{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T23:22:15Z","timestamp":1774653735601,"version":"3.50.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,7,25]],"date-time":"2023-07-25T00:00:00Z","timestamp":1690243200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,7,25]],"date-time":"2023-07-25T00:00:00Z","timestamp":1690243200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62001502"],"award-info":[{"award-number":["62001502"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2024,2]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Recovering the global accurate complex physics field from limited sensors is critical to the measurement and control of the engineering system. General reconstruction methods for recovering the field, especially the deep learning with more parameters and better representational ability, usually require large amounts of labeled data which is unaffordable in practice. To solve the problem, this paper proposes uncertainty guided ensemble self-training (UGE-ST), using plentiful unlabeled data to improve reconstruction performance and reduce the required labeled data. A novel self-training framework with the ensemble teacher and pre-training student designed to improve the accuracy of the pseudo-label and remedy the impact of noise is first proposed. On the other hand, uncertainty guided learning is proposed to encourage the model to focus on the highly confident regions of pseudo-labels and mitigate the effects of wrong pseudo-labeling in self-training, improving the performance of the reconstruction model. Experiments including the airfoil velocity and pressure field reconstruction and the electronic components\u2019 temperature field reconstruction indicate that our UGE-ST can save up to 90% of the data with the same accuracy as supervised learning.<\/jats:p>","DOI":"10.1007\/s40747-023-01167-4","type":"journal-article","created":{"date-parts":[[2023,7,25]],"date-time":"2023-07-25T08:01:59Z","timestamp":1690272119000},"page":"469-483","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Uncertainty guided ensemble self-training for semi-supervised global field reconstruction"],"prefix":"10.1007","volume":"10","author":[{"given":"Yunyang","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Zhiqiang","family":"Gong","sequence":"additional","affiliation":[]},{"given":"Xiaoyu","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-9834","authenticated-orcid":false,"given":"Wen","family":"Yao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,25]]},"reference":[{"key":"1167_CR1","doi-asserted-by":"publisher","first-page":"113763","DOI":"10.1016\/j.cma.2021.113763","volume":"379","author":"Q Hernandez","year":"2021","unstructured":"Hernandez Q, Badias A, Gonzalez D, Chinesta F, Cueto E (2021) Deep learning of thermodynamics-aware reduced-order models from data. Comput Methods Appl Mech Eng 379:113763","journal-title":"Comput Methods Appl Mech Eng"},{"issue":"21","key":"1167_CR2","doi-asserted-by":"publisher","first-page":"e2101784118","DOI":"10.1073\/pnas.2101784118","volume":"118","author":"D Kochkov","year":"2021","unstructured":"Kochkov D, Smith JA, Alieva A, Wang Q, Brenner MP, Hoyer S (2021) Machine learning-accelerated computational fluid dynamics. Proc Natl Acad Sci 118(21):e2101784118","journal-title":"Proc Natl Acad Sci"},{"issue":"2","key":"1167_CR3","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1093\/gji\/ggz204","volume":"218","author":"V Puzyrev","year":"2019","unstructured":"Puzyrev V (2019) Deep learning electromagnetic inversion with convolutional neural networks. Geophys J Int 218(2):817\u2013832","journal-title":"Geophys J Int"},{"key":"1167_CR4","doi-asserted-by":"publisher","first-page":"113741","DOI":"10.1016\/j.cma.2021.113741","volume":"379","author":"E Haghighat","year":"2021","unstructured":"Haghighat E, Raissi M, Moure A, Gomez H, Juanes R (2021) A physics-informed deep learning framework for inversion and surrogate modeling in solid mechanics. Comput Methods Appl Mech Eng 379:113741","journal-title":"Comput Methods Appl Mech Eng"},{"issue":"11","key":"1167_CR5","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1038\/s42256-021-00402-2","volume":"3","author":"K Fukami","year":"2021","unstructured":"Fukami K, Maulik R, Ramachandra N, Fukagata K, Taira K (2021) Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning. Nat Mach Intell 3(11):945\u2013951","journal-title":"Nat Mach Intell"},{"key":"1167_CR6","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.ress.2019.04.011","volume":"189","author":"X Zheng","year":"2019","unstructured":"Zheng X, Yao W, Xu Y, Chen X (2019) Improved compression inference algorithm for reliability analysis of complex multistate satellite system based on multilevel Bayesian network. Reliab Eng Syst Saf 189:123\u2013142","journal-title":"Reliab Eng Syst Saf"},{"key":"1167_CR7","doi-asserted-by":"publisher","first-page":"107011","DOI":"10.1016\/j.ress.2020.107011","volume":"202","author":"X Zheng","year":"2020","unstructured":"Zheng X, Yao W, Xu Y, Chen X (2020) Algorithms for BDayesian network modeling and reliability inference of complex multistate systems: Part i-independent systems. Reliab Eng Syst Saf 202:107011","journal-title":"Reliab Eng Syst Saf"},{"key":"1167_CR8","doi-asserted-by":"crossref","unstructured":"Djordjevic V, Stojanovic V, Tao H, Song X, He S, Gao W (2022) Data-driven control of hydraulic servo actuator based on adaptive dynamic programming. Discrete Contin Dyn Syst-Ser S 15(7):1633\u20131650","DOI":"10.3934\/dcdss.2021145"},{"key":"1167_CR9","unstructured":"Wold H (1966) Estimation of principal components and related models by iterative least squares. Multivariate Anal 1:391\u2013420"},{"issue":"5","key":"1167_CR10","doi-asserted-by":"publisher","first-page":"4098","DOI":"10.1109\/TIE.2019.2922941","volume":"67","author":"Q Jiang","year":"2019","unstructured":"Jiang Q, Yan X, Yi H, Gao F (2019) Data-driven batch-end quality modeling and monitoring based on optimized sparse partial least squares. IEEE Trans Ind Electron 67(5):4098\u20134107","journal-title":"IEEE Trans Ind Electron"},{"issue":"3","key":"1167_CR11","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1016\/j.bej.2005.08.002","volume":"27","author":"K Desai","year":"2006","unstructured":"Desai K, Badhe Y, Tambe SS, Kulkarni BD (2006) Soft-sensor development for fed-batch bioreactors using support vector regression. Biochem Eng J 27(3):225\u2013239","journal-title":"Biochem Eng J"},{"key":"1167_CR12","doi-asserted-by":"crossref","unstructured":"Shen L, Tao H, Ni Y et al (2023) Improved YOLOv3 model with feature map cropping for multi-scale road object detection. Measur Sci Technol 34(4):045406","DOI":"10.1088\/1361-6501\/acb075"},{"issue":"4","key":"1167_CR13","doi-asserted-by":"publisher","first-page":"2287","DOI":"10.1007\/s00158-021-02983-3","volume":"64","author":"X Zhao","year":"2021","unstructured":"Zhao X, Gong Z, Zhang J, Yao W, Chen X (2021) A surrogate model with data augmentation and deep transfer learning for temperature field prediction of heat source layout. Struct Multidiscip Optim 64(4):2287\u20132306","journal-title":"Struct Multidiscip Optim"},{"key":"1167_CR14","doi-asserted-by":"publisher","first-page":"105516","DOI":"10.1016\/j.engappai.2022.105516","volume":"117","author":"X Zhao","year":"2023","unstructured":"Zhao X, Gong Z, Zhang Y, Yao W, Chen X (2023) Physics-informed convolutional neural networks for temperature field prediction of heat source layout without labeled data. Eng Appl Artif Intell 117:105516","journal-title":"Eng Appl Artif Intell"},{"issue":"2","key":"1167_CR15","doi-asserted-by":"publisher","first-page":"1454","DOI":"10.1016\/j.jfranklin.2022.11.004","volume":"360","author":"H Tao","year":"2023","unstructured":"Tao H, Qiu J, Chen Y, Stojanovic V, Cheng L (2023) Unsupervised cross-domain rolling bearing fault diagnosis based on time-frequency information fusion. J Franklin Inst 360(2):1454\u20131477","journal-title":"J Franklin Inst"},{"key":"1167_CR16","unstructured":"Zhang Y, Gong Z, Zhou W, Zhao X, Zheng X, Yao W Multi-fidelity surrogate modeling for temperature field prediction using deep convolution neural network. arXiv preprint arXiv:2301.06674"},{"key":"1167_CR17","doi-asserted-by":"publisher","first-page":"108813","DOI":"10.1016\/j.ress.2022.108813","volume":"229","author":"W Yao","year":"2023","unstructured":"Yao W, Zheng X, Zhang J, Wang N, Tang G (2023) Deep adaptive arbitrary polynomial chaos expansion: a mini-data-driven semi-supervised method for uncertainty quantification. Reliab Eng Syst Saf 229:108813","journal-title":"Reliab Eng Syst Saf"},{"key":"1167_CR18","unstructured":"Zhang Y, Gong Z, Zhao X, Zheng X, Yao W (2022) Semi-supervised semantic segmentation with uncertainty-guided self cross supervision. In: Proceedings of the Asian Conference on computer vision, pp 4631\u20134647"},{"key":"1167_CR19","doi-asserted-by":"crossref","unstructured":"Lai C-I, Chuang Y-S, Lee H-Y, Li S-W, Glass J (2021) Semi-supervised spoken language understanding via self-supervised speech and language model pretraining, In: ICASSP 2021-2021 IEEE International Conference on acoustics, speech and signal processing (ICASSP), IEEE, pp 7468\u20137472","DOI":"10.1109\/ICASSP39728.2021.9414922"},{"key":"1167_CR20","doi-asserted-by":"publisher","first-page":"107043","DOI":"10.1016\/j.ymssp.2020.107043","volume":"146","author":"K Yu","year":"2021","unstructured":"Yu K, Lin TR, Ma H, Li X, Li X (2021) A multi-stage semi-supervised learning approach for intelligent fault diagnosis of rolling bearing using data augmentation and metric learning. Mech Syst Signal Process 146:107043","journal-title":"Mech Syst Signal Process"},{"key":"1167_CR21","doi-asserted-by":"crossref","unstructured":"Luo X, Chen J, Song T, Wang G (2021) Semi-supervised medical image segmentation through dual-task consistency. In: Proceedings of the AAAI Conference on artificial intelligence, Vol. 35, pp 8801\u20138809","DOI":"10.1609\/aaai.v35i10.17066"},{"key":"1167_CR22","doi-asserted-by":"publisher","first-page":"108732","DOI":"10.1016\/j.ress.2022.108732","volume":"227","author":"X Zheng","year":"2022","unstructured":"Zheng X, Yao W, Zhang Y, Zhang X (2022) Consistency regularization-based deep polynomial chaos neural network method for reliability analysis. Reliab Eng Syst Saf 227:108732","journal-title":"Reliab Eng Syst Saf"},{"key":"1167_CR23","doi-asserted-by":"crossref","unstructured":"Yang L, Zhuo W, Qi L, Shi Y, Gao Y (2022) St++: make self-training work better for semi-supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 4268\u20134277","DOI":"10.1109\/CVPR52688.2022.00423"},{"key":"1167_CR24","doi-asserted-by":"crossref","unstructured":"Yang X, Song Z, King I, Xu Z (2022) A survey on deep semi-supervised learning, IEEE Trans Knowl Data Eng. https:\/\/doi.org\/10.1109\/TKDE.2022.3220219","DOI":"10.1109\/TKDE.2022.3220219"},{"key":"1167_CR25","unstructured":"Laine S, Aila T Temporal ensembling for semi-supervised learning. arXiv preprint arXiv:1610.02242"},{"key":"1167_CR26","unstructured":"Tarvainen A, Valpola H Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in neural information processing systems, p 30"},{"key":"1167_CR27","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.neunet.2021.10.008","volume":"145","author":"V Verma","year":"2022","unstructured":"Verma V, Kawaguchi K, Lamb A, Kannala J, Solin A, Bengio Y, Lopez-Paz D (2022) Interpolation consistency training for semi-supervised learning. Neural Netw 145:90\u2013106","journal-title":"Neural Netw"},{"key":"1167_CR28","first-page":"6256","volume":"33","author":"Q Xie","year":"2020","unstructured":"Xie Q, Dai Z, Hovy E, Luong T, Le Q (2020) Unsupervised data augmentation for consistency training. Adv Neural Inf Process Syst 33:6256\u20136268","journal-title":"Adv Neural Inf Process Syst"},{"key":"1167_CR29","doi-asserted-by":"crossref","unstructured":"Pham H, Dai Z, Xie Q, Le QV (2021) Meta pseudo labels, In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 11557\u201311568","DOI":"10.1109\/CVPR46437.2021.01139"},{"key":"1167_CR30","doi-asserted-by":"crossref","unstructured":"Zhai X, Oliver A, Kolesnikov A, Beyer L (2019) S4l: self-supervised semi-supervised learning, In: Proceedings of the IEEE\/CVF International Conference on computer vision, pp 1476\u20131485","DOI":"10.1109\/ICCV.2019.00156"},{"issue":"2","key":"1167_CR31","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/s10994-019-05855-6","volume":"109","author":"JE Van Engelen","year":"2020","unstructured":"Van Engelen JE, Hoos HH (2020) A survey on semi-supervised learning. Mach Learn 109(2):373\u2013440","journal-title":"Mach Learn"},{"issue":"5","key":"1167_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-021-3645-4","volume":"66","author":"X Chen","year":"2023","unstructured":"Chen X, Gong Z, Zhao X, Zhou W, Yao W (2023) A machine learning surrogate modeling benchmark for temperature field reconstruction of heat source systems. Sci China Inf Sci 66(5):1\u201320","journal-title":"Sci China Inf Sci"},{"issue":"9","key":"1167_CR33","doi-asserted-by":"publisher","first-page":"1981","DOI":"10.1007\/s11431-020-1829-2","volume":"64","author":"B Li","year":"2021","unstructured":"Li B, Liu H, Wang R (2021) Data-driven sensor placement for efficient thermal field reconstruction. Sci China Technol Sci 64(9):1981\u20131994","journal-title":"Sci China Technol Sci"},{"issue":"3","key":"1167_CR34","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.taml.2020.01.031","volume":"10","author":"L Sun","year":"2020","unstructured":"Sun L, Wang J-X (2020) Physics-constrained Bayesian neural network for fluid flow reconstruction with sparse and noisy data. Theor Appl Mech Lett 10(3):161\u2013169","journal-title":"Theor Appl Mech Lett"},{"issue":"2238","key":"1167_CR35","doi-asserted-by":"publisher","first-page":"20200097","DOI":"10.1098\/rspa.2020.0097","volume":"476","author":"NB Erichson","year":"2020","unstructured":"Erichson NB, Mathelin L, Yao Z, Brunton SL, Mahoney MW, Kutz JN (2020) Shallow neural networks for fluid flow reconstruction with limited sensors. Proc R Soc A 476(2238):20200097","journal-title":"Proc R Soc A"},{"key":"1167_CR36","unstructured":"Havasi M, Jenatton R, Fort S, Liu JZ, Snoek J, Lakshminarayanan B, Dai AM, Tran D Training independent subnetworks for robust prediction. arXiv preprint arXiv:2010.06610"},{"issue":"1","key":"1167_CR37","doi-asserted-by":"publisher","first-page":"25","DOI":"10.2514\/1.J058291","volume":"58","author":"N Thuerey","year":"2020","unstructured":"Thuerey N, Wei\u00dfenow K, Prantl L, Hu X (2020) Deep learning methods for Reynolds-averaged Navier-Stokes simulations of airfoil flows. AIAA J 58(1):25\u201336","journal-title":"AIAA J"},{"issue":"1","key":"1167_CR38","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1109\/TNNLS.2020.2978577","volume":"32","author":"Z Gong","year":"2020","unstructured":"Gong Z, Zhong P, Hu W (2020) Statistical loss and analysis for deep learning in hyperspectral image classification. IEEE Trans Neural Netw Learn Syst 32(1):322\u2013333","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"6","key":"1167_CR39","doi-asserted-by":"publisher","first-page":"3599","DOI":"10.1109\/TGRS.2018.2886022","volume":"57","author":"Z Gong","year":"2019","unstructured":"Gong Z, Zhong P, Yu Y, Hu W, Li S (2019) A CNN with multiscale convolution and diversified metric for hyperspectral image classification. IEEE Trans Geosci Remote Sens 57(6):3599\u20133618","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"1167_CR40","doi-asserted-by":"crossref","unstructured":"Ronneberger O., Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention, Springer, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1167_CR41","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1515\/crll.1908.134.198","volume":"134","author":"G Vorono\u00ef","year":"1908","unstructured":"Vorono\u00ef G (1908) New applications of continuous parameters to the theory of quadratic forms. Z Reine Angew Math 134:198","journal-title":"Z Reine Angew Math"},{"key":"1167_CR42","unstructured":"Chen X, Gong Z, Zhao X, Zhou W, Yao W A machine learning modelling benchmark for temperature field reconstruction of heat-source systems. arXiv preprint arXiv:2108.08298"},{"key":"1167_CR43","doi-asserted-by":"crossref","unstructured":"Blum A, Mitchell T (1998) Combining labeled and unlabeled data with co-training. In: Proceedings of the Eleventh Annual Conference on Computational learning theory, pp 92\u2013100","DOI":"10.1145\/279943.279962"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-023-01167-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-023-01167-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-023-01167-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,10]],"date-time":"2024-02-10T22:18:31Z","timestamp":1707603511000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-023-01167-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,25]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["1167"],"URL":"https:\/\/doi.org\/10.1007\/s40747-023-01167-4","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,25]]},"assertion":[{"value":"19 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The code of the proposed method is publicly available at .","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Replication of results"}}]}}