Articles | Volume 21, issue 3
https://doi.org/10.5194/os-21-1065-2025
https://doi.org/10.5194/os-21-1065-2025
Research article
 | Highlight paper
 | 
20 Jun 2025
Research article | Highlight paper |  | 20 Jun 2025

Long-term prediction of the Gulf Stream meander using OceanNet: a principled neural-operator-based digital twin

Michael Gray, Ashesh Chattopadhyay, Tianning Wu, Anna Lowe, and Ruoying He

Related authors

Predicting ocean waves along the US east coast during energetic winter storms: sensitivity to whitecapping parameterizations
Mohammad Nabi Allahdadi, Ruoying He, and Vincent S. Neary
Ocean Sci., 15, 691–715, https://doi.org/10.5194/os-15-691-2019,https://doi.org/10.5194/os-15-691-2019, 2019
Short summary
Modeling pCO2 variability in the Gulf of Mexico
Zuo Xue, Ruoying He, Katja Fennel, Wei-Jun Cai, Steven Lohrenz, Wei-Jen Huang, Hanqin Tian, Wei Ren, and Zhengchen Zang
Biogeosciences, 13, 4359–4377, https://doi.org/10.5194/bg-13-4359-2016,https://doi.org/10.5194/bg-13-4359-2016, 2016
Short summary
Impacts of air–sea interactions on regional air quality predictions using WRF/Chem v3.6.1 coupled with ROMS v3.7: southeastern US example
J. He, R. He, and Y. Zhang
Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmdd-8-9965-2015,https://doi.org/10.5194/gmdd-8-9965-2015, 2015
Revised manuscript not accepted
Short summary
Mean circulation in the coastal ocean off northeastern North America from a regional-scale ocean model
K. Chen and R. He
Ocean Sci., 11, 503–517, https://doi.org/10.5194/os-11-503-2015,https://doi.org/10.5194/os-11-503-2015, 2015
Modeling ocean circulation and biogeochemical variability in the Gulf of Mexico
Z. Xue, R. He, K. Fennel, W.-J. Cai, S. Lohrenz, and C. Hopkinson
Biogeosciences, 10, 7219–7234, https://doi.org/10.5194/bg-10-7219-2013,https://doi.org/10.5194/bg-10-7219-2013, 2013

Related subject area

Approach: Numerical Models | Properties and processes: Mesoscale to submesoscale dynamics
Sensitivity of gyre-scale marine connectivity estimates to fine-scale circulation
Saeed Hariri, Sabrina Speich, Bruno Blanke, and Marina Lévy
Ocean Sci., 19, 1183–1201, https://doi.org/10.5194/os-19-1183-2023,https://doi.org/10.5194/os-19-1183-2023, 2023
Short summary

Cited articles

Agarwal, N., Kondrashov, D., Dueben, P., Ryzhov, E., and Berloff, P.: A comparison of data-driven approaches to build low-dimensional ocean models, J. Adv. Model. Earth Sy., 13, e2021MS002537, https://doi.org/10.1029/2021MS002537, 2021. a
Bi, K., Xie, L., Zhang, H., Chen, X., Gu, X., and Tian, Q.: Accurate medium-range global weather forecasting with 3D neural networks, Nature, 619, 533–538, https://doi.org/10.1038/s41586-023-06185-3, 2023. a, b, c, d
Chassignet, E. P. and Marshall, D. P.: Gulf Stream Separation in Numerical Ocean Models, Wiley, 39–61, https://doi.org/10.1029/177GM05, 2008. a, b
Chassignet, E. P. and Xu, X.: Impact of horizontal resolution (1/12° to 1/50°) on Gulf Stream separation, penetration, and variability, J. Phys. Oceanogr., 47, 1999–2021, https://doi.org/10.1175/JPO-D-17-0031.1, 2017. a
Chattopadhyay, A. and Hassanzadeh, P.: Long-term instabilities of deep learning-based digital twins of the climate system: the cause and a solution, arXiv [preprint], https://doi.org/10.48550/arXiv.2304.07029 2023. a, b, c, d, e, f, g, h, i, j, k, l
Download
Co-editor-in-chief
The use of neural networks to emulate the dynamics of the Earth system (ocean, atmosphere) is of critical importance since it enables efficient and operational forecast, data assimilation, and affordable uncertainty quantification. This field has been very productive in numerical weather forecasts but relatively fewer results were demonstrated in the oceans. This paper could be a reference for mesoscale ocean dynamics emulation.
Short summary
The Gulf Stream is a prominent oceanic feature in the northwestern Atlantic Ocean that influences weather patterns in the Northern Hemisphere and is notoriously difficult to predict. We present a machine learning model, OceanNet, to predict the position of the Gulf Stream months in advance. OceanNet is able to perform a 120 d prediction 4 000 000 times faster than traditional methods of ocean modeling with great accuracy.
Share