Hybrid machine learning approaches outperform mechanistic models of bloom timing in Eastern Redbud, Cercis canadensis

Hybrid machine learning approaches outperform mechanistic models of bloom timing in Eastern Redbud, Cercis canadensis | 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 Hybrid machine learning approaches outperform mechanistic models of bloom timing in Eastern Redbud, Cercis canadensis Tariq TSS Mohammad, Robert P Guralnick, Jorge AS Santiago-Blay, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7943611/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 06 May, 2026 Read the published version in International Journal of Biometeorology → Version 1 posted 4 You are reading this latest preprint version Abstract Predicting the timing of flowering has utility both in climate change planning and practical applications. Eastern Redbud ( Cercis canadensis ), a charismatic spring-flowering tree found predominantly in the eastern USA, has long captured public attention, yet robust models of its bloom timing are lacking. Here, we aim to understand flowering onset dynamics of C. canadensis , a challenge given potential for local adaptation and plasticity across its range. We utilized a hybrid phenology modeling framework that integrates a mechanistic chill–heat framework with a machine-learning correction layer. We expected that this integrative model would better capture non-linear dynamics in flowering onset across its range. Using observations of bloom onset maintained by the USA National Phenology Network collected across the tree’s range, we parameterized a process-based model incorporating chilling, forcing, and photoperiod cues, adjusted for latitude. This model predicted bloom dates with a mean absolute error of 7.3 days. Incorporating a machine-learning correction layer yielded a cross-validated mean error of 6.1 days, with improved representation of local anomalies and interannual variability. Out-of-sample validation using observations from herbarium and iNaturalist indicated the hybrid model retained predictive skill across contemporary and historical contexts. Our results also revealed that trees at higher latitudes require greater chilling and less forcing to flower than southern individuals. These results highlight the value of hybrid approaches that combine known extrinsic drivers linked to physiology with more flexible machine learning approaches, providing improved species-wide generalization. These analyses showcase both integrative modeling and integrative validation approaches to advance phenological forecasting. Cercis canadensis Eastern redbud machine learning phenological model Full Text Cite Share Download PDF Status: Published Journal Publication published 06 May, 2026 Read the published version in International Journal of Biometeorology → Version 1 posted Reviewers agreed at journal 19 Dec, 2025 Reviewers invited by journal 10 Nov, 2025 Editor assigned by journal 02 Nov, 2025 First submitted to journal 01 Nov, 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-7943611","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":543004001,"identity":"88379b75-cca3-4772-902f-4f65d3713fe1","order_by":0,"name":"Tariq TSS Mohammad","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBUlEQVRIiWNgGAWjYBCDBDDJU8HAwAYVYWzAoZQHVcsZkrXwtiFkcGqxZz/78MHbHJs8/mmnEx+8nWeXz8d/+NiDHww2shsO4LCFJ93YcO62tGKJ27mbgYxkyzaGY+mGPQxpxji1MKSxSfNuO5zYcDt3G5DBbMDG2GMmwcNwOBGnFv5n7L9BWubfzt3+m3dOvQEbM4+Z5B+G/7i1SKSxMYO0bADawszbcNiAjY3HTJqH4QBuLTeeMUsC/ZK4EegXyTnHjhuw8bClScsYJBvPxKGFvT+N8cPbbTaJ827nbvzwpqbaQL7/8DHJNxV2sn04tEDDAAMY4FGOQ8soGAWjYBSMAgQAAEmmWx2irOnjAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0009-1410-2482","institution":"The University of Arizona","correspondingAuthor":true,"prefix":"","firstName":"Tariq","middleName":"TSS","lastName":"Mohammad","suffix":""},{"id":543004002,"identity":"bb1924da-dd2f-4145-b191-5e196b3ab93b","order_by":1,"name":"Robert P Guralnick","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Robert","middleName":"P","lastName":"Guralnick","suffix":""},{"id":543004003,"identity":"410bd570-e362-40ae-99c9-1096dc18a5f9","order_by":2,"name":"Jorge AS Santiago-Blay","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Jorge","middleName":"AS","lastName":"Santiago-Blay","suffix":""},{"id":543004004,"identity":"69c37909-f642-44fc-a55f-d13aa727af98","order_by":3,"name":"Theresa M Crimmins","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Theresa","middleName":"M","lastName":"Crimmins","suffix":""}],"badges":[],"createdAt":"2025-10-26 18:00:44","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7943611/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7943611/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00484-026-03197-2","type":"published","date":"2026-05-07T00:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":96415211,"identity":"f983b2c6-9e03-42b8-ab8c-59494d7c6dbf","added_by":"auto","created_at":"2025-11-20 20:35:52","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7492,"visible":true,"origin":"","legend":"","description":"","filename":"ijbmIJBMD2500725.xml","url":"https://assets-eu.researchsquare.com/files/rs-7943611/v1/a1262deccad28c91c1134b8d.xml"},{"id":96454847,"identity":"6132555e-9320-4fa4-b964-03c18334e6ec","added_by":"auto","created_at":"2025-11-21 10:03:11","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":951,"visible":true,"origin":"","legend":"","description":"","filename":"IJBMD25007256288.go.xml","url":"https://assets-eu.researchsquare.com/files/rs-7943611/v1/1fb27529f856b827b032bc27.xml"},{"id":96415198,"identity":"dbb56ca2-32ce-4229-88fa-228eddb5497f","added_by":"auto","created_at":"2025-11-20 20:35:52","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":917,"visible":true,"origin":"","legend":"","description":"","filename":"IJBMD2500725Import.xml","url":"https://assets-eu.researchsquare.com/files/rs-7943611/v1/bce24d74cf94e666facb8dfc.xml"},{"id":96454943,"identity":"03812c82-572e-41bf-ace2-f0a5066f26c1","added_by":"auto","created_at":"2025-11-21 10:03:20","extension":"xml","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":182273,"visible":true,"origin":"","legend":"","description":"","filename":"IJBMD25007250enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7943611/v1/0da12ba4265c7e049e69029b.xml"},{"id":96415209,"identity":"bff54e3e-5f4d-46a6-9dce-a25f0e3eaade","added_by":"auto","created_at":"2025-11-20 20:35:52","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":73621,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7943611/v1/a56045668ea6bfc40a4e727a.jpeg"},{"id":96415194,"identity":"6d1106a5-1693-4790-baf9-71cb562d64e8","added_by":"auto","created_at":"2025-11-20 20:35:52","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":227444,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7943611/v1/5e028ce99bca10af077654cf.png"},{"id":96415205,"identity":"6cbd9d84-e7a7-4505-9a29-db9491581d12","added_by":"auto","created_at":"2025-11-20 20:35:52","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":195681,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7943611/v1/c77a7d1169a9b897cbd91fc1.png"},{"id":96415196,"identity":"c4e8eed6-3055-4a33-8d97-cb409a389c11","added_by":"auto","created_at":"2025-11-20 20:35:52","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":219057,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7943611/v1/983b932ee00fdeaec7fb53cb.png"},{"id":96415207,"identity":"2c8d11df-9dba-4849-9701-715602060aaf","added_by":"auto","created_at":"2025-11-20 20:35:52","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55134,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7943611/v1/ea4d5b5620489bc11496e2ca.png"},{"id":96415203,"identity":"6e2b34e0-fc05-4218-bd51-8b79d9e07aa0","added_by":"auto","created_at":"2025-11-20 20:35:52","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":72702,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7943611/v1/22a59c751a43eb90fdfe3c5a.png"},{"id":96453671,"identity":"a0712158-180e-46d4-bda5-b172f57a0c2a","added_by":"auto","created_at":"2025-11-21 10:01:14","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":61367,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7943611/v1/6bfe57da8f0113241197717e.png"},{"id":96415201,"identity":"16909671-ecad-42f1-9614-3393e7bc3835","added_by":"auto","created_at":"2025-11-20 20:35:52","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":44698,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7943611/v1/18342fa865ab1dbcf8bc711c.png"},{"id":96454313,"identity":"f42746e5-ea7b-45c6-a2bb-7e5839021e5e","added_by":"auto","created_at":"2025-11-21 10:02:36","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":51870,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7943611/v1/ac83604f884924e85b9a596e.png"},{"id":96454906,"identity":"0bbf75b6-7a3a-4b00-97fb-536d8d9125b7","added_by":"auto","created_at":"2025-11-21 10:03:17","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":25667,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7943611/v1/076c5611447a88e5029ee351.png"},{"id":96415210,"identity":"f012a370-a4b6-4179-ad07-4c5e8ced5371","added_by":"auto","created_at":"2025-11-20 20:35:52","extension":"xml","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":182938,"visible":true,"origin":"","legend":"","description":"","filename":"IJBMD25007250structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7943611/v1/827d87ca884941a03b571661.xml"},{"id":96454882,"identity":"ce6e85ca-b004-4a56-b025-f1a4ebdc5a0f","added_by":"auto","created_at":"2025-11-21 10:03:14","extension":"html","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":192767,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7943611/v1/de454b9855b042097f15d5a3.html"},{"id":109025720,"identity":"a9550ca6-3028-4769-ab75-12afa3d10978","added_by":"auto","created_at":"2026-05-11 20:55:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":637095,"visible":true,"origin":"","legend":"","description":"","filename":"Mohammadetalredbudflowermodel.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7943611/v1_covered_6b4f3790-efdd-4782-8990-6dac365b4ebc.pdf"}],"financialInterests":"","formattedTitle":"Hybrid machine learning approaches outperform mechanistic models of bloom timing in Eastern Redbud, Cercis canadensis","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-biometeorology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ijbm","sideBox":"Learn more about [International Journal of Biometeorology](http://link.springer.com/journal/484)","snPcode":"484","submissionUrl":"https://www.editorialmanager.com/ijbm/default2.aspx","title":"International Journal of Biometeorology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Cercis canadensis, Eastern redbud, machine learning, phenological model","lastPublishedDoi":"10.21203/rs.3.rs-7943611/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7943611/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003ePredicting the timing of flowering has utility both in climate change planning and practical applications. Eastern Redbud (\u003cem\u003eCercis canadensis\u003c/em\u003e), a charismatic spring-flowering tree found predominantly in the eastern USA, has long captured public attention, yet robust models of its bloom timing are lacking. Here, we aim to understand flowering onset dynamics of \u003cem\u003eC. canadensis\u003c/em\u003e, a challenge given potential for local adaptation and plasticity across its range. We utilized a hybrid phenology modeling framework that integrates a mechanistic chill\u0026ndash;heat framework with a machine-learning correction layer. We expected that this integrative model would better capture non-linear dynamics in flowering onset across its range. Using observations of bloom onset maintained by the USA National Phenology Network collected across the tree\u0026rsquo;s range, we parameterized a process-based model incorporating chilling, forcing, and photoperiod cues, adjusted for latitude. This model predicted bloom dates with a mean absolute error of 7.3 days. Incorporating a machine-learning correction layer yielded a cross-validated mean error of 6.1 days, with improved representation of local anomalies and interannual variability. Out-of-sample validation using observations from herbarium and iNaturalist indicated the hybrid model retained predictive skill across contemporary and historical contexts. Our results also revealed that trees at higher latitudes require greater chilling and less forcing to flower than southern individuals. These results highlight the value of hybrid approaches that combine known extrinsic drivers linked to physiology with more flexible machine learning approaches, providing improved species-wide generalization. These analyses showcase both integrative modeling and integrative validation approaches to advance phenological forecasting.\u003c/p\u003e","manuscriptTitle":"Hybrid machine learning approaches outperform mechanistic models of bloom timing in Eastern Redbud, Cercis canadensis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-20 20:35:47","doi":"10.21203/rs.3.rs-7943611/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"","date":"2025-12-19T06:59:33+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-11-11T02:12:35+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-11-03T01:02:39+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Biometeorology","date":"2025-11-01T23:55:17+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-biometeorology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ijbm","sideBox":"Learn more about [International Journal of Biometeorology](http://link.springer.com/journal/484)","snPcode":"484","submissionUrl":"https://www.editorialmanager.com/ijbm/default2.aspx","title":"International Journal of Biometeorology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"3b01573a-3288-458c-b4cc-2a81af3718ae","owner":[],"postedDate":"November 20th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-05-11T20:55:38+00:00","versionOfRecord":{"articleIdentity":"rs-7943611","link":"https://doi.org/10.1007/s00484-026-03197-2","journal":{"identity":"international-journal-of-biometeorology","isVorOnly":false,"title":"International Journal of Biometeorology"},"publishedOn":"2026-05-07 00:00:00","publishedOnDateReadable":"May 7th, 2026"},"versionCreatedAt":"2025-11-20 20:35:47","video":"","vorDoi":"10.1007/s00484-026-03197-2","vorDoiUrl":"https://doi.org/10.1007/s00484-026-03197-2","workflowStages":[]},"version":"v1","identity":"rs-7943611","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7943611","identity":"rs-7943611","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}