{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T17:33:12Z","timestamp":1783963992959,"version":"3.55.0"},"reference-count":29,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T00:00:00Z","timestamp":1769212800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T00:00:00Z","timestamp":1769212800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Concurrency and Computation"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    Accurate forecasting of carbon emissions from power generation enterprises is essential under China's dual\u2010control policy. Although deep learning methods show strong potential, studies on their optimal configuration remain limited. This paper proposed a hybrid deep learning framework integrating a convolutional neural network (CNN), bidirectional long short\u2010term memory (BiLSTM), and an attention mechanism for carbon emission prediction in natural gas power plants. The present study utilized two distinct optimization methodologies: a structured design strategy encompassing light, medium, and heavy configurations, while the other employed Bayesian optimization for hyperparameter tuning. The models were evaluated using 5\u2010fold cross\u2010validation on 619 operational samples from two 487.1\u2010MW condensing units in a power plant in Hainan, China. The medium configuration achieved the best balance between accuracy, efficiency, and stability, with R\n                    <jats:sup>2<\/jats:sup>\n                    \u2009=\u20090.9833, RMSE\u2009=\u20090.0342, and MAE\u2009=\u20090.0242. Under small\u2010sample conditions, the structured design approach outperformed Bayesian optimization by 0.16% in accuracy while requiring only 7.42% of the training time. The proposed framework provides an efficient and interpretable reference for selecting deep learning architectures in small\u2010sample industrial regression tasks and supports intelligent, low\u2010carbon power generation applications.\n                  <\/jats:p>","DOI":"10.1002\/cpe.70591","type":"journal-article","created":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T10:04:32Z","timestamp":1769249072000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Carbon Emission Prediction for Gas Power Plants Based on Deep Learning Under Small\u2010Sample Conditions"],"prefix":"10.1002","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2991-3861","authenticated-orcid":false,"given":"Xiaozhou","family":"Fan","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering North China Electric Power University  Baoding China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4174-3482","authenticated-orcid":false,"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering North China Electric Power University  Baoding China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanwen","family":"Bi","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering North China Electric Power University  Baoding China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering North China Electric Power University  Baoding China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,1,24]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43017\u2010021\u201000244\u2010x"},{"key":"e_1_2_8_3_1","volume-title":"An Energy Sector Roadmap to Carbon Neutrality in China","author":"IEA","year":"2021"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.spc.2024.04.007"},{"key":"e_1_2_8_5_1","unstructured":"The World Bank \u201cChina's Transition to a Low\u2010Carbon Economy and Climate Resilience Needs Shifts in Resources and Technologies \u201d(2022) https:\/\/www.worldbank.org\/en\/news\/press\u2010release\/2022\/10\/12\/china\u2010s\u2010transition\u2010to\u2010a\u2010low\u2010carbon\u2010economy\u2010and\u2010climate\u2010resilience\u2010needs\u2010shifts\u2010in\u2010resources\u2010and\u2010technologies."},{"issue":"1","key":"e_1_2_8_6_1","first-page":"50","article-title":"Study on the Potential of Greenhouse Gas Emission Reduction of Natura Gas Purification Plant Residual Pressure Power Generation Project","volume":"52","author":"Zhou W.","year":"2023","journal-title":"Petroleum & Natural Gas Chemistry Engineering"},{"key":"e_1_2_8_7_1","unstructured":"NET0 \u201cCarbon Accounting Methodologies for Measuring Emissions \u201d(2024) https:\/\/net0.com\/blog\/carbon\u2010accounting\u2010methodologies."},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1021\/acsenvironau.2c00014"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/app14188442"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcradv.2025.200263"},{"key":"e_1_2_8_11_1","first-page":"43","volume-title":"Proceedings of International Conference on Data, Electronics and Computing (ICDEC)","author":"Roy A.","year":"2023"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010024\u201068339\u20101"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11356\u2010024\u201035764\u20108"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csite.2024.105334"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1093\/ijlct\/ctaf012"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.3389\/fevo.2023.1270248"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.3390\/su151813934"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1186\/s42162\u2010024\u201000303\u20109"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065721300011"},{"key":"e_1_2_8_20_1","unstructured":"Q.Cao S.Liu A. J.Varghese et al. \u201cAutomatic Selection of the Best Neural Architecture for Time Series Forecasting via Multi\u2010Objective Optimization and Pareto Optimality Conditions \u201darXiv Preprint arXiv:2501.12215(2025) https:\/\/doi.org\/10.48550\/arXiv.2501.12215."},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010020\u201057866\u20102"},{"key":"e_1_2_8_22_1","first-page":"10767","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Yang Z.","year":"2020"},{"key":"e_1_2_8_23_1","unstructured":"J. M.Gorriz F.Segovia J.Ramirez et al. \u201cIs K\u2010Fold Cross Validation the Best Model Selection Method for Machine Learning? \u201darXiv Preprint arXiv:2401.16407(2024) https:\/\/doi.org\/10.48550\/arXiv.2401.16407."},{"key":"e_1_2_8_24_1","unstructured":"D.Ulmer C.Hardmeier andJ.Frellsen \u201cDeep\u2010Significance\u2010Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks \u201darXiv Preprint arXiv:2204.06815(2022) https:\/\/doi.org\/10.48550\/arXiv.2204.06815."},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010024\u201082188\u2010y"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0224365"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742\u20105468\/ac3a74"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.3390\/su142315988"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1903070116"},{"key":"e_1_2_8_30_1","unstructured":"S. D.Wang \u201cShort\u2010Term Power Load Forecasting Based on TPE\u2010IMBoost\u2010CS\u2010BiLSTM Two\u2010Stage Model Framework\u201d(M.S. thesis Northeast Agricultural University 2025) https:\/\/doi.org\/10.27010\/d.cnki.gdbnu.2025.000611. (in Chinese)."}],"container-title":["Concurrency and Computation: Practice and Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70591","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/cpe.70591","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T03:04:56Z","timestamp":1770260696000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cpe.70591"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,24]]},"references-count":29,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1002\/cpe.70591"],"URL":"https:\/\/doi.org\/10.1002\/cpe.70591","archive":["Portico"],"relation":{},"ISSN":["1532-0626","1532-0634"],"issn-type":[{"value":"1532-0626","type":"print"},{"value":"1532-0634","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,24]]},"assertion":[{"value":"2025-12-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70591"}}