fe2O3, SO3, P2O5, TiO2, MnO, and ZrO2, with a content of 1.20%, which was found to be proximate to the ash content of 1.76%. X-ray diffraction analysis was performed in order to ascertain the crystalline nature of the sawdust (CrI\u0026thinsp;=\u0026thinsp;57.56%) and the amorphous nature of the lignin obtained, with an average nanoparticle size of 0.53 nm. Morphological analysis by EDX revealed a highly porous structure of \u003cem\u003ePterocarpus tinctorius\u003c/em\u003e sawdust (which explains the efficiency of the extraction) and an irregular and compact structure of the lignin obtained. This work contributes to the optimization of environmentally friendly extraction techniques and provides a basis for the potential valorization of lignin in the pharmaceutical, cosmetics and coating materials industries. Subsequent research will concentrate on its utilization in sustainable (bio-based) epoxy resin synthesis systems.\u003c/p\u003e","manuscriptTitle":"Methodological approach to response surfaces and Bayesian optimization using the Gaussian process as predictive tools for lignin extraction from Pterocarpus tinctorius","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-09 13:00:52","doi":"10.21203/rs.3.rs-8781383/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":"e1015ceb-aa7c-4cbc-8c1c-656cc065ff99","owner":[],"postedDate":"February 9th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-02-18T10:08:08+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-09 13:00:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8781383","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8781383","identity":"rs-8781383","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}