Distilling Hydrological and Land Surface Model Parameters from Physio-Geographical Properties Using Text-Generating AI

Distilling Hydrological and Land Surface Model Parameters from Physio-Geographical Properties Using Text-Generating AI | 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 Distilling Hydrological and Land Surface Model Parameters from Physio-Geographical Properties Using Text-Generating AI Moritz Feigl, Mathew Herrnegger, Karsten Schulz This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7183457/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 13 Feb, 2026 Read the published version in Nature Water → Version 1 posted You are reading this latest preprint version Abstract The estimation of parameters for distributed hydrological and land-surface models is inherently difficult, particularly in data-scarce regions. We present a novel approach that employs variational autoencoders (VAEs) that have been trained as text-generating models to automatically generate optimal, interpretable parameter transfer functions. This AI-driven methodology transforms equation discovery into continuous latent-space optimization, thereby improving the interpretability of the model and the efficiency of the process. When evaluating this method in a prediction-in-ungauged-basins setting with the mesoscale Hydrological Model (mHM) across 162 German basins, it showed significant improvements in runoff predictions compared to both traditional regionalization techniques and state-of-the-art regional Long Short-Term Memory (LSTM) networks. The generated transfer functions are robust, scalable, and physically interpretable, which is a substantial improvement in the field of large-scale process-based environmental modeling. Earth and environmental sciences/Hydrology Earth and environmental sciences/Climate sciences/Hydrology Physical sciences/Mathematics and computing/Software Land-Surface modeling parameter regionalization generative AI Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Published Journal Publication published 13 Feb, 2026 Read the published version in Nature Water → 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-7183457","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":497601440,"identity":"82577b07-b02a-4296-b8cf-bf7025601355","order_by":0,"name":"Moritz Feigl","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+klEQVRIie3RsUoDMRzH8d8RaJbIrf9bfAMhchAQTnyVc7mtILg4iBSE69Q6+xhuHVP+0FsyODr23iAuBeEQYy04Xe9GwXzhT5Z8SEKAWOyPZsOkEEjs+wx6HAkmmwlg/fxLBuiehJVPxpCz+aJl34FSKV/5clXk2orW477rJcY12loFyh7VDU9dZbSd5IRN/ynmrQpvITxoViVPay60hQEmQ0SDrr7JxZ7IHfA5REqQFtJyUnO4mDJI6iPEbWCdJSJWWC9clWesbul6mfeTphb+risofWra7ceqOF828xfvd6e95BCFUYe7hD9FOQR+kttx+2KxWOzf9QUjs1c304JDmwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-3545-864X","institution":"BOKU University Vienna","correspondingAuthor":true,"prefix":"","firstName":"Moritz","middleName":"","lastName":"Feigl","suffix":""},{"id":497601441,"identity":"1dfe5b50-dd70-417f-a916-d9b746a4198f","order_by":1,"name":"Mathew Herrnegger","email":"","orcid":"https://orcid.org/0000-0002-5388-2831","institution":"BOKU University Vienna,","correspondingAuthor":false,"prefix":"","firstName":"Mathew","middleName":"","lastName":"Herrnegger","suffix":""},{"id":497601442,"identity":"d8f13d75-04da-4ff6-88b3-343ec86c1b0e","order_by":2,"name":"Karsten Schulz","email":"","orcid":"","institution":"BOKU University Vienna","correspondingAuthor":false,"prefix":"","firstName":"Karsten","middleName":"","lastName":"Schulz","suffix":""}],"badges":[],"createdAt":"2025-07-22 06:50:57","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7183457/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7183457/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s44221-026-00583-3","type":"published","date":"2026-02-13T05:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":102654804,"identity":"13a544cc-5cb5-4c18-ae91-7caa9c9c7bfa","added_by":"auto","created_at":"2026-02-14 08:10:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2994084,"visible":true,"origin":"","legend":"Article File","description":"","filename":"feigletalnaturewater22Jul2025.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7183457/v1_covered_f1eb0769-de7f-4a66-98bb-a12e63769c2c.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Distilling Hydrological and Land Surface Model Parameters from Physio-Geographical Properties Using Text-Generating AI","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Land-Surface modeling, parameter regionalization, generative AI","lastPublishedDoi":"10.21203/rs.3.rs-7183457/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7183457/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The estimation of parameters for distributed hydrological and land-surface models is inherently difficult, particularly in data-scarce regions. We present a novel approach that employs variational autoencoders (VAEs) that have been trained as text-generating models to automatically generate optimal, interpretable parameter transfer functions. This AI-driven methodology transforms equation discovery into continuous latent-space optimization, thereby improving the interpretability of the model and the efficiency of the process. \r\nWhen evaluating this method in a prediction-in-ungauged-basins setting with the mesoscale Hydrological Model (mHM) across 162 German basins, it showed significant improvements in runoff predictions compared to both traditional regionalization techniques and state-of-the-art regional Long Short-Term Memory (LSTM) networks. The generated transfer functions are robust, scalable, and physically interpretable, which is a substantial improvement in the field of large-scale process-based environmental modeling.","manuscriptTitle":"Distilling Hydrological and Land Surface Model Parameters from Physio-Geographical Properties Using Text-Generating AI","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-11 04:45:00","doi":"10.21203/rs.3.rs-7183457/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-water","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"natwater","sideBox":"Learn more about [Nature Water](https://www.nature.com/natwater/)","snPcode":"44221","submissionUrl":"https://mts-natwater.nature.com/cgi-bin/main.plex","title":"Nature Water","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Research","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"3c491239-b05d-46a7-86e6-5adb48cb9ec2","owner":[],"postedDate":"August 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":52862012,"name":"Earth and environmental sciences/Hydrology"},{"id":52862013,"name":"Earth and environmental sciences/Climate sciences/Hydrology"},{"id":52862014,"name":"Physical sciences/Mathematics and computing/Software"}],"tags":[],"updatedAt":"2026-02-14T08:10:15+00:00","versionOfRecord":{"articleIdentity":"rs-7183457","link":"https://doi.org/10.1038/s44221-026-00583-3","journal":{"identity":"nature-water","isVorOnly":false,"title":"Nature Water"},"publishedOn":"2026-02-13 05:00:00","publishedOnDateReadable":"February 13th, 2026"},"versionCreatedAt":"2025-08-11 04:45:00","video":"","vorDoi":"10.1038/s44221-026-00583-3","vorDoiUrl":"https://doi.org/10.1038/s44221-026-00583-3","workflowStages":[]},"version":"v1","identity":"rs-7183457","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7183457","identity":"rs-7183457","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}