Adaptive hybrid potential evapotranspiration (PET) prediction method based on automatic machine learning

Adaptive hybrid potential evapotranspiration (PET) prediction method based on automatic machine learning | 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 Adaptive hybrid potential evapotranspiration (PET) prediction method based on automatic machine learning Zhang Chenjia, Xu Tianxin, Zhang Yan, Abdu Kaimu Abullimiti, Zhang Yutong, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5657062/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 In arid areas, estimation of crop water demand through potential evapotranspiration (PET) forecast has a guiding effect on water-saving irrigation, to cope with the crisis of water shortage. Neural network-based PET prediction methods is considered to have huge application potential because of its small prediction error. However, the physical conditions and data quality in different regions make the choice of neural network different, making it difficult to provide a general PET prediction method. So an adaptive hybrid model based on automatic machine learning for short-term PET prediction is proposed coupling neural network and PET formula. Process is divided into two stages: learning and forecasting. Learning stage includes three modules: meteorological data reconstructing, adaptive data set generation and adaptive hybrid model (PET calculation formula + neural network) selecting. Forecast stage includes two modules: adaptive data set generation and rolling prediction. 105 standard weather stations in Xinjiang were used as data sets (43 of them had missing data) to test model. According to modules, networks and PET formulas used in the prediction process, corresponding labels were generated in each dataset forecast result. Ratio of training set and test set for each data set was 8:2. Grid search was used to optimize the best hyperparameter combination. In test set, the average absolute error (MAE) and average squared error (MSE) of the model prediction were 0.338mm and 0.270, achieving high prediction accuracy. The mean prediction error is smaller to any single mixed model. We demonstrate that the neural network applicability varies among the used data sources, and Gate Recurrent Unit (GRU) and 1 Dimension convolutional neural network (1DCNN) are more suitable for the selected datasets, while Long Short Term Memory network (LSTM) and Multilayer Perceptron (MLP) are not applicable. Combined with the analysis of the labels, We find evidences that applicability of neural networks and PET formulas is independent of geographic region and degree of drought. In 2023, method of rolling prediction for 1-15 days is verified, and the verification results show that PET prediction error based on neural network is significantly smaller than useing weather forecast data to calculate PET. In addition, by comparison,we determined that adaptive input length can effectively reduce the prediction error, MAE was 27.52% smaller than fixed input length, and MSE was 45.76% smaller than fixed input length. The proposed method realized the automatic machine learning of PET forecast, can predict PET more accurately, and can be further expanded by adding neural networks and PET formulas to improve its generalization ability. Adaptive hybrid model Automated machine learning Grid search Neural network PET forecast Full Text Additional Declarations No competing interests reported. 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-5657062","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":392397476,"identity":"e7961e88-e4b9-4059-8747-7b3bd1496fa6","order_by":0,"name":"Zhang Chenjia","email":"","orcid":"","institution":"China Agricultural University","correspondingAuthor":false,"prefix":"","firstName":"Zhang","middleName":"","lastName":"Chenjia","suffix":""},{"id":392397478,"identity":"51737801-0745-406f-b22d-9b95f87613fd","order_by":1,"name":"Xu Tianxin","email":"","orcid":"","institution":"China Agricultural University","correspondingAuthor":false,"prefix":"","firstName":"Xu","middleName":"","lastName":"Tianxin","suffix":""},{"id":392397479,"identity":"8ecb3198-831e-4559-9484-5529f03e15df","order_by":2,"name":"Zhang Yan","email":"","orcid":"","institution":"Xichang University","correspondingAuthor":false,"prefix":"","firstName":"Zhang","middleName":"","lastName":"Yan","suffix":""},{"id":392397480,"identity":"49fb9ac3-a47e-46a8-8f39-1aed7566702e","order_by":3,"name":"Abdu Kaimu Abullimiti","email":"","orcid":"","institution":"Beijing Lianchuang Siyuan Measurement and Control Technology Co., Ltd. Beijing","correspondingAuthor":false,"prefix":"","firstName":"Abdu","middleName":"Kaimu","lastName":"Abullimiti","suffix":""},{"id":392397481,"identity":"64f25dab-e923-4d38-b4d7-61140357bc27","order_by":4,"name":"Zhang Yutong","email":"","orcid":"","institution":"China Agricultural University","correspondingAuthor":false,"prefix":"","firstName":"Zhang","middleName":"","lastName":"Yutong","suffix":""},{"id":392397482,"identity":"8df8f327-9768-4f35-a2be-ed867fd0a243","order_by":5,"name":"Guo Lirui","email":"","orcid":"","institution":"Yangzhou University","correspondingAuthor":false,"prefix":"","firstName":"Guo","middleName":"","lastName":"Lirui","suffix":""},{"id":392397483,"identity":"dafd9e0c-ef0c-463e-9df7-9398b95713cb","order_by":6,"name":"Ma Daokun","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAqElEQVRIiWNgGAWjYHACY4YPEIYB8VoYZ5CshZmHJC267Yc3G9vU2CU2sDdvk2CouUNYi9mZtOLknGPJiQ08x8okGI49I0LLgRzjw7kNzIkNEjlmEowNh4nQcv6N8WHLhvrEBvk3xGq5kWOcDFQJtIWHaC3Pig17jh03buNJK7ZIOEaUw5I3S/yoqZbtZz+88caHGiK0wAEbiEggQcMoGAWjYBSMAjwAAJLjN1MCfdp+AAAAAElFTkSuQmCC","orcid":"","institution":"China Agricultural University","correspondingAuthor":true,"prefix":"","firstName":"Ma","middleName":"","lastName":"Daokun","suffix":""}],"badges":[],"createdAt":"2024-12-17 00:08:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5657062/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5657062/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":72494523,"identity":"e5603c99-ca3d-4dad-9356-d17821d4ad1f","added_by":"auto","created_at":"2024-12-28 01:31:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1712685,"visible":true,"origin":"","legend":"","description":"","filename":"AdaptivehybridPETpredictionmethod.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5657062/v1_covered_739ecc68-e054-4557-8247-56846280d8e5.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Adaptive hybrid potential evapotranspiration (PET) prediction method based on automatic machine learning","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":"[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":"Adaptive hybrid model, Automated machine learning, Grid search, Neural network, PET forecast","lastPublishedDoi":"10.21203/rs.3.rs-5657062/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5657062/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn arid areas, estimation of crop water demand through potential evapotranspiration (PET) forecast has a guiding effect on water-saving irrigation, to cope with the crisis of water shortage. Neural network-based PET prediction methods is considered to have huge application potential because of its small prediction error. However, the physical conditions and data quality in different regions make the choice of neural network different, making it difficult to provide a general PET prediction method. So an adaptive hybrid model based on automatic machine learning for short-term PET prediction is proposed coupling neural network and PET formula. Process is divided into two stages: learning and forecasting. Learning stage includes three modules: meteorological data reconstructing, adaptive data set generation and adaptive hybrid model (PET calculation formula + neural network) selecting. Forecast stage includes two modules: adaptive data set generation and rolling prediction. 105 standard weather stations in Xinjiang were used as data sets (43 of them had missing data) to test model. According to modules, networks and PET formulas used in the prediction process, corresponding labels were generated in each dataset forecast result. Ratio of training set and test set for each data set was 8:2. Grid search was used to optimize the best hyperparameter combination. In test set, the average absolute error (MAE) and average squared error (MSE) of the model prediction were 0.338mm and 0.270, achieving high prediction accuracy. The mean prediction error is smaller to any single mixed model. We demonstrate that the neural network applicability varies among the used data sources, and Gate Recurrent Unit (GRU) and 1 Dimension convolutional neural network (1DCNN) are more suitable for the selected datasets, while Long Short Term Memory network (LSTM) and Multilayer Perceptron (MLP) are not applicable. Combined with the analysis of the labels, We find evidences that applicability of neural networks and PET formulas is independent of geographic region and degree of drought. In 2023, method of rolling prediction for 1-15 days is verified, and the verification results show that PET prediction error based on neural network is significantly smaller than useing weather forecast data to calculate PET. In addition, by comparison,we determined that adaptive input length can effectively reduce the prediction error, MAE was 27.52% smaller than fixed input length, and MSE was 45.76% smaller than fixed input length. The proposed method realized the automatic machine learning of PET forecast, can predict PET more accurately, and can be further expanded by adding neural networks and PET formulas to improve its generalization ability.\u003c/p\u003e","manuscriptTitle":"Adaptive hybrid potential evapotranspiration (PET) prediction method based on automatic machine learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-23 06:28:57","doi":"10.21203/rs.3.rs-5657062/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":"ac0f90a9-e662-40b9-b7de-99f127904753","owner":[],"postedDate":"December 23rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-12-28T01:23:14+00:00","versionOfRecord":[],"versionCreatedAt":"2024-12-23 06:28:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5657062","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5657062","identity":"rs-5657062","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}