Lightweight Deep Learning for Agricultural Loss Forecasting: GRU with Transfer Learning and Edge Deployment

Lightweight Deep Learning for Agricultural Loss Forecasting: GRU with Transfer Learning and Edge Deployment | 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 Lightweight Deep Learning for Agricultural Loss Forecasting: GRU with Transfer Learning and Edge Deployment IDOWU OLUGBENGA ADEWUMI, Victoria Bola Oyekunle This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7370153/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 Precise forecasting of post-harvest deterioration in perishable crops like cassava is essential for minimizing food waste, enhancing supply chain effectiveness, and aiding decision-making in agricultural systems. This study introduces an efficient, interpretable forecasting system founded on Gated Recurrent Units (GRUs), designed for implementation in low-resource settings defined by scarce data, operational noise, and restricted computational power. The suggested method identifies short- to medium-term time dependencies in multivariate sensor data and integrates interpretability techniques such as SHAP, saliency maps, and LIME to deliver feature attribution throughout time steps. A two-phase transfer learning approach is used to improve generalization from high-resource to low-resource settings, tackling data shortages in smallholder agricultural situations. Experimental assessments juxtapose the GRU with conventional (ARIMA, XGBoost), recurrent (LSTM, BiLSTM), and transformer-based (Temporal Fusion Transformer, Informer) benchmarks, where the GRU records the minimum MAE (4.26%), RMSE (7.88%), and the maximum R 2 (0.884). On-device benchmarking validates real-time capability, achieving sub-10 ms latency on Raspberry Pi 4, under 100 ms latency on ESP32, and a model size below 512 KB post-quantization. The findings show that the suggested GRU provides an efficient balance among predictive accuracy, interpretability, and computational efficiency, facilitating practical field application for forecasting post-harvest losses in resource-limited agricultural settings. Artificial Intelligence and Machine Learning Agricultural Engineering Agronomy Agricultural Economics & Policy Time-Series Forecasting Gated Recurrent Units (GRU) Model Interpretability Edge AI Transfer Learning SHAP Domain Adaptation Lightweight Deep Learning Temporal Transformers 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-7370153","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":500308116,"identity":"147e91e2-2c91-4fe8-8570-a358831733b1","order_by":0,"name":"IDOWU OLUGBENGA ADEWUMI","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4klEQVRIie2PsQrCMBRFI4F0eegaQeIvVAIi6MdUCp1SXDuIixA3v8XJWSjWJR+QURA6OBUK4qQmTk5t3ARzCCGBe3jvIuTx/CSRPTMgGB/Mjw5clYR1AxlZBdwUhHLOQIX21a70NnFBzxmeSyrqq15OAAX5cdekUFXGYaSIUdL9VBRmMUgS3ThGi9F5LuGtcEGMQmHcqAz1ojqYvF2s5OLhoIRadMyUkBNQ+JJKB2WkSm66RIwEcozTLQXS1oWd4rJ/z54wXONLLW4r1gvyorn+B4S+b9e4BVffpD0ej+d/eAGHUkb7sOtaHwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-7005-3306","institution":"Software Engineering Program, Department of Computer and Information Engineering, Faculty of Natural and Applied Science, Lead City University, Ibadan, Nigeria.","correspondingAuthor":true,"prefix":"","firstName":"IDOWU","middleName":"OLUGBENGA","lastName":"ADEWUMI","suffix":""},{"id":500308117,"identity":"6590fe0f-2d70-4fb1-a7a7-34856c692fb3","order_by":1,"name":"Victoria Bola Oyekunle","email":"","orcid":"","institution":"Department of Computer and Information Engineering, Faculty of Natural and Applied Science, Lead City University, Ibadan, Nigeria","correspondingAuthor":false,"prefix":"","firstName":"Victoria","middleName":"Bola","lastName":"Oyekunle","suffix":""}],"badges":[],"createdAt":"2025-08-14 05:53:45","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-7370153/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7370153/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":89263244,"identity":"f67765ce-43e6-4bc6-8408-39c53229d752","added_by":"auto","created_at":"2025-08-18 07:29:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":613725,"visible":true,"origin":"","legend":"","description":"","filename":"newleveragegru.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7370153/v1_covered_bd8d0dcd-d023-4034-a431-60c2d954559e.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eLightweight Deep Learning for Agricultural Loss Forecasting: GRU with Transfer Learning and Edge Deployment\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"[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":"Time-Series Forecasting, Gated Recurrent Units (GRU), Model Interpretability, Edge AI, Transfer Learning, SHAP, Domain Adaptation, Lightweight Deep Learning, Temporal Transformers","lastPublishedDoi":"10.21203/rs.3.rs-7370153/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7370153/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003ePrecise forecasting of post-harvest deterioration in perishable crops like cassava is essential for minimizing food waste, enhancing supply chain effectiveness, and aiding decision-making in agricultural systems. This study introduces an efficient, interpretable forecasting system founded on Gated Recurrent Units (GRUs), designed for implementation in low-resource settings defined by scarce data, operational noise, and restricted computational power. The suggested method identifies short- to medium-term time dependencies in multivariate sensor data and integrates interpretability techniques such as SHAP, saliency maps, and LIME to deliver feature attribution throughout time steps. A two-phase transfer learning approach is used to improve generalization from high-resource to low-resource settings, tackling data shortages in smallholder agricultural situations. Experimental assessments juxtapose the GRU with conventional (ARIMA, XGBoost), recurrent (LSTM, BiLSTM), and transformer-based (Temporal Fusion Transformer, Informer) benchmarks, where the GRU records the minimum MAE (4.26%), RMSE (7.88%), and the maximum R\u003csup\u003e2\u003c/sup\u003e (0.884). On-device benchmarking validates real-time capability, achieving sub-10 ms latency on Raspberry Pi 4, under 100 ms latency on ESP32, and a model size below 512 KB post-quantization. The findings show that the suggested GRU provides an efficient balance among predictive accuracy, interpretability, and computational efficiency, facilitating practical field application for forecasting post-harvest losses in resource-limited agricultural settings.\u003c/p\u003e","manuscriptTitle":"Lightweight Deep Learning for Agricultural Loss Forecasting: GRU with Transfer Learning and Edge Deployment","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-18 07:05:52","doi":"10.21203/rs.3.rs-7370153/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":"6254ff2e-f4df-4f5c-85fe-7fae86909cd0","owner":[],"postedDate":"August 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":53145750,"name":"Artificial Intelligence and Machine Learning"},{"id":53145751,"name":"Agricultural Engineering"},{"id":53145752,"name":"Agronomy"},{"id":53145753,"name":"Agricultural Economics \u0026 Policy"}],"tags":[],"updatedAt":"2025-08-18T07:05:52+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-18 07:05:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7370153","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7370153","identity":"rs-7370153","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}