PSUMamba: Dual-Path Bidirectional Mamba for Plant Stress Monitoring via Temporal Hyperspectral Imaging

PSUMamba: Dual-Path Bidirectional Mamba for Plant Stress Monitoring via Temporal Hyperspectral Imaging | 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 PSUMamba: Dual-Path Bidirectional Mamba for Plant Stress Monitoring via Temporal Hyperspectral Imaging Weiqun Wang, Shirin Ghatrehsamani This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9140549/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 24 You are reading this latest preprint version Abstract Temporal hyperspectral imaging enables non-destructive monitoring of agricultural stress through spectral signatures evolving across extended observation periods, yet processing high-dimensional spatial-spectral-temporal sequences remains computationally prohibitive for real-time deployment. Traditional machine learning methods sacrifice temporal information through dimensionality reduction, while hybrid deep learning architectures combining convolutional and recurrent networks suffer from optimization pathologies at component boundaries. We introduce PSUMamba, a dual-path bidirectional Mamba architecture that processes 204-band hyperspectral sequences across eight timepoints through linear-complexity state space models, achieving 95.05% accuracy with 99.00% AUC-ROC using 153,268 parameters. The architecture maintains perfect specificity (100%) with 93.67% sensitivity while out-performing Vision Transformer with 39-fold fewer parameters and 37.5% reduced training time. Separate spectral and temporal pathways with adaptive fusion enable specialized biochemical and physiological feature extraction without quadratic attention overhead. Ablation studies confirm temporal features dominate classification under experimental conditions, with dual-path fusion providing superior probabilistic calibration (97.35% AUC) over single-path variants. Statistical comparisons demonstrate significant improvements over PLS-DA (∆=12.07%, p=0.0001), 3D CNN (∆=15.48%, p=0.0042) and 1D CNN-LSTM (∆=33.77%, p < 0.0001). The results establish PSUMamba as efficient alternatives to transformers for temporal hyperspectral classification in agricultural stress monitoring, with the dual-path framework providing a generalizable template for multimodal temporal problems requiring linear-complexity long-range dependency modeling. Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Physical sciences/Mathematics and computing biotic and abiotic stress bidirectional scanning dual-path fusion Vision Mamba selective state space real-time classification Full Text Additional Declarations No competing interests reported. Supplementary Files references.zip PSUMambaDualPathBidirectionalMambaforPlantStressMonitoringviaTemporalHyperspectralImaging.zip Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 11 May, 2026 Reviews received at journal 03 May, 2026 Reviews received at journal 15 Apr, 2026 Reviews received at journal 09 Apr, 2026 Reviews received at journal 06 Apr, 2026 Reviews received at journal 06 Apr, 2026 Reviewers agreed at journal 31 Mar, 2026 Reviews received at journal 30 Mar, 2026 Reviewers agreed at journal 30 Mar, 2026 Reviewers agreed at journal 30 Mar, 2026 Reviewers agreed at journal 29 Mar, 2026 Reviews received at journal 29 Mar, 2026 Reviewers agreed at journal 29 Mar, 2026 Reviews received at journal 27 Mar, 2026 Reviewers agreed at journal 26 Mar, 2026 Reviewers agreed at journal 26 Mar, 2026 Reviewers agreed at journal 26 Mar, 2026 Reviewers agreed at journal 26 Mar, 2026 Reviewers agreed at journal 26 Mar, 2026 Reviewers invited by journal 26 Mar, 2026 Editor invited by journal 24 Mar, 2026 Editor assigned by journal 19 Mar, 2026 Submission checks completed at journal 19 Mar, 2026 First submitted to journal 16 Mar, 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-9140549","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":614065663,"identity":"c8c650d7-7669-41f1-99d6-777863edf488","order_by":0,"name":"Weiqun Wang","email":"","orcid":"","institution":"Pennsylvania State University","correspondingAuthor":false,"prefix":"","firstName":"Weiqun","middleName":"","lastName":"Wang","suffix":""},{"id":614065664,"identity":"e04409ac-84c4-4ddf-b10f-e085ab41715d","order_by":1,"name":"Shirin Ghatrehsamani","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyElEQVRIiWNgGAWjYHAC9g8fKtjkIGw24rSwMc44w2dMmhZm3ja5xAaitcjPbr/2mLfNLH07/xkDhg9lhwlrMbhzptxwzrm03J0zcgwYZ5wjRotEToLEm7JjuRtu8BgAXUiEFvkZQC08bP/TDc6fMWD+S4wWhhvpxyR52tgSDA7kGDAzEqMF6Bdmwxln2Ax3zkgrONhzLp0Ih81uf/gAGJXy5vyHNz74UWZNhMMkeAwg1gHxASLUg7SwP4BrGQWjYBSMglGAFQAAZIU+fyIt1kIAAAAASUVORK5CYII=","orcid":"","institution":"Pennsylvania State University","correspondingAuthor":true,"prefix":"","firstName":"Shirin","middleName":"","lastName":"Ghatrehsamani","suffix":""}],"badges":[],"createdAt":"2026-03-16 17:08:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9140549/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9140549/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105750870,"identity":"7d698032-8ffd-42f2-aabd-ed90608d0b70","added_by":"auto","created_at":"2026-03-30 15:25:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3815401,"visible":true,"origin":"","legend":"","description":"","filename":"PSUMambaDualPathBidirectionalMambaforPlantStressMonitoringviaTemporalHyperspectralImaging.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9140549/v1_covered_8effb10d-eef2-48b6-8717-f1d58c4379b3.pdf"},{"id":105750519,"identity":"501cf224-0a73-4d55-9c86-9c0c434e6cdd","added_by":"auto","created_at":"2026-03-30 15:23:17","extension":"zip","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":4308,"visible":true,"origin":"","legend":"","description":"","filename":"references.zip","url":"https://assets-eu.researchsquare.com/files/rs-9140549/v1/4492ce6305c8c449b86c4366.zip"},{"id":105750515,"identity":"4bb335e3-95bc-457e-987c-1f8cd35ab86c","added_by":"auto","created_at":"2026-03-30 15:23:16","extension":"zip","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":12381051,"visible":true,"origin":"","legend":"","description":"","filename":"PSUMambaDualPathBidirectionalMambaforPlantStressMonitoringviaTemporalHyperspectralImaging.zip","url":"https://assets-eu.researchsquare.com/files/rs-9140549/v1/84cd1032071ed6f31d710e73.zip"}],"financialInterests":"No competing interests reported.","formattedTitle":"PSUMamba: Dual-Path Bidirectional Mamba for Plant Stress Monitoring via Temporal Hyperspectral Imaging","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":"biotic and abiotic stress, bidirectional scanning, dual-path fusion, Vision Mamba, selective state space, real-time classification","lastPublishedDoi":"10.21203/rs.3.rs-9140549/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9140549/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Temporal hyperspectral imaging enables non-destructive monitoring of agricultural stress through spectral signatures evolving across extended observation periods, yet processing high-dimensional spatial-spectral-temporal sequences remains computationally prohibitive for real-time deployment. Traditional machine learning methods sacrifice temporal information through dimensionality reduction, while hybrid deep learning architectures combining convolutional and recurrent networks suffer from optimization pathologies at component boundaries. We introduce PSUMamba, a dual-path bidirectional Mamba architecture that processes 204-band hyperspectral sequences across eight timepoints through linear-complexity state space models, achieving 95.05% accuracy with 99.00% AUC-ROC using 153,268 parameters. The architecture maintains perfect specificity (100%) with 93.67% sensitivity while out-performing Vision Transformer with 39-fold fewer parameters and 37.5% reduced training time. Separate spectral and temporal pathways with adaptive fusion enable specialized biochemical and physiological feature extraction without quadratic attention overhead. Ablation studies confirm temporal features dominate classification under experimental conditions, with dual-path fusion providing superior probabilistic calibration (97.35% AUC) over single-path variants. Statistical comparisons demonstrate significant improvements over PLS-DA (∆=12.07%, p=0.0001), 3D CNN (∆=15.48%, p=0.0042) and 1D CNN-LSTM (∆=33.77%, p \u003c 0.0001). The results establish PSUMamba as efficient alternatives to transformers for temporal hyperspectral classification in agricultural stress monitoring, with the dual-path framework providing a generalizable template for multimodal temporal problems requiring linear-complexity long-range dependency modeling.","manuscriptTitle":"PSUMamba: Dual-Path Bidirectional Mamba for Plant Stress Monitoring via Temporal Hyperspectral Imaging","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-30 15:23:03","doi":"10.21203/rs.3.rs-9140549/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-11T07:34:58+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-03T18:08:07+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-15T15:52:03+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-09T07:02:37+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-07T02:29:37+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-06T14:56:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"232344563745524823190379448694401279944","date":"2026-03-31T16:19:38+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-31T03:16:44+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"23156604238523033498339395268470728463","date":"2026-03-30T17:19:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"292035154333628703434325591378091519904","date":"2026-03-30T17:01:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"199790574939236649598755969487175475221","date":"2026-03-29T12:54:17+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-29T07:22:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"156101366822071359462440952476378075037","date":"2026-03-29T07:15:26+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-27T05:44:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"113762639237563755307747405597139873996","date":"2026-03-26T22:57:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"62098894549797738476621933981272029788","date":"2026-03-26T21:00:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"324282953271666330320478638633033408390","date":"2026-03-26T20:24:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"42390150741942076051381568036758252111","date":"2026-03-26T18:26:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"295522181325162596812709056851461543351","date":"2026-03-26T16:23:58+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-26T16:09:20+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-03-24T06:12:52+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-20T03:39:43+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-20T03:39:17+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-03-16T16:53:13+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":"6378cead-ce5a-482c-a51f-9b4365034f26","owner":[],"postedDate":"March 30th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-11T07:34:58+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-03T18:08:07+00:00","index":94,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[{"id":65339764,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":65339765,"name":"Physical sciences/Engineering"},{"id":65339766,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-05-11T07:43:24+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-30 15:23:03","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9140549","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9140549","identity":"rs-9140549","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}