{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T02:44:14Z","timestamp":1791600254909,"version":"4.3.4"},"reference-count":36,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.knosys.2026.115969","type":"journal-article","created":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T09:24:16Z","timestamp":1778577856000},"page":"115969","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["MTformer: A physics-guided spatio-temporal transformer for complex dynamic system modeling"],"prefix":"10.1016","volume":"347","author":[{"given":"Hao","family":"Tian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7672-7251","authenticated-orcid":false,"given":"Xiang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanliu","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3066-3716","authenticated-orcid":false,"given":"Yongmei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.115969_b1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1017\/jfm.2016.803","article-title":"Deep learning in fluid dynamics","volume":"814","author":"Kutz","year":"2017","journal-title":"J. Fluid Mech."},{"issue":"39","key":"10.1016\/j.knosys.2026.115969_b2","doi-asserted-by":"crossref","first-page":"9684","DOI":"10.1073\/pnas.1810286115","article-title":"Deep learning to represent subgrid processes in climate models","volume":"115","author":"Rasp","year":"2018","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"2","key":"10.1016\/j.knosys.2026.115969_b3","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/S0968-090X(01)00004-3","article-title":"Urban traffic flow prediction using a fuzzy-neural approach","volume":"10","author":"Yin","year":"2002","journal-title":"Transp. Res. C"},{"key":"10.1016\/j.knosys.2026.115969_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.jcp.2019.108925","article-title":"PDE-Net 2.0: Learning PDEs from data with a numeric-symbolic hybrid deep network","volume":"399","author":"Long","year":"2019","journal-title":"J. Comput. Phys."},{"key":"10.1016\/j.knosys.2026.115969_b5","doi-asserted-by":"crossref","unstructured":"H. Wu, B. Xiao, N. Codella, M. Liu, X. Dai, L. Yuan, L. Zhang, Cvt: Introducing convolutions to vision transformers, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 22\u201331.","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"10.1016\/j.knosys.2026.115969_b6","doi-asserted-by":"crossref","first-page":"25390","DOI":"10.52202\/068431-1841","article-title":"Earthformer: Exploring space-time transformers for earth system forecasting","volume":"35","author":"Gao","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115969_b7","first-page":"1","article-title":"Rainformer: Features extraction balanced network for radar-based precipitation nowcasting","volume":"19","author":"Bai","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.knosys.2026.115969_b8","series-title":"PredFormer: transformers are effective spatial-temporal predictive learners","author":"Tang","year":"2024"},{"key":"10.1016\/j.knosys.2026.115969_b9","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume":"28","author":"Shi","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115969_b10","series-title":"Deep predictive coding networks for video prediction and unsupervised learning","author":"Lotter","year":"2016"},{"key":"10.1016\/j.knosys.2026.115969_b11","article-title":"Predrnn: Recurrent neural networks for predictive learning using spatiotemporal lstms","volume":"30","author":"Wang","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115969_b12","series-title":"International Conference on Machine Learning","first-page":"5123","article-title":"Predrnn++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning","author":"Wang","year":"2018"},{"key":"10.1016\/j.knosys.2026.115969_b13","unstructured":"Y. Wang, L. Jiang, M.-H. Yang, L.-J. Li, M. Long, L. Fei-Fei, Eidetic 3D LSTM: A model for video prediction and beyond, in: International Conference on Learning Representations, 2018."},{"key":"10.1016\/j.knosys.2026.115969_b14","doi-asserted-by":"crossref","unstructured":"Y. Wang, J. Zhang, H. Zhu, M. Long, J. Wang, P.S. Yu, Memory in memory: A predictive neural network for learning higher-order non-stationarity from spatiotemporal dynamics, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 9154\u20139162.","DOI":"10.1109\/CVPR.2019.00937"},{"issue":"2","key":"10.1016\/j.knosys.2026.115969_b15","doi-asserted-by":"crossref","first-page":"2208","DOI":"10.1109\/TPAMI.2022.3165153","article-title":"Predrnn: A recurrent neural network for spatiotemporal predictive learning","volume":"45","author":"Wang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.115969_b16","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.knosys.2026.115969_b17","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.knosys.2026.115969_b18","doi-asserted-by":"crossref","unstructured":"Z. Gao, C. Tan, L. Wu, S.Z. Li, Simvp: Simpler yet better video prediction, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 3170\u20133180.","DOI":"10.1109\/CVPR52688.2022.00317"},{"key":"10.1016\/j.knosys.2026.115969_b19","first-page":"26950","article-title":"Mau: A motion-aware unit for video prediction and beyond","volume":"34","author":"Chang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115969_b20","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2026.3657055","article-title":"GMG: A video prediction method based on global focus and motion guided","author":"Du","year":"2026","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.115969_b21","doi-asserted-by":"crossref","unstructured":"Y. Zhong, L. Liang, I. Zharkov, U. Neumann, Mmvp: Motion-matrix-based video prediction, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 4273\u20134283.","DOI":"10.1109\/ICCV51070.2023.00394"},{"key":"10.1016\/j.knosys.2026.115969_b22","doi-asserted-by":"crossref","unstructured":"C. Tan, Z. Gao, L. Wu, Y. Xu, J. Xia, S. Li, S.Z. Li, Temporal attention unit: Towards efficient spatiotemporal predictive learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 18770\u201318782.","DOI":"10.1109\/CVPR52729.2023.01800"},{"key":"10.1016\/j.knosys.2026.115969_b23","series-title":"Icml","first-page":"4","article-title":"Is space-time attention all you need for video understanding?","volume":"Vol. 2","author":"Bertasius","year":"2021"},{"key":"10.1016\/j.knosys.2026.115969_b24","doi-asserted-by":"crossref","unstructured":"A. Arnab, M. Dehghani, G. Heigold, C. Sun, M. Lu\u010di\u0107, C. Schmid, Vivit: A video vision transformer, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 6836\u20136846.","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"10.1016\/j.knosys.2026.115969_b25","doi-asserted-by":"crossref","unstructured":"M. Tarasiou, E. Chavez, S. Zafeiriou, Vits for sits: Vision transformers for satellite image time series, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 10418\u201310428.","DOI":"10.1109\/CVPR52729.2023.01004"},{"key":"10.1016\/j.knosys.2026.115969_b26","doi-asserted-by":"crossref","unstructured":"S. Tang, C. Li, P. Zhang, R. Tang, Swinlstm: Improving spatiotemporal prediction accuracy using swin transformer and lstm, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 13470\u201313479.","DOI":"10.1109\/ICCV51070.2023.01239"},{"key":"10.1016\/j.knosys.2026.115969_b27","doi-asserted-by":"crossref","unstructured":"V.L. Guen, N. Thome, Disentangling physical dynamics from unknown factors for unsupervised video prediction, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11474\u201311484.","DOI":"10.1109\/CVPR42600.2020.01149"},{"key":"10.1016\/j.knosys.2026.115969_b28","series-title":"Fourier neural operator for parametric partial differential equations","author":"Li","year":"2020"},{"issue":"3","key":"10.1016\/j.knosys.2026.115969_b29","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1038\/s42256-021-00302-5","article-title":"Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators","volume":"3","author":"Lu","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.knosys.2026.115969_b30","first-page":"77187","article-title":"Convolutional neural operators for robust and accurate learning of PDEs","volume":"36","author":"Raonic","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115969_b31","doi-asserted-by":"crossref","unstructured":"X. Nie, Y. Yan, S. Li, C. Tan, X. Chen, H. Jin, Z. Zhu, S.Z. Li, D. Qi, Wavelet-driven spatiotemporal predictive learning: Bridging frequency and time variations, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 4334\u20134342.","DOI":"10.1609\/aaai.v38i5.28230"},{"key":"10.1016\/j.knosys.2026.115969_b32","doi-asserted-by":"crossref","unstructured":"J. Zhang, Y. Zheng, D. Qi, Deep spatio-temporal residual networks for citywide crowd flows prediction, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 31, 2017.","DOI":"10.1609\/aaai.v31i1.10735"},{"key":"10.1016\/j.knosys.2026.115969_b33","series-title":"International Conference on Machine Learning","first-page":"843","article-title":"Unsupervised learning of video representations using lstms","author":"Srivastava","year":"2015"},{"key":"10.1016\/j.knosys.2026.115969_b34","doi-asserted-by":"crossref","unstructured":"G. Yan, Z. Zhong, J. Hua, Self-supervised 3D human mesh recovery from a single image with uncertainty-aware learning, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 6422\u20136430.","DOI":"10.1609\/aaai.v38i6.28462"},{"key":"10.1016\/j.knosys.2026.115969_b35","first-page":"22009","article-title":"Sevir: A storm event imagery dataset for deep learning applications in radar and satellite meteorology","volume":"33","author":"Veillette","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115969_b36","doi-asserted-by":"crossref","unstructured":"L. Yuan, Y. Chen, T. Wang, W. Yu, Y. Shi, Z.-H. Jiang, F.E. Tay, J. Feng, S. Yan, Tokens-to-token vit: Training vision transformers from scratch on imagenet, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 558\u2013567.","DOI":"10.1109\/ICCV48922.2021.00060"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126006957?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126006957?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T12:13:50Z","timestamp":1780920830000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126006957"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":36,"alternative-id":["S0950705126006957"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115969","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MTformer: A physics-guided spatio-temporal transformer for complex dynamic system modeling","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115969","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"115969"}}