Carbon Emission Prediction for Energy-Intensive Industries Based on a TCN-Transformer Hybrid Model

Carbon Emission Prediction for Energy-Intensive Industries Based on a TCN-Transformer Hybrid Model | 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 Carbon Emission Prediction for Energy-Intensive Industries Based on a TCN-Transformer Hybrid Model Bowen Zheng, Mingming Pan, Chang Liu, Jie Tong, Jianfeng Li, Zhong Zhuang, and 8 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6824772/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 20 Apr, 2026 Read the published version in Scientific Reports → Version 1 posted 8 You are reading this latest preprint version Abstract This research presents a systematic framework for high-precision carbon emission forecasting in energy-intensive industries, integrating emission accounting methodologies with a Temporal Convolutional Network (TCN)-Transformer hybrid architecture. First, direct and indirect emissions from representative enterprises in the steel, concrete, and electrolytic aluminum sectors were rigorously quantified using the Intergovernmental Panel on Climate Change (IPCC)emission factor approach. Subsequently, a TCN-Transformer model was developed to capture temporal patterns in annual emission data, where the TCN module leverages dilated convolutions and residual connections to extract multi-scale features, while the Transformer component employs multi-head self-attention to model long-range dependencies. Empirical results demonstrate that the proposed hybrid model outperforms standalone Transformer architectures by 35% in prediction accuracy, achieving a Mean Absolute Percentage Error (MAPE) of 3.21%. This significant improvement underscores the model's efficacy in capturing complex emission dynamics, providing a robust tool for proactive carbon management strategies. Physical sciences/Engineering/Electrical and electronic engineering Physical sciences/Engineering/Energy infrastructure/Energy grids and networks Carbon Emission Prediction Energy-Intensive Industries TCN-Transformer Steel Industry Concrete Industry Electrolytic Aluminum Full Text Additional Declarations No competing interests reported. Supplementary Files SupplementaryInformation.xlsx Cite Share Download PDF Status: Published Journal Publication published 20 Apr, 2026 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 03 Jul, 2025 Reviews received at journal 23 Jun, 2025 Reviewers agreed at journal 13 Jun, 2025 Reviewers invited by journal 12 Jun, 2025 Editor assigned by journal 12 Jun, 2025 Editor invited by journal 09 Jun, 2025 Submission checks completed at journal 08 Jun, 2025 First submitted to journal 04 Jun, 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-6824772","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":471996482,"identity":"25d67365-51e3-4121-b1b5-6396dcb501a7","order_by":0,"name":"Bowen Zheng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1klEQVRIiWNgGAWjYBACAyBmBjH4QcQDiACRWiQbGBgbEkjSYnCAWC3mEgnMnwsq7thtPt5j/iChwsaYgf3w0Q34tFjOSGAwnnHmWfK2M2cMGxLOpJkx8KSl3cDrsNsJDMm8bYeTzW7kGDYkth22YZDgMSOo5TDvv8PJxjNI0MLYzNtw2M5AAqLFjKAWy/kPm5l5jh1OkDhzrHAG0C/GbIT8Ys5z+PBnnprD9vztzRs+fKiwMexnP3wMrxYGYGyAyMQGGJ8Nv3IEsCdW4SgYBaNgFIxAAAC/CEwnSoYFtwAAAABJRU5ErkJggg==","orcid":"","institution":"China Electric Power Research Institute","correspondingAuthor":true,"prefix":"","firstName":"Bowen","middleName":"","lastName":"Zheng","suffix":""},{"id":471996483,"identity":"a2573748-3de6-47bd-9c81-8ce3fb94864b","order_by":1,"name":"Mingming Pan","email":"","orcid":"","institution":"China Electric Power Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Mingming","middleName":"","lastName":"Pan","suffix":""},{"id":471996484,"identity":"f492e525-4f4e-49a3-a59b-74668d2a3754","order_by":2,"name":"Chang Liu","email":"","orcid":"","institution":"China Electric Power Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Chang","middleName":"","lastName":"Liu","suffix":""},{"id":471996485,"identity":"08495f9c-8b5a-42ee-874a-8ff272595fe3","order_by":3,"name":"Jie Tong","email":"","orcid":"","institution":"China Electric Power Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Jie","middleName":"","lastName":"Tong","suffix":""},{"id":471996486,"identity":"2de1c79e-75c9-4b79-8fad-45953ce5fceb","order_by":4,"name":"Jianfeng Li","email":"","orcid":"","institution":"China Electric Power Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Jianfeng","middleName":"","lastName":"Li","suffix":""},{"id":471996487,"identity":"c54d298f-cc71-4f0f-9c0d-bfc3eb0fc1af","order_by":5,"name":"Zhong Zhuang","email":"","orcid":"","institution":"State Grid Jiangsu Marketing Service Center","correspondingAuthor":false,"prefix":"","firstName":"Zhong","middleName":"","lastName":"Zhuang","suffix":""},{"id":471996488,"identity":"7d82f164-e499-4e0d-8cb8-ec92ca9c8858","order_by":6,"name":"Meimei Duan","email":"","orcid":"","institution":"State Grid Jiangsu Marketing Service Center","correspondingAuthor":false,"prefix":"","firstName":"Meimei","middleName":"","lastName":"Duan","suffix":""},{"id":471996490,"identity":"369b712a-8252-4475-a3a7-4089cd6c6889","order_by":7,"name":"Kaijie Fang","email":"","orcid":"","institution":"State Grid Jiangsu Marketing Service Center","correspondingAuthor":false,"prefix":"","firstName":"Kaijie","middleName":"","lastName":"Fang","suffix":""},{"id":471996491,"identity":"c22cc55e-ce55-4851-962c-4d76c8e90475","order_by":8,"name":"Yixuan Huang","email":"","orcid":"","institution":"State Grid Jiangsu Marketing Service Center","correspondingAuthor":false,"prefix":"","firstName":"Yixuan","middleName":"","lastName":"Huang","suffix":""},{"id":471996492,"identity":"cf78ea8f-7282-470b-8227-be3f7da0a1cb","order_by":9,"name":"Jing Zhang","email":"","orcid":"","institution":"China Electric Power Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Jing","middleName":"","lastName":"Zhang","suffix":""},{"id":471996493,"identity":"54474562-784d-432c-9e21-77d16e6187f8","order_by":10,"name":"Zixuan Guo","email":"","orcid":"","institution":"China Electric Power Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Zixuan","middleName":"","lastName":"Guo","suffix":""},{"id":471996494,"identity":"2ba196b2-85ca-4e91-b314-51721dc87934","order_by":11,"name":"Xu Xu","email":"","orcid":"","institution":"Xi’an Jiaotong-Liverpool University","correspondingAuthor":false,"prefix":"","firstName":"Xu","middleName":"","lastName":"Xu","suffix":""},{"id":471996495,"identity":"d16f7f1f-465e-4839-bc79-38160c33ceff","order_by":12,"name":"Jinjia Cao","email":"","orcid":"","institution":"Xi’an Jiaotong-Liverpool University","correspondingAuthor":false,"prefix":"","firstName":"Jinjia","middleName":"","lastName":"Cao","suffix":""},{"id":471996496,"identity":"972983be-da73-4db0-9766-d086f408f5b0","order_by":13,"name":"Yunfei Bo","email":"","orcid":"","institution":"Xi’an Jiaotong-Liverpool University","correspondingAuthor":false,"prefix":"","firstName":"Yunfei","middleName":"","lastName":"Bo","suffix":""}],"badges":[],"createdAt":"2025-06-05 03:23:47","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6824772/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6824772/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-026-49249-w","type":"published","date":"2026-04-20T15:58:13+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":107929338,"identity":"b474d143-8029-4894-8ef4-f4cae253338c","added_by":"auto","created_at":"2026-04-27 16:14:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":694786,"visible":true,"origin":"","legend":"","description":"","filename":"RevisedManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6824772/v1_covered_0be7e022-d18d-493d-a8a5-5dab17763a4f.pdf"},{"id":84823113,"identity":"623d2fbd-14f0-4915-8ab9-568668672e1f","added_by":"auto","created_at":"2025-06-17 16:27:46","extension":"xlsx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":44049,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryInformation.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-6824772/v1/290f651e3b019cf160d7135b.xlsx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Carbon Emission Prediction for Energy-Intensive Industries Based on a TCN-Transformer Hybrid Model","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":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Carbon Emission Prediction, Energy-Intensive Industries, TCN-Transformer, Steel Industry, Concrete Industry, Electrolytic Aluminum","lastPublishedDoi":"10.21203/rs.3.rs-6824772/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6824772/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis research presents a systematic framework for high-precision carbon emission forecasting in energy-intensive industries, integrating emission accounting methodologies with a Temporal Convolutional Network (TCN)-Transformer hybrid architecture. First, direct and indirect emissions from representative enterprises in the steel, concrete, and electrolytic aluminum sectors were rigorously quantified using the Intergovernmental Panel on Climate Change (IPCC)emission factor approach. Subsequently, a TCN-Transformer model was developed to capture temporal patterns in annual emission data, where the TCN module leverages dilated convolutions and residual connections to extract multi-scale features, while the Transformer component employs multi-head self-attention to model long-range dependencies. Empirical results demonstrate that the proposed hybrid model outperforms standalone Transformer architectures by 35% in prediction accuracy, achieving a Mean Absolute Percentage Error (MAPE) of 3.21%. This significant improvement underscores the model's efficacy in capturing complex emission dynamics, providing a robust tool for proactive carbon management strategies.\u003c/p\u003e","manuscriptTitle":"Carbon Emission Prediction for Energy-Intensive Industries Based on a TCN-Transformer Hybrid Model","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-17 16:27:41","doi":"10.21203/rs.3.rs-6824772/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-07-03T06:13:40+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-23T14:59:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"111613900238115850437389569591804020492","date":"2025-06-13T06:33:19+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-13T01:39:30+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-13T01:38:32+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-06-10T02:49:24+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-06-09T02:57:56+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-06-05T03:20:17+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"8c309206-2c9b-4daa-85c4-70070eadb90b","owner":[],"postedDate":"June 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":50122907,"name":"Physical sciences/Engineering/Electrical and electronic engineering"},{"id":50122908,"name":"Physical sciences/Engineering/Energy infrastructure/Energy grids and networks"}],"tags":[],"updatedAt":"2026-04-27T16:13:08+00:00","versionOfRecord":{"articleIdentity":"rs-6824772","link":"https://doi.org/10.1038/s41598-026-49249-w","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2026-04-20 15:58:13","publishedOnDateReadable":"April 20th, 2026"},"versionCreatedAt":"2025-06-17 16:27:41","video":"","vorDoi":"10.1038/s41598-026-49249-w","vorDoiUrl":"https://doi.org/10.1038/s41598-026-49249-w","workflowStages":[]},"version":"v1","identity":"rs-6824772","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6824772","identity":"rs-6824772","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}