Machine learning models and SHAP-based interpretability for predicting the strength of cemented rock fill in an underground mine un Pataz, Peru

Machine learning models and SHAP-based interpretability for predicting the strength of cemented rock fill in an underground mine un Pataz, Peru | 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 Machine learning models and SHAP-based interpretability for predicting the strength of cemented rock fill in an underground mine un Pataz, Peru Javier Quispe-Pari, Juan A. Vega-Gonzalez, Jairo J. Marquina-Araujo, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9030746/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 The determination of uniaxial compressive strength (UCS) of cemented rock fill (CRF) in underground mining relies on laboratory testing and curing periods, delaying mix-design decisions and quality control when operational thresholds must be met. This study evaluated and compared machine learning models and Shapley Additive Explanations (SHAP) interpretability to predict CRF UCS at an underground mine in Pataz (La Libertad, Peru). An experimental dataset included mix variables cement (C), water (W), waste rock (WR), and screened aggregate (SCR) and derived proportions cement content (C%), water-to-cement ratio (w/c), and waste-rock-to-cement ratio (WR/c) along with curing ages of 7, 14, and 28 days. Data were cleaned using interquartile-range capping and transformed with the Yeo–Johnson method, then split into 70% training (n = 105) and 30% testing (n = 45). Models were trained and tuned with 5-fold cross-validation, including NGBoost, EBM, CatBoost, LightGBM, and Extra Trees. Performance was assessed using the coefficient of determination (R2), RMSE, MAE, MAPE, sMAPE, NRMSE, RMSLE, and VAF. On the test set, EBM performed best (R2 = 0.98; RMSE = 0.07; MAE = 0.045; MAPE = 2.59%; sMAPE = 2.61%; NRMSE = 0.03; RMSLE = 0.02; VAF = 98.31%). SHAP interpretability confirmed that curing age (CD) was the dominant predictor (mean |SHAP| = 0.264–0.277), followed by binder- and proportion-related variables (C, C%, w/c, WR/c, and SCR). In conclusion, the proposed models enable highly accurate and explainable UCS estimation, providing a practical tool to optimize mix designs and strengthen CRF quality control under operational conditions. Cemented rock fill uniaxial compressive strength machine learning SHAP underground mining Full Text Additional Declarations No competing interests reported. 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-9030746","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":601997180,"identity":"d7c54649-a144-45fa-8e2f-f9d96e64448d","order_by":0,"name":"Javier Quispe-Pari","email":"","orcid":"","institution":"National University of Trujillo","correspondingAuthor":false,"prefix":"","firstName":"Javier","middleName":"","lastName":"Quispe-Pari","suffix":""},{"id":601997181,"identity":"eaa5baa2-9f5d-4466-aa49-5a1849afea5c","order_by":1,"name":"Juan A. Vega-Gonzalez","email":"","orcid":"","institution":"National University of Trujillo","correspondingAuthor":false,"prefix":"","firstName":"Juan","middleName":"A.","lastName":"Vega-Gonzalez","suffix":""},{"id":601997182,"identity":"8975be80-d98e-452b-b43c-ae6479659418","order_by":2,"name":"Jairo J. Marquina-Araujo","email":"","orcid":"","institution":"National University of Trujillo","correspondingAuthor":false,"prefix":"","firstName":"Jairo","middleName":"J.","lastName":"Marquina-Araujo","suffix":""},{"id":601997183,"identity":"a136c8a7-8f34-4d52-919e-6d78c1f219ff","order_by":3,"name":"Marco A. Cotrina-Teatino","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6ElEQVRIiWNgGAWjYNACAyBmb2BgSEBw8QLGBpAaHp4DQC0JRGsBAh4JkHJitOi2Hz7+uKLgjry95BuzBw9/3EtsYG/eJsG4wwanFrMzaYmNZwyeGfZI55gbJCQUJzbwHCuTYDyThlvLDR7DxgaDw4xALWYSCQkJiQ0SQAZj22GCWux7JM9Atci/AWn5T1BLYo8ED8wWHpCWA3j9MhOoJbnnTFqZREJagnEbT1qxReKZZNxajh8+8LHhz2Hb9vbD2yR/2CTI9rMf3njj4w47nFowARuISGwgQQcEMJKuZRSMglEwCoYvAADBhlPJ15su3wAAAABJRU5ErkJggg==","orcid":"","institution":"National University of Trujillo","correspondingAuthor":true,"prefix":"","firstName":"Marco","middleName":"A.","lastName":"Cotrina-Teatino","suffix":""}],"badges":[],"createdAt":"2026-03-04 13:23:42","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9030746/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9030746/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104406239,"identity":"45e08cfb-198f-4e24-8460-1f421c64c787","added_by":"auto","created_at":"2026-03-11 12:25:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2531755,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9030746/v1_covered_13875f87-771c-4840-a164-227c86022092.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Machine learning models and SHAP-based interpretability for predicting the strength of cemented rock fill in an underground mine un Pataz, Peru","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":"Cemented rock fill, uniaxial compressive strength, machine learning, SHAP, underground mining","lastPublishedDoi":"10.21203/rs.3.rs-9030746/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9030746/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The determination of uniaxial compressive strength (UCS) of cemented rock fill (CRF) in underground mining relies on laboratory testing and curing periods, delaying mix-design decisions and quality control when operational thresholds must be met. This study evaluated and compared machine learning models and Shapley Additive Explanations (SHAP) interpretability to predict CRF UCS at an underground mine in Pataz (La Libertad, Peru). An experimental dataset included mix variables cement (C), water (W), waste rock (WR), and screened aggregate (SCR) and derived proportions cement content (C%), water-to-cement ratio (w/c), and waste-rock-to-cement ratio (WR/c) along with curing ages of 7, 14, and 28 days. Data were cleaned using interquartile-range capping and transformed with the Yeo–Johnson method, then split into 70% training (n = 105) and 30% testing (n = 45). Models were trained and tuned with 5-fold cross-validation, including NGBoost, EBM, CatBoost, LightGBM, and Extra Trees. Performance was assessed using the coefficient of determination (R2), RMSE, MAE, MAPE, sMAPE, NRMSE, RMSLE, and VAF. On the test set, EBM performed best (R2 = 0.98; RMSE = 0.07; MAE = 0.045; MAPE = 2.59%; sMAPE = 2.61%; NRMSE = 0.03; RMSLE = 0.02; VAF = 98.31%). SHAP interpretability confirmed that curing age (CD) was the dominant predictor (mean |SHAP| = 0.264–0.277), followed by binder- and proportion-related variables (C, C%, w/c, WR/c, and SCR). In conclusion, the proposed models enable highly accurate and explainable UCS estimation, providing a practical tool to optimize mix designs and strengthen CRF quality control under operational conditions.","manuscriptTitle":"Machine learning models and SHAP-based interpretability for predicting the strength of cemented rock fill in an underground mine un Pataz, Peru","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-10 16:27:56","doi":"10.21203/rs.3.rs-9030746/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":"cca839db-91f2-4e7b-8a99-d31aec394a53","owner":[],"postedDate":"March 10th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-10T16:27:56+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-10 16:27:56","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9030746","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9030746","identity":"rs-9030746","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}