{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T12:59:47Z","timestamp":1781787587223,"version":"3.54.5"},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100006769","name":"Russian Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006769","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012190","name":"FSBSI Directorate of State Scientific and Technical Programs","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Computational Science"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.jocs.2026.102917","type":"journal-article","created":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:13:44Z","timestamp":1780445624000},"page":"102917","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Exploring the limitations of transformer models for metocean forecasting"],"prefix":"10.1016","volume":"99","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6680-0940","authenticated-orcid":false,"given":"Julia","family":"Borisova","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mikhail","family":"Borisov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stanislava","family":"Vostrikova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Viktor","family":"Golikov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrey","family":"Kuznetsov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gleb","family":"Solovev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander A.","family":"Stepanets","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mikhail","family":"Krinitskiy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6839-9957","authenticated-orcid":false,"given":"Nikolay O.","family":"Nikitin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jocs.2026.102917_b1","series-title":"International Conference on Computational Science","first-page":"104","article-title":"Understanding the limitations of deep transformer models for sea ice forecasting","author":"Borisova","year":"2025"},{"key":"10.1016\/j.jocs.2026.102917_b2","doi-asserted-by":"crossref","unstructured":"A. Zeng, M. Chen, L. Zhang, Q. Xu, Are transformers effective for time series forecasting?, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, 2023, pp. 11121\u201311128.","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"10.1016\/j.jocs.2026.102917_b3","first-page":"1","article-title":"Advancing Arctic sea ice remote sensing with AI and deep learning: now and future","volume":"2024","author":"Li","year":"2024","journal-title":"EGUsphere"},{"issue":"1","key":"10.1016\/j.jocs.2026.102917_b4","doi-asserted-by":"crossref","first-page":"5124","DOI":"10.1038\/s41467-021-25257-4","article-title":"Seasonal Arctic sea ice forecasting with probabilistic deep learning","volume":"12","author":"Andersson","year":"2021","journal-title":"Nat. Commun."},{"issue":"22","key":"10.1016\/j.jocs.2026.102917_b5","doi-asserted-by":"crossref","first-page":"5837","DOI":"10.3390\/rs14225837","article-title":"Data-driven short-term daily operational sea ice regional forecasting","volume":"14","author":"Grigoryev","year":"2022","journal-title":"Remote. Sens."},{"key":"10.1016\/j.jocs.2026.102917_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.rse.2024.114568","article-title":"Long-term prediction of Arctic sea ice concentrations using deep learning: Effects of surface temperature, radiation, and wind conditions","volume":"318","author":"Kim","year":"2025","journal-title":"Remote Sens. Environ."},{"key":"10.1016\/j.jocs.2026.102917_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.109445","article-title":"Deep coastal sea elements forecasting using UNet-based models","volume":"252","author":"Fern\u00e1ndez","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.jocs.2026.102917_b8","series-title":"Efficient spatio-temporal weather forecasting using U-Net","author":"Punjabi","year":"2021"},{"key":"10.1016\/j.jocs.2026.102917_b9","doi-asserted-by":"crossref","unstructured":"Z. Liu, J. Ning, Y. Cao, Y. Wei, Z. Zhang, S. Lin, H. Hu, Video swin transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 3202\u20133211.","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"10.1016\/j.jocs.2026.102917_b10","doi-asserted-by":"crossref","first-page":"2721","DOI":"10.1007\/s00382-018-4288-y","article-title":"Regional Arctic sea\u2013ice prediction: Potential versus operational seasonal forecast skill","volume":"52","author":"Bushuk","year":"2019","journal-title":"Clim. Dyn."},{"key":"10.1016\/j.jocs.2026.102917_b11","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.jocs.2026.102917_b12","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"},{"issue":"3","key":"10.1016\/j.jocs.2026.102917_b13","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.5194\/gmd-12-1087-2019","article-title":"SEAS5: the new ECMWF seasonal forecast system","volume":"12","author":"Johnson","year":"2019","journal-title":"Geosci. Model. Dev."},{"key":"10.1016\/j.jocs.2026.102917_b14","doi-asserted-by":"crossref","unstructured":"K. He, H. Fan, Y. Wu, S. Xie, R. Girshick, Momentum contrast for unsupervised visual representation learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 9729\u20139738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"10.1016\/j.jocs.2026.102917_b15","doi-asserted-by":"crossref","unstructured":"M. Destro, M. Gygli, CycleCL: Self-supervised Learning for Periodic Videos, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2024, pp. 2861\u20132870.","DOI":"10.1109\/WACV57701.2024.00284"},{"issue":"10","key":"10.1016\/j.jocs.2026.102917_b16","doi-asserted-by":"crossref","DOI":"10.1029\/2019GL086749","article-title":"Arctic sea ice in CMIP6","volume":"47","author":"Notz","year":"2020","journal-title":"Geophys. Res. Lett."},{"issue":"15","key":"10.1016\/j.jocs.2026.102917_b17","doi-asserted-by":"crossref","first-page":"6399","DOI":"10.1175\/JCLI-D-20-0491.1","article-title":"A spatial evaluation of Arctic sea ice and regional limitations in CMIP6 historical simulations","volume":"34","author":"Watts","year":"2021","journal-title":"J. Clim."},{"issue":"9","key":"10.1016\/j.jocs.2026.102917_b18","doi-asserted-by":"crossref","first-page":"2665","DOI":"10.5194\/gmd-18-2665-2025","article-title":"SICNetseason V1. 0: a transformer-based deep learning model for seasonal Arctic sea ice prediction by incorporating sea ice thickness data","volume":"18","author":"Ren","year":"2025","journal-title":"Geosci. Model. Dev."},{"issue":"6","key":"10.1016\/j.jocs.2026.102917_b19","first-page":"1673","article-title":"Extended-range arctic sea ice forecast with convolutional long short-term memory networks","volume":"149","author":"Liu","year":"2021","journal-title":"Mon. Weather Rev."},{"issue":"6","key":"10.1016\/j.jocs.2026.102917_b20","doi-asserted-by":"crossref","first-page":"2806","DOI":"10.1109\/TPAMI.2020.3045007","article-title":"A review on deep learning techniques for video prediction","volume":"44","author":"Oprea","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jocs.2026.102917_b21","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.jocs.2026.102917_b22","unstructured":"W. Yu, Y. Lu, S. Easterbrook, S. Fidler, Efficient and information-preserving future frame prediction and beyond, in: International Conference on Learning Representations, 2020."},{"key":"10.1016\/j.jocs.2026.102917_b23","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.jocs.2026.102917_b24","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jocs.2026.102917_b25","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al., An image is worth 16x16 words: Transformers for image recognition at scale, 2020, arXiv preprint arXiv:2010.11929."},{"key":"10.1016\/j.jocs.2026.102917_b26","series-title":"Deep learning and foundation models for weather prediction: A survey","author":"Shi","year":"2025"},{"issue":"2","key":"10.1016\/j.jocs.2026.102917_b27","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1109\/TBDATA.2024.3378061","article-title":"Spatio-temporal transformer network for weather forecasting","volume":"11","author":"Ji","year":"2024","journal-title":"IEEE Trans. Big Data"},{"key":"10.1016\/j.jocs.2026.102917_b28","series-title":"SEA-ViT: Sea surface currents forecasting using vision transformer and GRU-Based Spatio-Temporal covariance modeling","author":"Panboonyuen","year":"2024"},{"issue":"9","key":"10.1016\/j.jocs.2026.102917_b29","doi-asserted-by":"crossref","first-page":"5521","DOI":"10.3390\/app13095521","article-title":"Comparing vision transformers and convolutional neural networks for image classification: A literature review","volume":"13","author":"Maur\u00edcio","year":"2023","journal-title":"Appl. Sci."},{"key":"10.1016\/j.jocs.2026.102917_b30","article-title":"Transformers for vision: A survey on innovative methods for computer vision","author":"Hassija","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.jocs.2026.102917_b31","article-title":"A physics-embedded transformer-CNN architecture for data-driven turbulence prediction and surrogate modeling of high-fidelity fluid dynamics","author":"Ghosh","year":"2025","journal-title":"Eur. J. Mech. B Fluids"},{"key":"10.1016\/j.jocs.2026.102917_b32","series-title":"Minimalist traffic prediction: Linear layer is all you need","author":"Duan","year":"2023"},{"issue":"1","key":"10.1016\/j.jocs.2026.102917_b33","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1007\/s10916-024-02105-8","article-title":"Comparison of vision transformers and convolutional neural networks in medical image analysis: A systematic review","volume":"48","author":"Takahashi","year":"2024","journal-title":"J. Med. Syst."},{"key":"10.1016\/j.jocs.2026.102917_b34","series-title":"Aurora: A foundation model of the atmosphere","author":"Bodnar","year":"2024"},{"key":"10.1016\/j.jocs.2026.102917_b35","series-title":"Your transformer is secretly linear","author":"Razzhigaev","year":"2024"},{"key":"10.1016\/j.jocs.2026.102917_b36","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.neunet.2017.07.002","article-title":"Error bounds for approximations with deep ReLU networks","volume":"94","author":"Yarotsky","year":"2017","journal-title":"Neural Netw."},{"key":"10.1016\/j.jocs.2026.102917_b37","first-page":"69819","article-title":"Openstl: A comprehensive benchmark of spatio-temporal predictive learning","volume":"36","author":"Tan","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"11","key":"10.1016\/j.jocs.2026.102917_b38","doi-asserted-by":"crossref","DOI":"10.1029\/2020MS002203","article-title":"WeatherBench: a benchmark data set for data-driven weather forecasting","volume":"12","author":"Rasp","year":"2020","journal-title":"J. Adv. Model. Earth Syst."},{"key":"10.1016\/j.jocs.2026.102917_b39","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"},{"issue":"1","key":"10.1016\/j.jocs.2026.102917_b40","doi-asserted-by":"crossref","first-page":"21740","DOI":"10.3402\/tellusa.v65i0.21740","article-title":"The role of model and initial condition error in numerical weather forecasting investigated with an observing system simulation experiment","volume":"65","author":"Priv\u00e9","year":"2013","journal-title":"Tellus A: Dyn. Meteorol. Ocean.","ISSN":"https:\/\/id.crossref.org\/issn\/1600-0870","issn-type":"print"},{"issue":"16","key":"10.1016\/j.jocs.2026.102917_b41","doi-asserted-by":"crossref","first-page":"8814","DOI":"10.1002\/jgrd.50682","article-title":"A novel approach to improve numerical weather prediction skills by using anomaly integration and historical data","volume":"118","author":"Peng","year":"2013","journal-title":"J. Geophys. Res.: Atmospheres"},{"key":"10.1016\/j.jocs.2026.102917_b42","doi-asserted-by":"crossref","DOI":"10.1007\/s00376-021-0215-y","article-title":"A deep learning method for bias correction of ECMWF 24\u2013240 h forecasts","volume":"38","author":"Han","year":"2021","journal-title":"Adv. Atmospheric Sci."},{"issue":"758","key":"10.1016\/j.jocs.2026.102917_b43","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1002\/qj.4596","article-title":"Investigating transformer-based models for spatial downscaling and correcting biases of near-surface temperature and wind-speed forecasts","volume":"150","author":"Zhong","year":"2024","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"10.1016\/j.jocs.2026.102917_b44","series-title":"WeatherGNN: Exploiting complicated relationships in numerical weather prediction bias correction","author":"Wu","year":"2023"},{"key":"10.1016\/j.jocs.2026.102917_b45","doi-asserted-by":"crossref","DOI":"10.3389\/feart.2021.698876","article-title":"The Copernicus global 1\/12 oceanic and sea ice GLORYS12 reanalysis","volume":"9","author":"Jean-Michel","year":"2021","journal-title":"Front. Earth Sci."},{"issue":"3","key":"10.1016\/j.jocs.2026.102917_b46","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1016\/j.pocean.2009.07.005","article-title":"Circulation and multiple-scale variability in the Southern California bight","volume":"82","author":"Dong","year":"2009","journal-title":"Prog. Oceanogr."},{"key":"10.1016\/j.jocs.2026.102917_b47","series-title":"California Cooperative Oceanic Fisheries Investigations Report","first-page":"129","article-title":"Long-term trends of interannual variability in the California Current System","author":"Lluch-Belda","year":"2001"},{"key":"10.1016\/j.jocs.2026.102917_b48","doi-asserted-by":"crossref","first-page":"11","DOI":"10.3354\/meps139011","article-title":"Ocean warming and long-term change in pelagic bird abundance within the california current system","volume":"139","author":"Veit","year":"1996","journal-title":"Mar. Ecol. Prog. Ser."},{"key":"10.1016\/j.jocs.2026.102917_b49","article-title":"Product user manual for osi saf global sea ice concentration","author":"Tonboe","year":"2016","journal-title":"Dan. Meteorol. Inst.: Cph. Den."},{"key":"10.1016\/j.jocs.2026.102917_b50","series-title":"Ncep gfs 0. 25 degree global forecast grids historical archive","author":"NOAA\/NWS\/NCEP","year":"2015"},{"issue":"730","key":"10.1016\/j.jocs.2026.102917_b51","doi-asserted-by":"crossref","first-page":"1999","DOI":"10.1002\/qj.3803","article-title":"The ERA5 global reanalysis","volume":"146","author":"Hersbach","year":"2020","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"10.1016\/j.jocs.2026.102917_b52","series-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","volume":"Vol. 9351","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.jocs.2026.102917_b53","series-title":"Proceedings of the 2019 Conference of the North","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.jocs.2026.102917_b54","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.jocs.2026.102917_b55","series-title":"Vision transformer for small-size datasets","author":"Lee","year":"2021"},{"key":"10.1016\/j.jocs.2026.102917_b56","series-title":"Large batch training of convolutional networks","author":"You","year":"2017"},{"key":"10.1016\/j.jocs.2026.102917_b57","series-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"10.1016\/j.jocs.2026.102917_b58","series-title":"Umap: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018"}],"container-title":["Journal of Computational Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877750326001353?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1877750326001353?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T12:42:15Z","timestamp":1781786535000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1877750326001353"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":58,"alternative-id":["S1877750326001353"],"URL":"https:\/\/doi.org\/10.1016\/j.jocs.2026.102917","relation":{},"ISSN":["1877-7503"],"issn-type":[{"value":"1877-7503","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Exploring the limitations of transformer models for metocean forecasting","name":"articletitle","label":"Article Title"},{"value":"Journal of Computational Science","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jocs.2026.102917","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"102917"}}