An Effective Artificial Intelligence Pipeline for Automatic Manatee Count Using Their Tonal Vocalizations

An Effective Artificial Intelligence Pipeline for Automatic Manatee Count Using Their Tonal Vocalizations | 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 An Effective Artificial Intelligence Pipeline for Automatic Manatee Count Using Their Tonal Vocalizations Fabricio Quirós-Corella, Priscilla Cubero-Pardo, Athena Rycyk, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5418369/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 Despite their vulnerable status, manatee conservation efforts are hindered because of limited scientific data due to the data collection challenges. Bio-acoustic studies utilizing advanced computational analy- sis of long-term recordings offer a promising approach for determining the manatee’s presence and abundance. The following manuscript describes an artificial intelligence pipeline that effectively implements automatic manatee identification and counting. The first step is fine-tuning a pre- trained deep neuronal network using transfer learning to detect manatee sounds with a binary accuracy of 96%. In the second phase, the pipeline implements an unsupervised learning method to group acoustic fea- tures of the detected sounds with a clustering score of 72%. The article addresses the implications and the outcomes of testing this proof of con- cept under experimental conditions with passive acoustics monitoring data on the Caribbean coast of Costa Rica and Panama. Artificial Intelligence and Machine Learning Artificial intelligence bio-acoustics clustering deep learning machine learning music information retrieval passive acoustics monitoring transfer learning unsupervised learning. Full Text Additional Declarations The authors declare no competing interests. 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-5418369","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":375890168,"identity":"871b7a6f-078b-4110-903b-0b38be8130cd","order_by":0,"name":"Fabricio Quirós-Corella","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzklEQVRIiWNgGAWjYBAC9gYGhgNAWo54LTwHIFqMwbwDxGoBgcQG4rWw5xgerqioS+9v7z34+QODnTwD+9kH+LXwvDE4eObM4dwZZ84lSxxgSDZs4Ek3wKvFXiLH4GBj24HcDUAGUAtzAoMEGwGHQbTUpRvIvzH+cYChnmgtzAkGEjxmQFsOE6GF51nBwYYzhw1nnMkxszhjcNywjSeNgBb25M0fGyrq5PnbzxjfqKioludnP4ZfCwNDAjIHGFYEnIWhZRSMglEwCkYBFgAAydhAp/sqog0AAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0001-5248-2249","institution":"National High Technology Center","correspondingAuthor":true,"prefix":"","firstName":"Fabricio","middleName":"","lastName":"Quirós-Corella","suffix":""},{"id":375890169,"identity":"1a678c64-1892-44b0-8790-92c9ccaacd92","order_by":1,"name":"Priscilla Cubero-Pardo","email":"","orcid":"","institution":"National High Technology Center","correspondingAuthor":false,"prefix":"","firstName":"Priscilla","middleName":"","lastName":"Cubero-Pardo","suffix":""},{"id":375890170,"identity":"0a635444-b8b2-4df4-9ff4-9ef66e58b1e3","order_by":2,"name":"Athena Rycyk","email":"","orcid":"","institution":"New College of Florida","correspondingAuthor":false,"prefix":"","firstName":"Athena","middleName":"","lastName":"Rycyk","suffix":""},{"id":375890171,"identity":"8c5492f2-0d73-438f-8eec-7f5d2ea0508a","order_by":3,"name":"Beth Brady","email":"","orcid":"","institution":"Save the Manatee Club","correspondingAuthor":false,"prefix":"","firstName":"Beth","middleName":"","lastName":"Brady","suffix":""},{"id":375890172,"identity":"87f38f25-673b-4116-9e40-f6ed2b60fcac","order_by":4,"name":"César Castro-Azofeifa","email":"","orcid":"","institution":"National High Technology Center","correspondingAuthor":false,"prefix":"","firstName":"César","middleName":"","lastName":"Castro-Azofeifa","suffix":""},{"id":375890173,"identity":"6c817774-64fb-4a38-b42e-097dc8ea8e7a","order_by":5,"name":"Sebastián Mora-Ramı́rez","email":"","orcid":"","institution":"National High Technology Center","correspondingAuthor":false,"prefix":"","firstName":"Sebastián","middleName":"","lastName":"Mora-Ramı́rez","suffix":""},{"id":375890174,"identity":"08dd4215-f9ec-45ee-b0e7-8b4108ddee66","order_by":6,"name":"Juan Pablo Ureña-Madrigal","email":"","orcid":"","institution":"National High Technology Center","correspondingAuthor":false,"prefix":"","firstName":"Juan","middleName":"Pablo","lastName":"Ureña-Madrigal","suffix":""}],"badges":[],"createdAt":"2024-11-08 18:29:59","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-5418369/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5418369/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":68775046,"identity":"8b11fb3a-22bc-4144-847d-05229344337c","added_by":"auto","created_at":"2024-11-12 01:24:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":947418,"visible":true,"origin":"","legend":"","description":"","filename":"paper015.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5418369/v1_covered_97653b89-1d97-4bb6-8216-164228583bfa.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eAn Effective Artificial Intelligence Pipeline for Automatic Manatee Count Using Their Tonal Vocalizations\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[{"identity":"918164b6-cc03-43e1-8944-3abe6653803e","identifier":"10.13039/100006363","name":"National Geographic Society","awardNumber":"NGS-84535T-21","order_by":0},{"identity":"3ae3427d-8fbc-4206-a190-f3595b264250","identifier":"10.13039/100006112","name":"Microsoft Research","awardNumber":"69005a29-9390-4178-b6a2- 4e4b68b470c6","order_by":1}],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"National High Technology Center","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"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":"Artificial intelligence, bio-acoustics, clustering, deep learning, machine learning, music information retrieval, passive acoustics monitoring, transfer learning, unsupervised learning.","lastPublishedDoi":"10.21203/rs.3.rs-5418369/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5418369/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDespite their vulnerable status, manatee conservation efforts are hindered because of limited scientific data due to the data collection challenges. Bio-acoustic studies utilizing advanced computational analy- sis of long-term recordings offer a promising approach for determining the manatee’s presence and abundance. The following manuscript describes an artificial intelligence pipeline that effectively implements automatic manatee identification and counting. The first step is fine-tuning a pre- trained deep neuronal network using transfer learning to detect manatee sounds with a binary accuracy of 96%. In the second phase, the pipeline implements an unsupervised learning method to group acoustic fea- tures of the detected sounds with a clustering score of 72%. The article addresses the implications and the outcomes of testing this proof of con- cept under experimental conditions with passive acoustics monitoring data on the Caribbean coast of Costa Rica and Panama.\u003c/p\u003e","manuscriptTitle":"An Effective Artificial Intelligence Pipeline for Automatic Manatee Count Using Their Tonal Vocalizations","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-12 01:16:41","doi":"10.21203/rs.3.rs-5418369/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":"21028683-c8d4-4728-8ed8-a70ff2c1fa5e","owner":[],"postedDate":"November 12th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":40022795,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2024-11-12T01:16:41+00:00","versionOfRecord":[],"versionCreatedAt":"2024-11-12 01:16:41","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5418369","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5418369","identity":"rs-5418369","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}