{"paper_id":"45b5d689-c13f-4963-ab85-9a4b05f73fa4","body_text":"GraphCrossFormer A Graph-Enhanced Cross-Attention Transformer for Crop Yield 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 Research Article GraphCrossFormer A Graph-Enhanced Cross-Attention Transformer for Crop Yield Prediction Qiang Cai, Xiang Lei, YanZhao Ren, HaiSheng Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7336174/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 Accurate forecasting of agricultural yields is essential to ensuring global food security and developing effective climate change adaptation strategies. As global environmental changes make weather patterns increasingly unpredictable and shift agricultural zones, traditional forecasting models often fall short. These models struggle to capture the complex interplay between crop characteristics and dynamic environmental factors that impact yields. To address this, we introduce GraphCrossFormer—an advanced transformer-based architecture designed specifically to improve crop yield predictions. Its key innovations include: (1) A GraphFormer module that models feature dependencies through message-passing in fully connected graphs, and (2) A cross-attention mechanism that dynamically integrates scenario-level context like emission trajectories and adaptation strategies.Together, these components learn spatial, semantic, and contextual relationships within a unified, interpretable framework, significantly boosting prediction accuracy. This thesis utilizes a global dataset covering wheat, rice, corn and soybeans, and predicts their impacts on yields based on various meteorological data,and GraphCrossFormer consistently outperformed alternatives. It achieves improved prediction accuracy and reduced errors for different crop types and climate scenarios. Furthermore, interpretability analyses using attention-basedand gradient-based methods reveal the relative importance of critical climate variables and management factors. Ultimately, the proposed model offers an effective, powerful, and interpretable tool for reliable crop yield forecasts in the context of climate-resilient agricultural planning. Crop yield prediction meteorological parameters GraphFormer Cross-Attention mechanism Full Text 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-7336174\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":true,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":516905687,\"identity\":\"a557482c-1813-4d78-a28f-9fb7a2b89024\",\"order_by\":0,\"name\":\"Qiang Cai\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Qiang\",\"middleName\":\"\",\"lastName\":\"Cai\",\"suffix\":\"\"},{\"id\":516905688,\"identity\":\"8815bfbf-c990-43e8-80ee-c72fce6fc163\",\"order_by\":1,\"name\":\"Xiang Lei\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5ElEQVRIie3PsWrCUBTG8XO5cKZDdTwBia9winDp1ldJEOKi4JhBrOFKMxRx9TEcHQ2BTHF3jOQF7NbBodK1kqRbh/ubvz+cA+A4/xAO66y+CfvKqqQK4kV78gTRWGj+MtKpzqUqi/bEh6np0zUO0y1G3mWtOxwGRQQsrDaWTByuEHrpR9CcKFtUIqy9e3IODwPg8rRvTjROJBDG55+kRBCetSRIho/C9JqTmYfvukNCZLyVMCuLEXRLGMej+0yU1TkHZUGtvwx3OqvhtnxLtlny+RUv/F66aU5+ob/NHcdxnIe+AUmSQsaRv5GJAAAAAElFTkSuQmCC\",\"orcid\":\"https://orcid.org/0009-0000-9172-8707\",\"institution\":\"Beijing Technology and Business University\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Xiang\",\"middleName\":\"\",\"lastName\":\"Lei\",\"suffix\":\"\"},{\"id\":516905689,\"identity\":\"9ad92910-b7b6-4200-941b-8193677ed2b6\",\"order_by\":2,\"name\":\"YanZhao Ren\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"YanZhao\",\"middleName\":\"\",\"lastName\":\"Ren\",\"suffix\":\"\"},{\"id\":516905690,\"identity\":\"a419ec48-fc70-4463-a9b0-ec33f6588b77\",\"order_by\":3,\"name\":\"HaiSheng Li\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"HaiSheng\",\"middleName\":\"\",\"lastName\":\"Li\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2025-08-10 00:13:12\",\"currentVersionCode\":1,\"declarations\":\"\",\"doi\":\"10.21203/rs.3.rs-7336174/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-7336174/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":92383689,\"identity\":\"6df5da79-86b1-42b3-a2c2-d2477d5bec46\",\"added_by\":\"auto\",\"created_at\":\"2025-09-29 06:45:54\",\"extension\":\"xml\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":6147,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"ijbmIJBMD2500538.xml\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7336174/v1/7c5ad797cd6809a2b9ec9b23.xml\"},{\"id\":92383690,\"identity\":\"a9857b9e-3142-42da-9e36-fac441ee264a\",\"added_by\":\"auto\",\"created_at\":\"2025-09-29 06:45:54\",\"extension\":\"xml\",\"order_by\":2,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":958,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"IJBMD25005385772.go.xml\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7336174/v1/d6b0db47bca517afa1b919fe.xml\"},{\"id\":92384521,\"identity\":\"2b36cd8f-705a-4f2e-b815-7495aa652ed3\",\"added_by\":\"auto\",\"created_at\":\"2025-09-29 06:53:54\",\"extension\":\"xml\",\"order_by\":3,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":887,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"IJBMD2500538Import.xml\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7336174/v1/0e05f009943e361e2d9bea28.xml\"},{\"id\":92384517,\"identity\":\"10b03da8-cebf-4484-af9b-a34d063174ae\",\"added_by\":\"auto\",\"created_at\":\"2025-09-29 06:53:54\",\"extension\":\"xml\",\"order_by\":4,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":105481,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"IJBMD25005380enriched.xml\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7336174/v1/85f653ac948262f4ff387fcd.xml\"},{\"id\":92384730,\"identity\":\"52338252-766e-419f-836b-81ca5c06546b\",\"added_by\":\"auto\",\"created_at\":\"2025-09-29 07:01:54\",\"extension\":\"png\",\"order_by\":5,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":184494,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage1.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7336174/v1/c806b4db8785e20584bb5289.png\"},{\"id\":92384516,\"identity\":\"8e2814c6-01fb-4e7a-b264-65da48104a13\",\"added_by\":\"auto\",\"created_at\":\"2025-09-29 06:53:54\",\"extension\":\"png\",\"order_by\":6,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":52582,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage2.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7336174/v1/d97be4bacb5354dc25b28682.png\"},{\"id\":92383693,\"identity\":\"539c7d45-3042-4ef9-949d-f3ef59cd4bf1\",\"added_by\":\"auto\",\"created_at\":\"2025-09-29 06:45:54\",\"extension\":\"png\",\"order_by\":7,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":43281,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage3.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7336174/v1/714ade5ddacb547914a8fe48.png\"},{\"id\":92384515,\"identity\":\"570b3975-7dd8-4717-bdac-452619237016\",\"added_by\":\"auto\",\"created_at\":\"2025-09-29 06:53:54\",\"extension\":\"png\",\"order_by\":8,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":78453,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage4.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7336174/v1/5ca84dd157c052c4ff1f57d2.png\"},{\"id\":92383698,\"identity\":\"af694412-0ff7-441b-a3e1-694c67c299e2\",\"added_by\":\"auto\",\"created_at\":\"2025-09-29 06:45:54\",\"extension\":\"png\",\"order_by\":9,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":76391,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"floatimage5.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7336174/v1/8aceed5cc3dd206652a23b61.png\"},{\"id\":92383700,\"identity\":\"76edf38f-cd33-4727-9f7a-10e888ee5b6c\",\"added_by\":\"auto\",\"created_at\":\"2025-09-29 06:45:54\",\"extension\":\"png\",\"order_by\":10,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":51658,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage1.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7336174/v1/0728eece02c15d6d419e0ff7.png\"},{\"id\":92384731,\"identity\":\"a26e7bfc-29fa-4a15-bc73-93e6d7a4198e\",\"added_by\":\"auto\",\"created_at\":\"2025-09-29 07:01:55\",\"extension\":\"png\",\"order_by\":11,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":12398,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage2.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7336174/v1/2bed0da214648866c7cd7005.png\"},{\"id\":92383696,\"identity\":\"8a5a2bf9-9e2d-453b-84d1-b7c282a19ec7\",\"added_by\":\"auto\",\"created_at\":\"2025-09-29 06:45:54\",\"extension\":\"png\",\"order_by\":12,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":14525,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage3.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7336174/v1/7a279632507f5093f2795111.png\"},{\"id\":92384518,\"identity\":\"105c8491-16b8-4b8f-8630-c51fe7800697\",\"added_by\":\"auto\",\"created_at\":\"2025-09-29 06:53:54\",\"extension\":\"png\",\"order_by\":13,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":19853,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage4.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7336174/v1/267b35e2580e06a4038b825d.png\"},{\"id\":92384523,\"identity\":\"b1a01b75-d9b6-4731-897f-e9a718f4d73f\",\"added_by\":\"auto\",\"created_at\":\"2025-09-29 06:53:55\",\"extension\":\"png\",\"order_by\":14,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":22072,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"Onlinefloatimage5.png\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7336174/v1/e2d5f424660a50f9272b142a.png\"},{\"id\":92383702,\"identity\":\"8a6b6f11-1f50-4239-a9ae-0c7f4f10bad5\",\"added_by\":\"auto\",\"created_at\":\"2025-09-29 06:45:54\",\"extension\":\"xml\",\"order_by\":15,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":105002,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"IJBMD25005380structuring.xml\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7336174/v1/7b5d00e2650ca3e8ae179d01.xml\"},{\"id\":92383704,\"identity\":\"1bb2736f-4690-4ef9-a53d-25ced1cac124\",\"added_by\":\"auto\",\"created_at\":\"2025-09-29 06:45:55\",\"extension\":\"html\",\"order_by\":16,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"acdc-reference\",\"size\":115589,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"earlyproof.html\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7336174/v1/217c2e518a2b9184048f6a9c.html\"},{\"id\":93624868,\"identity\":\"0b604170-12cd-4043-8bab-58de58f13b84\",\"added_by\":\"auto\",\"created_at\":\"2025-10-15 19:00:01\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":662440,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"GraphCrossFormerforCropYieldPrediction.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7336174/v1_covered_0d274d7b-99e8-4d8f-901c-9f74942522d2.pdf\"}],\"financialInterests\":\"\",\"formattedTitle\":\"GraphCrossFormer A Graph-Enhanced Cross-Attention Transformer for Crop Yield Prediction\",\"fulltext\":[],\"fulltextSource\":\"\",\"fullText\":\"\",\"funders\":[],\"hasAdminPriorityOnWorkflow\":false,\"hasManuscriptDocX\":false,\"hasOptedInToPreprint\":true,\"hasPassedJournalQc\":\"\",\"hasAnyPriority\":false,\"hideJournal\":true,\"highlight\":\"\",\"institution\":\"\",\"isAcceptedByJournal\":false,\"isAuthorSuppliedPdf\":true,\"isDeskRejected\":\"\",\"isHiddenFromSearch\":false,\"isInQc\":false,\"isInWorkflow\":false,\"isPdf\":true,\"isPdfUpToDate\":true,\"isWithdrawnOrRetracted\":false,\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"Crop yield prediction, meteorological parameters, GraphFormer, Cross-Attention mechanism\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-7336174/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-7336174/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"\\u003cp\\u003eAccurate forecasting of agricultural yields is essential to ensuring global food security and developing effective climate change adaptation strategies. As global environmental changes make weather patterns increasingly unpredictable and shift agricultural zones, traditional forecasting models often fall short. These models struggle to capture the complex interplay between crop characteristics and dynamic environmental factors that impact yields. To address this, we introduce GraphCrossFormer\\u0026mdash;an advanced transformer-based architecture designed specifically to improve crop yield predictions. Its key innovations include: (1) A GraphFormer module that models feature dependencies through message-passing in fully connected graphs, and (2) A cross-attention mechanism that dynamically integrates scenario-level context like emission trajectories and adaptation strategies.Together, these components learn spatial, semantic, and contextual relationships within a unified, interpretable framework, significantly boosting prediction accuracy. This thesis utilizes a global dataset covering wheat, rice, corn and soybeans, and predicts their impacts on yields based on various meteorological data,and GraphCrossFormer consistently outperformed alternatives. It achieves improved prediction accuracy and reduced errors for different crop types and climate scenarios. Furthermore, interpretability analyses using attention-basedand gradient-based methods reveal the relative importance of critical climate variables and management factors. Ultimately, the proposed model offers an effective, powerful, and interpretable tool for reliable crop yield forecasts in the context of climate-resilient agricultural planning.\\u003c/p\\u003e\",\"manuscriptTitle\":\"GraphCrossFormer A Graph-Enhanced Cross-Attention Transformer for Crop Yield Prediction\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2025-09-29 06:45:50\",\"doi\":\"10.21203/rs.3.rs-7336174/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"dad344ee-571b-46f5-a673-094ac7e6b525\",\"owner\":[],\"postedDate\":\"September 29th, 2025\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"posted\",\"subjectAreas\":[],\"tags\":[],\"updatedAt\":\"2025-10-15T18:51:51+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2025-09-29 06:45:50\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-7336174\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-7336174\",\"identity\":\"rs-7336174\",\"version\":[\"v1\"]},\"buildId\":\"8U1c8b4HqxoKbykW_rLl7\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}