A Geospatial Approach to Measuring Economic Activity

A Geospatial Approach to Measuring Economic Activity | 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 Social Sciences - Article A Geospatial Approach to Measuring Economic Activity Anton Yang, Jianwei Ai, Costas Arkolakis This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8051642/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 We introduce a new methodology to detect and measure economic activity using geospatial data and apply it to steel production, a major industrial pollution source worldwide. Combining plant output data with geospatial data, such as ambient air pollutants, nighttime lights, and temperature, we train machine learning models to predict plant locations and output. We identify about 40% (70%) of plants missing from the training sample within a 1 km (5 km) radius and achieve R^2 above 0.8 for output prediction at a 1 km grid and at the plant level, as well as for both regional and time series validations. We apply the model trained on Chinese steel data to North Korea and use it to identify steel locations and output absent from official statistics but consistent with independent open-source and defector-based reports. Our approach can be adapted to other industries and regions, and used by policymakers and researchers to track and measure industrial activity in near real time. Scientific community and society/Social sciences/Economics Scientific community and society/Social sciences/Interdisciplinary studies Geospatial approach economic activity steel production machine learning Full Text Additional Declarations There is NO Competing Interest. 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-8051642","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Social Sciences - Article","associatedPublications":[],"authors":[{"id":543035903,"identity":"f2bdb604-7eb6-4645-9274-89d4a3b9076e","order_by":0,"name":"Anton Yang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIiWNgGAWjYHAD5gMMDAUgRgJBlTAGG1CpAWlaeAyI08I/u//g4wKGw/Lm/Gu+SfwwsGHgZ88xwKtF4s5hZuMZDIcNd854u02yxyCNQbLnDX4tDDeS2aR5GA4zbrhxdpsEj8FhBoMbBGyRh2qx33DjzDPJPwb/GewJaTGAaknccL4HyDA4wGAgQUCL4Y1kY2Meg/TkDTfYjK1lDJJ5JM48K8CrRe5G4sPHPBXWthvOH354802FnRx/e/IGvFqgzmsGhl0CiwSQyUOEcjCoA8bQAeYPxCofBaNgFIyCkQUA7T5EVnIoVJ0AAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0001-8341-6164","institution":"Yale University","correspondingAuthor":true,"prefix":"","firstName":"Anton","middleName":"","lastName":"Yang","suffix":""},{"id":543035904,"identity":"61b06841-f600-4a1a-bcc2-1f91df062959","order_by":1,"name":"Jianwei Ai","email":"","orcid":"","institution":"Cornell University","correspondingAuthor":false,"prefix":"","firstName":"Jianwei","middleName":"","lastName":"Ai","suffix":""},{"id":543035905,"identity":"8f442223-6706-4cf9-b041-c04f97598a67","order_by":2,"name":"Costas Arkolakis","email":"","orcid":"","institution":"Yale University","correspondingAuthor":false,"prefix":"","firstName":"Costas","middleName":"","lastName":"Arkolakis","suffix":""}],"badges":[],"createdAt":"2025-11-06 23:10:26","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8051642/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8051642/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96711587,"identity":"c026db96-3fd2-4661-99d2-e72ba30a74e5","added_by":"auto","created_at":"2025-11-25 10:12:16","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":17071187,"visible":true,"origin":"","legend":"Article File","description":"","filename":"GeospatialAllInOne.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8051642/v1_covered_38ea9bc2-9dee-4cff-bb07-6f2a8492367c.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"A Geospatial Approach to Measuring Economic Activity","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":"Geospatial approach, economic activity, steel production, machine learning","lastPublishedDoi":"10.21203/rs.3.rs-8051642/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8051642/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"We introduce a new methodology to detect and measure economic activity using geospatial data and apply it to steel production, a major industrial pollution source worldwide. Combining plant output data with geospatial data, such as ambient air pollutants, nighttime lights, and temperature, we train machine learning models to predict plant locations and output. We identify about 40% (70%) of plants missing from the training sample within a 1 km (5 km) radius and achieve R^2 above 0.8 for output prediction at a 1 km grid and at the plant level, as well as for both regional and time series validations. We apply the model trained on Chinese steel data to North Korea and use it to identify steel locations and output absent from official statistics but consistent with independent open-source and defector-based reports. Our approach can be adapted to other industries and regions, and used by policymakers and researchers to track and measure industrial activity in near real time.","manuscriptTitle":"A Geospatial Approach to Measuring Economic Activity","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-25 05:31:35","doi":"10.21203/rs.3.rs-8051642/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"6ebf73ba-83ec-4743-8d87-db00458ed4a1","owner":[],"postedDate":"November 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":57768898,"name":"Scientific community and society/Social sciences/Economics"},{"id":57768899,"name":"Scientific community and society/Social sciences/Interdisciplinary studies"}],"tags":[],"updatedAt":"2025-11-25T05:31:35+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-25 05:31:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8051642","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8051642","identity":"rs-8051642","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}