An adaptive KAN with Toptheta attention and dynamic thresholding for interpretable mineral prospectivity prediction

preprint OA: closed
Full text JSON View at publisher
Full text 26,257 characters · extracted from preprint-html · click to expand
An adaptive KAN with Toptheta attention and dynamic thresholding for interpretable mineral prospectivity prediction | 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 Article An adaptive KAN with Toptheta attention and dynamic thresholding for interpretable mineral prospectivity prediction Yonghang Lou, Yue Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8296509/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 Mineral Prospectivity Mapping (MPM) can provide key decision-making information for mineral exploration task. Deep learning provides a powerful tool for MPM. However, when dealing with high-dimensional and large-scale geological spatial data, many deep learning models are unable to deeply explore the interaction information between geological characteristics and mineralization, thereby reducing the reliability of the model results. Thus, this study proposes an adaptive Kolmogorov-Arnold network (A-KAN) model, by introducing the Toptheta attention mechanism and dynamic threshold training strategy into the Kolmogorov-Arnold network (KAN) model. Through learnable multivariate continuous functions, the A-KAN model can accurately capture the nonlinear relationships between key controlling mineralization characteristic in high-dimensional geospatial data. Specifically, this study took the MPM of the tungsten polymetallic deposits in Nanling Metallogenic Belt, China, as an example, and constructed a 41-dimensional geospatial dataset as the input of the model. The results show that compared with KAN, CNN, and SVM models, the A-KAN model has significant advantages in identifying known deposits, demonstrating stronger classification and prediction performance. More importantly, this study conducted interpretability and visualization analysis of model training and results from four aspects. This improves the rationality and reliability of the model results, providing more scientific, and reliable technical support for MPM. Earth and environmental sciences/Environmental sciences Physical sciences/Mathematics and computing Earth and environmental sciences/Solid earth sciences Kolmogorov-Arnold networks Mineral prospectivity mapping Model interpretability High-dimensional geospatial data Machine learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 10 Feb, 2026 Reviewers agreed at journal 08 Feb, 2026 Reviews received at journal 05 Jan, 2026 Reviewers agreed at journal 23 Dec, 2025 Reviewers invited by journal 23 Dec, 2025 Editor assigned by journal 17 Dec, 2025 Editor invited by journal 12 Dec, 2025 Submission checks completed at journal 09 Dec, 2025 First submitted to journal 09 Dec, 2025 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-8296509","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":564814341,"identity":"1d522940-c3a0-4213-a469-4f42ad7afb27","order_by":0,"name":"Yonghang Lou","email":"","orcid":"","institution":"China University of Geosciences","correspondingAuthor":false,"prefix":"","firstName":"Yonghang","middleName":"","lastName":"Lou","suffix":""},{"id":564814342,"identity":"e918dd6a-6698-4ed3-9470-78f98b205a9f","order_by":1,"name":"Yue Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5klEQVRIiWNgGAWjYBACPmYw9V/O/jDzAYjQAQJa2CBamI0ZjrclEKkFQjEnNpw5Y0CkFnYeM2meCjZjxhk5Hz/z/GKQ47uRwPi5AK/DQFrO8MgxS+RulubtYzCWvJHALD2DkBbeNgljNoncbcy8PQyJG24kAAUJavlnkNgjkfMMpKWeSC0NCYkzeM4A2T8YEgwIa2Ertpxz7ICxAXubseTcBgnDmWceNkvj08LPf3jjjTc1B+QMmJkffnjzx0ae73jywc/4tAABiwScydgGYjM24NcAjMYPCPYfQopHwSgYBaNgJAIAngVBbNAuMWQAAAAASUVORK5CYII=","orcid":"","institution":"China University of Geosciences","correspondingAuthor":true,"prefix":"","firstName":"Yue","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2025-12-06 19:08:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8296509/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8296509/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":99311889,"identity":"ced0c897-c0ac-4748-84cd-c3fbe2cd6300","added_by":"auto","created_at":"2025-12-31 16:17:15","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":49447325,"visible":true,"origin":"","legend":"","description":"","filename":"RevisedManuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/0f2eda9a384063662af9c77e.docx"},{"id":98992548,"identity":"4401f513-7981-442f-93ab-2484d319395a","added_by":"auto","created_at":"2025-12-25 10:54:35","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4675,"visible":true,"origin":"","legend":"","description":"","filename":"3cb9591ee1a146948554fa5d0bbedc7c.json","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/01288d463d23eb4f19aef9e1.json"},{"id":98992532,"identity":"56626f92-eee5-4801-9424-ff12d57ca0f2","added_by":"auto","created_at":"2025-12-25 10:54:33","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":219946,"visible":true,"origin":"","legend":"","description":"","filename":"3cb9591ee1a146948554fa5d0bbedc7c1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/9bd4c274141c222d29bb3a33.xml"},{"id":99312148,"identity":"c06b85b5-5fcb-4a1c-a7af-f0ebb85e9314","added_by":"auto","created_at":"2025-12-31 16:18:11","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6619192,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/6c8bf3dfac6af530e0d155d0.png"},{"id":98992533,"identity":"f7cc4733-9e3e-47da-87c3-79a6f2aaf569","added_by":"auto","created_at":"2025-12-25 10:54:34","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":230725,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/73a317eb5c43a66626c88647.png"},{"id":98992541,"identity":"9113b9b6-25cc-4e0d-b5b1-0f84d49623a8","added_by":"auto","created_at":"2025-12-25 10:54:35","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1133743,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/5ac34b061bde2a2dfc062adc.png"},{"id":98992553,"identity":"22835a23-56d5-4eca-a9f8-c799e7c03717","added_by":"auto","created_at":"2025-12-25 10:54:35","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9331512,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/c7485e916a09e318ca8d4143.png"},{"id":98992537,"identity":"2aa58263-ab12-42bb-942c-f28c1be438a7","added_by":"auto","created_at":"2025-12-25 10:54:35","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29325,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/15f69bcc04f8bd3c0d16c395.png"},{"id":99312792,"identity":"f8f590dd-9e60-412a-bc87-f62d16d59127","added_by":"auto","created_at":"2025-12-31 16:19:29","extension":"jpeg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":195092,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage14.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/055a82135119d8ae7d212d42.jpeg"},{"id":99312301,"identity":"7343109b-9cbc-44a9-9a8f-816b2f79a35f","added_by":"auto","created_at":"2025-12-31 16:18:44","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3630146,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/ecd7018f2f185e2dbba3f019.png"},{"id":98992551,"identity":"0a3798ef-ac59-41f1-b8a7-67189044eb82","added_by":"auto","created_at":"2025-12-25 10:54:35","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17284144,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/68aa8d8321945d351ee13461.png"},{"id":99312061,"identity":"311a6dc1-8c6c-49ad-9583-a8082ba4b865","added_by":"auto","created_at":"2025-12-31 16:17:49","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3189124,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/a669c31201d075881ffeae3c.png"},{"id":99313242,"identity":"5f180aad-58f5-4b59-b2fe-c30776b828a7","added_by":"auto","created_at":"2025-12-31 16:19:55","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2393344,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/a8858cab4f9aac49a64b1ea7.png"},{"id":99311986,"identity":"9cf791db-3c4c-4939-a2ce-04436041efcf","added_by":"auto","created_at":"2025-12-31 16:17:32","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1305443,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/e5f954ab1056f9a294cf8601.png"},{"id":99312883,"identity":"ea6c09c8-1d33-4ecd-9335-fa6009827161","added_by":"auto","created_at":"2025-12-31 16:19:33","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":777400,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/49af9777e02cec82f28eef14.png"},{"id":98992557,"identity":"33c8130d-71a5-4596-9291-ce2ae61eeaab","added_by":"auto","created_at":"2025-12-25 10:54:36","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4840876,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/4a8d8977d75af9001a8ba97b.png"},{"id":98992539,"identity":"20848280-0d22-4f0c-908c-350b269f4ebe","added_by":"auto","created_at":"2025-12-25 10:54:35","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":642768,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/1141cdfbcb1cddbc3196b6f9.png"},{"id":98992538,"identity":"f0732521-a48c-4603-8692-e3385dd877b8","added_by":"auto","created_at":"2025-12-25 10:54:35","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1315294,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/795a648fce07638f892acabe.png"},{"id":98992544,"identity":"00ae24f2-4eb5-4e82-9afc-f26ff474fa8c","added_by":"auto","created_at":"2025-12-25 10:54:35","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":82259,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/8a34976a7f77bc83361b2b9f.png"},{"id":99312398,"identity":"3b89f23c-3f31-463d-90c4-cbe2652c198d","added_by":"auto","created_at":"2025-12-31 16:18:56","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":336380,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/9e37b0a513f1f0255c709020.png"},{"id":98992556,"identity":"2a639ded-6b0d-4d8a-b320-2d2cd23283c8","added_by":"auto","created_at":"2025-12-25 10:54:36","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2435518,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/f523dc5881499c142fdac694.png"},{"id":98992560,"identity":"0f322240-caba-4fbe-91e7-28efe6fa9426","added_by":"auto","created_at":"2025-12-25 10:54:36","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11066,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/6a368aaf6cb994a4b6b2b905.png"},{"id":98992545,"identity":"39984dbf-aece-4c14-bdec-439a9ed83609","added_by":"auto","created_at":"2025-12-25 10:54:35","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":56861,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/af06a9e136ff085f0cd67dc2.png"},{"id":98992542,"identity":"8d7831be-ed46-47a5-b02e-159de1ab2f03","added_by":"auto","created_at":"2025-12-25 10:54:35","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1426617,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/177aa1dd2266e8b0c9ac2366.png"},{"id":99311981,"identity":"152218ba-4d15-4666-92cb-a721cb8896e8","added_by":"auto","created_at":"2025-12-31 16:17:31","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3471528,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/8c7953dc44f690289f78b9b4.png"},{"id":98992565,"identity":"c48d40cb-fac5-403e-903b-d7cb8f96e54d","added_by":"auto","created_at":"2025-12-25 10:54:36","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":585203,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/ce4a4233bc60653d2656edd5.png"},{"id":98992564,"identity":"2a7adfec-3776-4c16-af38-ebb936f6cdb9","added_by":"auto","created_at":"2025-12-25 10:54:36","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":571180,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/df2cdce6e135fdb32fb9b7e3.png"},{"id":98992559,"identity":"6b2d0305-7c81-4b8a-ab4e-0c24a9f69927","added_by":"auto","created_at":"2025-12-25 10:54:36","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":265277,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/abc123d73f4f936273d2b7a2.png"},{"id":98992546,"identity":"fa3aadf0-14a2-45ff-ad32-c4e9e60bd948","added_by":"auto","created_at":"2025-12-25 10:54:35","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":228760,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/8e2aa9cc5248989bdfd6d769.png"},{"id":99313047,"identity":"c9e5d091-a79d-47a3-a1ba-98dddd5cd7d6","added_by":"auto","created_at":"2025-12-31 16:19:44","extension":"png","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":855003,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/01963931663fcd0913434404.png"},{"id":98992552,"identity":"13702ab9-7204-458d-afed-1ea93fbbc2b6","added_by":"auto","created_at":"2025-12-25 10:54:35","extension":"png","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":231005,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/df2972503718772a38440e0a.png"},{"id":98992562,"identity":"ce1ed358-2a02-4da8-a33c-d03b36fc6133","added_by":"auto","created_at":"2025-12-25 10:54:36","extension":"xml","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":217264,"visible":true,"origin":"","legend":"","description":"","filename":"3cb9591ee1a146948554fa5d0bbedc7c1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/db51eb96a27bee02881b0400.xml"},{"id":98992555,"identity":"e77f67aa-0a4a-484b-8abb-18f7728c8f9d","added_by":"auto","created_at":"2025-12-25 10:54:36","extension":"html","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":242481,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1/903303f2ff4302b72d69cda1.html"},{"id":99323095,"identity":"efa95f00-54f8-4211-be5d-f065ce0ff803","added_by":"auto","created_at":"2025-12-31 16:44:56","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2413749,"visible":true,"origin":"","legend":"","description":"","filename":"RevisedManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8296509/v1_covered_254bbf8c-f981-47fd-a1a2-e2b68bdce222.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An adaptive KAN with Toptheta attention and dynamic thresholding for interpretable mineral prospectivity prediction","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Kolmogorov-Arnold networks, Mineral prospectivity mapping, Model interpretability, High-dimensional geospatial data, Machine learning","lastPublishedDoi":"10.21203/rs.3.rs-8296509/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8296509/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMineral Prospectivity Mapping (MPM) can provide key decision-making information for mineral exploration task. Deep learning provides a powerful tool for MPM. However, when dealing with high-dimensional and large-scale geological spatial data, many deep learning models are unable to deeply explore the interaction information between geological characteristics and mineralization, thereby reducing the reliability of the model results. Thus, this study proposes an adaptive Kolmogorov-Arnold network (A-KAN) model, by introducing the Toptheta attention mechanism and dynamic threshold training strategy into the Kolmogorov-Arnold network (KAN) model. Through learnable multivariate continuous functions, the A-KAN model can accurately capture the nonlinear relationships between key controlling mineralization characteristic in high-dimensional geospatial data. Specifically, this study took the MPM of the tungsten polymetallic deposits in Nanling Metallogenic Belt, China, as an example, and constructed a 41-dimensional geospatial dataset as the input of the model. The results show that compared with KAN, CNN, and SVM models, the A-KAN model has significant advantages in identifying known deposits, demonstrating stronger classification and prediction performance. More importantly, this study conducted interpretability and visualization analysis of model training and results from four aspects. This improves the rationality and reliability of the model results, providing more scientific, and reliable technical support for MPM.\u003c/p\u003e","manuscriptTitle":"An adaptive KAN with Toptheta attention and dynamic thresholding for interpretable mineral prospectivity prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-25 10:54:28","doi":"10.21203/rs.3.rs-8296509/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-10T09:51:32+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"237499346359330611415114200323641195327","date":"2026-02-08T20:58:36+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-05T16:18:17+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"333590312829828861071189698675625826700","date":"2025-12-23T13:01:51+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-23T11:49:45+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-17T14:03:11+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-12-12T14:02:15+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-10T04:39:08+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-12-10T04:29:20+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"379b8906-6fd4-45e9-afbf-49890ff32824","owner":[],"postedDate":"December 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":60137453,"name":"Earth and environmental sciences/Environmental sciences"},{"id":60137454,"name":"Physical sciences/Mathematics and computing"},{"id":60137455,"name":"Earth and environmental sciences/Solid earth sciences"}],"tags":[],"updatedAt":"2026-04-30T23:23:11+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-25 10:54:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8296509","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8296509","identity":"rs-8296509","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00