Enhanced Firefly Optimization with Lévy–Opposition Learning for Dilated–Residual U-Net Based PV Defect Segmentation

Enhanced Firefly Optimization with Lévy–Opposition Learning for Dilated–Residual U-Net Based PV Defect Segmentation | 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 Enhanced Firefly Optimization with Lévy–Opposition Learning for Dilated–Residual U-Net Based PV Defect Segmentation Mustafa Ihsan FALIH, Oguz Karan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8816179/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 13 You are reading this latest preprint version Abstract Accurate segmentation of photovoltaic (PV) defects is essential for automated inspection, performance monitoring, and long-term reliability of solar modules. This paper presents a novel defect segmentation framework that integrates a Dilated Residual U-Net with a Lévy–Opposition Learning enhanced Firefly Algorithm (FA-LOL) for hyperparameter optimization. The proposed architecture combines dilated convolutions to capture long-range spatial dependencies with residual connections that stabilize gradient flow and enhance deep feature representation. FA-LOL introduces Lévy-flight exploration and opposition-based diversity, enabling efficient navigation of the hyperparameter search space and preventing premature convergence. Experiments were conducted on two publicly available datasets: the PVEL-AD electroluminescence dataset and the Solar Cell Defect Segmentation dataset. The proposed method achieved a Dice score of 0.9353 and an IoU of 0.88 , outperforming vanilla U-Net, Residual U-Net, Dilated U-Net, and multiple optimization baselines including standard Firefly Algorithm, PSO, GWO, and ACO. Ablation studies confirm that both dilation and residual pathways significantly contribute to the observed improvements, while FA-LOL provides measurable optimization gains. These results demonstrate that the proposed FA-LOL optimized Dilated Residual U-Net is a reliable and efficient solution for high-precision PV defect segmentation across diverse imaging modalities. Photovoltaic defect segmentation U-Net Firefly Algorithm Lévy–Opposition Learning Metaheuristic optimization Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 28 Apr, 2026 Reviews received at journal 29 Mar, 2026 Reviews received at journal 25 Mar, 2026 Reviewers agreed at journal 20 Mar, 2026 Reviewers agreed at journal 20 Mar, 2026 Reviewers agreed at journal 18 Mar, 2026 Reviewers agreed at journal 16 Mar, 2026 Reviews received at journal 28 Feb, 2026 Reviewers agreed at journal 25 Feb, 2026 Reviewers invited by journal 24 Feb, 2026 Editor assigned by journal 15 Feb, 2026 Submission checks completed at journal 15 Feb, 2026 First submitted to journal 07 Feb, 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-8816179","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":597216535,"identity":"26782fbf-11b7-45c5-a7cb-bcd1b7db98c6","order_by":0,"name":"Mustafa Ihsan FALIH","email":"data:image/png;base64,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","orcid":"","institution":"Altınbaş University","correspondingAuthor":true,"prefix":"","firstName":"Mustafa","middleName":"Ihsan","lastName":"FALIH","suffix":""},{"id":597216536,"identity":"66b22141-70cc-4433-8888-290cd59fd46d","order_by":1,"name":"Oguz Karan","email":"","orcid":"","institution":"Siemens Digital Industries Foundational Technologies","correspondingAuthor":false,"prefix":"","firstName":"Oguz","middleName":"","lastName":"Karan","suffix":""}],"badges":[],"createdAt":"2026-02-07 14:24:24","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8816179/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8816179/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":103508106,"identity":"ebebf0dc-2b5c-44e6-a96a-9858047cfb79","added_by":"auto","created_at":"2026-02-26 13:47:14","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1129140,"visible":true,"origin":"","legend":"","description":"","filename":"paper3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8816179/v1_covered_dfbe2d48-813d-493e-86e4-465bee680172.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhanced Firefly Optimization with Lévy–Opposition Learning for Dilated–Residual U-Net Based PV Defect Segmentation","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":"discover-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Computing](https://link.springer.com/journal/10791)","snPcode":"10791","submissionUrl":"https://submission.springernature.com/new-submission/10791/3","title":"Discover Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Photovoltaic defect segmentation, U-Net, Firefly Algorithm, Lévy–Opposition Learning, Metaheuristic optimization","lastPublishedDoi":"10.21203/rs.3.rs-8816179/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8816179/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate segmentation of photovoltaic (PV) defects is essential for automated inspection, performance monitoring, and long-term reliability of solar modules. This paper presents a novel defect segmentation framework that integrates a Dilated Residual U-Net with a L\u0026eacute;vy\u0026ndash;Opposition Learning enhanced Firefly Algorithm (FA-LOL) for hyperparameter optimization. The proposed architecture combines dilated convolutions to capture long-range spatial dependencies with residual connections that stabilize gradient flow and enhance deep feature representation. FA-LOL introduces L\u0026eacute;vy-flight exploration and opposition-based diversity, enabling efficient navigation of the hyperparameter search space and preventing premature convergence. Experiments were conducted on two publicly available datasets: the PVEL-AD electroluminescence dataset and the Solar Cell Defect Segmentation dataset. The proposed method achieved a Dice score of \u003cb\u003e0.9353\u003c/b\u003e and an IoU of \u003cb\u003e0.88\u003c/b\u003e, outperforming vanilla U-Net, Residual U-Net, Dilated U-Net, and multiple optimization baselines including standard Firefly Algorithm, PSO, GWO, and ACO. Ablation studies confirm that both dilation and residual pathways significantly contribute to the observed improvements, while FA-LOL provides measurable optimization gains. These results demonstrate that the proposed FA-LOL optimized Dilated Residual U-Net is a reliable and efficient solution for high-precision PV defect segmentation across diverse imaging modalities.\u003c/p\u003e","manuscriptTitle":"Enhanced Firefly Optimization with Lévy–Opposition Learning for Dilated–Residual U-Net Based PV Defect Segmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-26 05:37:59","doi":"10.21203/rs.3.rs-8816179/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-28T16:52:21+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-29T14:24:04+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-25T07:30:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"81706030435800406128257116510330725405","date":"2026-03-20T13:31:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"254226429618015241137646659644981415655","date":"2026-03-20T07:21:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"88802191321689371457701411623196772579","date":"2026-03-18T04:20:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"110363768269330050198540905560134569030","date":"2026-03-17T01:24:05+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-28T12:56:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"103808893147305370212875850374861486202","date":"2026-02-26T01:06:04+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-24T14:52:20+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-16T01:28:03+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-16T01:26:51+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Computing","date":"2026-02-07T14:02:56+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"discover-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Computing](https://link.springer.com/journal/10791)","snPcode":"10791","submissionUrl":"https://submission.springernature.com/new-submission/10791/3","title":"Discover Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"7e8b689c-e787-4a00-9f5e-63a698362c3a","owner":[],"postedDate":"February 26th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-05T05:39:17+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-26 05:37:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8816179","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8816179","identity":"rs-8816179","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}