Machine learning can improve the mapping of food consumption and diet quality

Machine learning can improve the mapping of food consumption and diet quality | 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 Machine learning can improve the mapping of food consumption and diet quality Thijs de Lange, Michiel van Dijk This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8618507/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Detailed spatial information on food consumption and diet quality is essential to develop effective policies for a successful transition towards sustainable and healthy diets. However, fine-scale maps of food consumption patterns are not frequently available. To address this, we used a machine learning framework in combination with household survey information and spatial variables to generate high-resolution maps (30 arcsec; ~1 km) for 25 different food groups. The models explain more than 50% of the variance in food consumption of ten distinct food groups, which account for 71.7% of total energy consumption (in kcal). We applied this approach to calculate an indicator showing the distance to the EAT-Lancet diet, the global reference for a healthy diet. This resulted in insightful high-resolution diet quality maps. Altogether, we demonstrate that machine learning models combined with household survey give insight into the complex interplay between food environment-related and individual-based motivational factors influence food consumption. Social science/Geography Social science/Science, technology and society Full Text Additional Declarations There is NO Competing Interest. Supplementary Files SupplementaryInformation.pdf Supplementary Information of Machine learning can improve the mapping of food consumption and diet quality Cite Share Download PDF Status: Under Review 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-8618507","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":585862378,"identity":"29240c3b-ad8a-4839-82d1-9798c14b5f08","order_by":0,"name":"Thijs de Lange","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5UlEQVRIiWNgGAWjYDACCcYGAwYGZgY+MK8CTDIewKeDB6aFDcw9AxEloAVMQbUwthGhxV66uaHwB4O1HBv72cMvPs47nLi9gfcAfltkDjYY8zCkG7Px5KVZztx2OHHOAb4EAg5LbDBmYDic2MaQY2bMu+124gwGHgOCWgx/MByub+N/Y2b8dw6RWgx4GA4nsEnkGD9mbCBGyw2gw3gM0g3bJN6YMfYc+288g5mAFvYZ6c8Mf1RYy/Pz5xh/+FGTJjuDvcfwAT4tQMBmwGAAYcDiiCBghpnJ/IGw4lEwCkbBKBiJAACwbkaZY9jcnwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0003-1599-7037","institution":"Wageningen Social \u0026 Economic Research, Wageningen University and Research (WUR)","correspondingAuthor":true,"prefix":"","firstName":"Thijs","middleName":"","lastName":"de Lange","suffix":""},{"id":585862379,"identity":"c63496aa-2dce-4f08-a1fa-de3b2d2e7ac1","order_by":1,"name":"Michiel van Dijk","email":"","orcid":"https://orcid.org/0000-0002-5207-7304","institution":"Wageningen Social \u0026 Economic Research","correspondingAuthor":false,"prefix":"","firstName":"Michiel","middleName":"van","lastName":"Dijk","suffix":""}],"badges":[],"createdAt":"2026-01-16 11:49:01","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8618507/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8618507/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108667998,"identity":"8463e2db-bcbe-43d7-bfd2-307a067293b2","added_by":"auto","created_at":"2026-05-07 06:57:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1085096,"visible":true,"origin":"","legend":"Article File","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8618507/v1_covered_4f339d22-2787-46fe-8dc0-8297e45db4ad.pdf"},{"id":108667854,"identity":"c43e3b09-4236-484c-9c10-25f00231967f","added_by":"auto","created_at":"2026-05-07 06:57:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":4050500,"visible":true,"origin":"","legend":"Supplementary Information of Machine learning can improve the mapping of food consumption and diet quality","description":"","filename":"SupplementaryInformation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8618507/v1/43ce009866051c9f9e3e27f3.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Machine learning can improve the mapping of food consumption and diet quality","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"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":"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":"","lastPublishedDoi":"10.21203/rs.3.rs-8618507/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8618507/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Detailed spatial information on food consumption and diet quality is essential to develop effective policies for a successful transition towards sustainable and healthy diets. However, fine-scale maps of food consumption patterns are not frequently available. To address this, we used a machine learning framework in combination with household survey information and spatial variables to generate high-resolution maps (30 arcsec; ~1 km) for 25 different food groups. The models explain more than 50% of the variance in food consumption of ten distinct food groups, which account for 71.7% of total energy consumption (in kcal). We applied this approach to calculate an indicator showing the distance to the EAT-Lancet diet, the global reference for a healthy diet. This resulted in insightful high-resolution diet quality maps. Altogether, we demonstrate that machine learning models combined with household survey give insight into the complex interplay between food environment-related and individual-based motivational factors influence food consumption.","manuscriptTitle":"Machine learning can improve the mapping of food consumption and diet quality","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-07 06:56:02","doi":"10.21203/rs.3.rs-8618507/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-food","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"natfood","sideBox":"Learn more about [Nature Food](http://www.nature.com/natfood/)","snPcode":"","submissionUrl":"","title":"Nature Food","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Research","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"5c5d99a9-8b98-410f-a08f-b7ca166d8981","owner":[],"postedDate":"May 7th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":62332459,"name":"Social science/Geography"},{"id":62332460,"name":"Social science/Science, technology and society"}],"tags":[],"updatedAt":"2026-05-07T06:56:02+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-07 06:56:02","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8618507","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8618507","identity":"rs-8618507","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}