Leveraging Machine Learning to Reveal Transparency in Integrated Assessment Model Ensembles

Leveraging Machine Learning to Reveal Transparency in Integrated Assessment Model Ensembles | 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 Leveraging Machine Learning to Reveal Transparency in Integrated Assessment Model Ensembles Hongbo Duan, Yixin Sun, Yun Tang, Gokul Iyer, Xiyu Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7727414/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 25 Apr, 2026 Read the published version in Climatic Change → Version 1 posted 4 You are reading this latest preprint version Abstract Integrated assessment and energy system models have long been criticized for their limited interpretability of results, particularly by policymakers, who find it difficult to use the evaluation results for informed policy-making due to the challenge of understanding the underlying model drivers and their assumptions. This underscores the urgent need to systematically attribute model outcomes to their underlying drivers for effective decision support. Here, we present a novel post-attribution framework combining error diagnostics, machine learning, and econometric analysis to disentangle the impacts of model inputs, structural inertia, and implicit assumptions. This framework is applied to post-evaluate global energy system and demand sector scenarios across mainstream Integrated Assessment Models (IAMs), identifying the root causes of discrepancies between models regarding the pace of energy transition. We find that the largest discrepancies in model inputs stem from energy demand variables, while errors in economic and energy supply variables are relatively minor, although the latter's input errors can have a delayed impact on long-term emissions forecasts. Significant differences in decarbonization pathways across models, largely driven by model preferences and technological assumptions such as technological inertia, cost, and maturity timelines, underscore the importance of considering modeling preferences in IAMs when attributing long-term emission differences. Our study paves the way for interpreting IAM ensembles results through machine learning, identifying the deep drivers of result discrepancies, and supporting model development and policy decision-making. Full Text Supplementary Files Supplementaryinformation.docx Cite Share Download PDF Status: Published Journal Publication published 25 Apr, 2026 Read the published version in Climatic Change → Version 1 posted Reviewers agreed at journal 22 Oct, 2025 Reviewers invited by journal 22 Oct, 2025 Editor assigned by journal 30 Sep, 2025 First submitted to journal 29 Sep, 2025 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-7727414","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":533195834,"identity":"790b2e31-c64f-4245-a79d-2776293ed2e2","order_by":0,"name":"Hongbo Duan","email":"","orcid":"","institution":"University of the Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Hongbo","middleName":"","lastName":"Duan","suffix":""},{"id":533195835,"identity":"edf0b16d-71a4-48f8-860d-ba4834f8290e","order_by":1,"name":"Yixin Sun","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFklEQVRIie2RMUvDQBTHX4gky4OsTyrkK1wohIBiv8qFQKczCC4FQQOFuMS9H8OpqwGhLumeo4OUQqYOOggpdOgFdRAuYDeH+y13cPze//84AIPhv8KBwHOnJQCLjlBOiwVXCh2RxGrB1PEHxZ9dLWidRymU4vOpvaYRULL+aOHSB3dZ6oenY+IV3VjZci4LRnFG4+EAIQkyTLlWIRESn1A8tR7nNTJSewkYANjqgkxfrFPU8NzGRu5ZV0zYuxbuexWov1MKB52VSrEyEg4hvPQqrNoOI7VLPEMnXJ11cdiE58hegxyFvtiDCOQuv4uf3zaN3O4vRp6bbGQ7ufU9t9IXAzj5/RfOV/rPRYv93v9mMBgMBsUBqQpUKTlqay4AAAAASUVORK5CYII=","orcid":"https://orcid.org/0009-0002-3198-3938","institution":"University of the Chinese Academy of Sciences","correspondingAuthor":true,"prefix":"","firstName":"Yixin","middleName":"","lastName":"Sun","suffix":""},{"id":533195836,"identity":"d136ddd2-9e6c-4ce6-9c1c-ff5be869cda9","order_by":2,"name":"Yun Tang","email":"","orcid":"","institution":"University of the Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Yun","middleName":"","lastName":"Tang","suffix":""},{"id":533195837,"identity":"49eca28f-3671-4e9e-b8b7-5f4f5cd18ada","order_by":3,"name":"Gokul Iyer","email":"","orcid":"","institution":"University of Maryland","correspondingAuthor":false,"prefix":"","firstName":"Gokul","middleName":"","lastName":"Iyer","suffix":""},{"id":533195838,"identity":"fba400c3-0c0a-4b24-b5eb-25528ce616eb","order_by":4,"name":"Xiyu Li","email":"","orcid":"","institution":"University of the Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Xiyu","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-09-27 09:22:37","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7727414/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7727414/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10584-026-04181-w","type":"published","date":"2026-04-25T15:58:20+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":95081728,"identity":"ce215738-26a0-41ba-adef-6ba402808f9d","added_by":"auto","created_at":"2025-11-04 06:24:45","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10069,"visible":true,"origin":"","legend":"","description":"","filename":"climCLIMD2501722.xml","url":"https://assets-eu.researchsquare.com/files/rs-7727414/v1/7499024722362ac87ecc8128.xml"},{"id":95081738,"identity":"359f86e6-1371-45e6-acb0-6156ccf979df","added_by":"auto","created_at":"2025-11-04 06:24:49","extension":"xml","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1055,"visible":true,"origin":"","legend":"","description":"","filename":"CLIMD250172233856.go.xml","url":"https://assets-eu.researchsquare.com/files/rs-7727414/v1/8f75c0569f21b698cb54712e.xml"},{"id":95081742,"identity":"a735ee2c-63d6-43c9-b4e9-7a0a4dcd5b2c","added_by":"auto","created_at":"2025-11-04 06:24:51","extension":"xml","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":854,"visible":true,"origin":"","legend":"","description":"","filename":"CLIMD2501722Import.xml","url":"https://assets-eu.researchsquare.com/files/rs-7727414/v1/464b87974f1cca050affeab7.xml"},{"id":95081736,"identity":"00487cfb-7e52-46b2-b639-357e4508c0dd","added_by":"auto","created_at":"2025-11-04 06:24:49","extension":"xml","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7213,"visible":true,"origin":"","legend":"","description":"","filename":"CLIMD25017220enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7727414/v1/92a39f93dd212d17941f36d3.xml"},{"id":95081729,"identity":"b22132c9-ffe7-4c07-abcb-a8c80ad5d409","added_by":"auto","created_at":"2025-11-04 06:24:45","extension":"xml","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6376,"visible":true,"origin":"","legend":"","description":"","filename":"CLIMD25017220structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7727414/v1/83986da242e0ad84f403b5a4.xml"},{"id":95224374,"identity":"a294ee93-ac06-4017-900d-4642e6f0b346","added_by":"auto","created_at":"2025-11-05 16:23:40","extension":"html","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10435,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7727414/v1/47485eb0d44a133184067f9b.html"},{"id":107928293,"identity":"3f32c1e3-64f2-4d90-a8b7-105d1ba60d80","added_by":"auto","created_at":"2026-04-27 16:09:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1639662,"visible":true,"origin":"","legend":"","description":"","filename":"Maintext.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7727414/v1_covered_071450d7-1a3b-4610-81c2-627dc59c6c3c.pdf"},{"id":95081739,"identity":"bb3a306c-ea9a-4f7b-8e09-d177b0ccd1ea","added_by":"auto","created_at":"2025-11-04 06:24:50","extension":"docx","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":8967345,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementaryinformation.docx","url":"https://assets-eu.researchsquare.com/files/rs-7727414/v1/90b61e08ccfe38acb3abc596.docx"}],"financialInterests":"","formattedTitle":"Leveraging Machine Learning to Reveal Transparency in Integrated Assessment Model Ensembles","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"climatic-change","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"clim","sideBox":"Learn more about [Climatic Change](https://www.springer.com/journal/10584)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/clim/default.aspx","title":"Climatic Change","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7727414/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7727414/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Integrated assessment and energy system models have long been criticized for their limited interpretability of results, particularly by policymakers, who find it difficult to use the evaluation results for informed policy-making due to the challenge of understanding the underlying model drivers and their assumptions. This underscores the urgent need to systematically attribute model outcomes to their underlying drivers for effective decision support. Here, we present a novel post-attribution framework combining error diagnostics, machine learning, and econometric analysis to disentangle the impacts of model inputs, structural inertia, and implicit assumptions. This framework is applied to post-evaluate global energy system and demand sector scenarios across mainstream Integrated Assessment Models (IAMs), identifying the root causes of discrepancies between models regarding the pace of energy transition. We find that the largest discrepancies in model inputs stem from energy demand variables, while errors in economic and energy supply variables are relatively minor, although the latter's input errors can have a delayed impact on long-term emissions forecasts. Significant differences in decarbonization pathways across models, largely driven by model preferences and technological assumptions such as technological inertia, cost, and maturity timelines, underscore the importance of considering modeling preferences in IAMs when attributing long-term emission differences. Our study paves the way for interpreting IAM ensembles results through machine learning, identifying the deep drivers of result discrepancies, and supporting model development and policy decision-making.","manuscriptTitle":"Leveraging Machine Learning to Reveal Transparency in Integrated Assessment Model Ensembles","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-04 06:24:36","doi":"10.21203/rs.3.rs-7727414/v1","editorialEvents":[{"type":"communityComments","content":1},{"type":"reviewerAgreed","content":"","date":"2025-10-22T09:51:26+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-22T07:27:09+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-30T17:07:39+00:00","index":"","fulltext":""},{"type":"submitted","content":"Climatic Change","date":"2025-09-29T22:26:18+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"climatic-change","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"clim","sideBox":"Learn more about [Climatic Change](https://www.springer.com/journal/10584)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/clim/default.aspx","title":"Climatic Change","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"c8267194-060f-4bcc-809d-7f2622202bef","owner":[],"postedDate":"November 4th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-04-27T16:06:53+00:00","versionOfRecord":{"articleIdentity":"rs-7727414","link":"https://doi.org/10.1007/s10584-026-04181-w","journal":{"identity":"climatic-change","isVorOnly":false,"title":"Climatic Change"},"publishedOn":"2026-04-25 15:58:20","publishedOnDateReadable":"April 25th, 2026"},"versionCreatedAt":"2025-11-04 06:24:36","video":"","vorDoi":"10.1007/s10584-026-04181-w","vorDoiUrl":"https://doi.org/10.1007/s10584-026-04181-w","workflowStages":[]},"version":"v1","identity":"rs-7727414","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7727414","identity":"rs-7727414","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}