Application of intelligent correction in ocean numerical forecasting based on spatiotemporal convolutional network (STCN)

Abstract

Marine numerical forecasting is susceptible to complex spatiotemporal systematic errors, particularly during extreme weather events, such as typhoons, which majorly impede its efficacy in disaster prevention and mitigation. To address this challenge, the present study proposes an intelligent correction model based on a spatiotemporal convolutional network. A decoupled convolutional design that separates temporal and spatial dimensions is employed, enabling hierarchical parallel extraction and deep synergistic fusion of spatiotemporal error features from multivariable forecast fields. The experimental validation was conducted using multisource data acquired from the northern South China Sea from November 2023 to September 2025. The findings indicate that the proposed model has a substantial impact on enhancing the precision of critical variables, including sea surface temperature, sea surface elevation, and wave height. Specifically, the root mean square error (RMSE) of sea surface temperature decreased by an average of 23.8%, and the RMSE of wave height decreased by up to 24.0% under typhoon conditions. The spatiotemporal convolutional network (STCN) model has been demonstrated to enhance the spatial structure of typhoon-induced ocean responses and improve extreme value predictions in case studies of Typhoons Mitag and Ragasa in 2025. These enhancements contribute to an increased physical plausibility of the forecast fields. The present study corroborates the STCN model’s superiority in addressing systematic errors in numerical oceanic forecasts, particularly in the context of extreme weather events. It offers a reliable data-driven approach to enhance the overall accuracy of operational ocean forecasting.

Keywords

Spatiotemporal convolutional network (STCN) / Ocean numerical forecasting / Intelligent correction / Multivariable joint correction / Typhoon

References

[1] Alahi A, Goel K, Ramanathan V, Robicquet A, Li FF, Savarese S (2016) Social LSTM: human trajectory prediction in crowded spaces. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 961–971. https://doi.org/10.1109/CVPR.2016.110

[2] Burnett W, Harper S, Preller R, Jacobs G, LaCroix K. Overview of operational ocean forecasting in the US Navy: past, present, and future. Oceanography, 2014, 2732431.

[3] Chao YH, Hsu MK, Chen HW, Wang YH, Chen GY, Liu CT. Sieving nonlinear internal waves through path prediction. Int J Remote Sens, 2008, 292163916402.

[4] Chen HZ, Xing XF, Xu XM (2020) Learning spatio-temporal convolutional network for real-time object tracking. In: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 2153–2157. https://doi.org/10.1109/ICASSP40776.2020.9054757

[5] Fang JJ, Li XJ, Li J, Huang ZA, Yu YQ, Huang XM, et al. Physically constrained adaptive deep learning for ocean vertical-mixing parameterization. Adv Atmos Sci, 2024, 42: 165-177.

[6] Gharamti ME, Ait-El-Fquih B, Hoteit I. An iterative ensemble Kalman filter with one-step-ahead smoothing for state-parameters estimation of contaminant transport models. J Hydrol, 2015, 527: 442-457.

[7] Kumar P, Quraishi A, Rusho MA, Raparthi M, Degadwala S (2025) Enhancing video action recognition with spatial–temporal convolutional attention networks. In: Ghinea G et al (eds) Intelligent computing and networking. IC-ICN 2024. Lecture notes in networks and systems, vol 1172. Springer, Singapore, pp 149–168. https://doi.org/10.1007/978-981-97-8631-2_9

[8] Lazić L, Pejanović G, Živković M, Ilić L. Improved wind forecasts for wind power generation using the Eta model and MOS (model output statistics) method. Energy, 2014, 73: 567-574.

[9] Lea C, Flynn MD, Vidal R, Reiter A, Hager GD (2017) Temporal convolutional networks for action segmentation and detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 1003–1012. https://doi.org/10.1109/CVPR.2017.113

[10] LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE, 1998, 861122782324.

[11] LeCun Y, Bottou L, Orr GB, Müller KR. Orr GB. Efficient backprop. Neural networks: tricks of the trade, 1998, Berlin: Springer, 9-50.

[12] Li XJ, Lu WL. Particle network EnKF for large-scale data assimilation. Front Phys, 2022, 10. 998503

[13] Lin YD, Zhong GQ. A multi-channel LSTM model for sea surface temperature prediction. J Phys-Conf Ser, 2021, 1880. 012029

[14] Liu SK, Liu K, Wang Z, Liu YY, Bai B, Zhao R. Investigation of a transformer-based hybrid artificial neural networks for climate data prediction and analysis. Front Environ Sci, 2025, 12. 1464241

[15] Nerini D, Foresti L, Leuenberger D, Robert S, Germann U. A reduced-space ensemble Kalman filter approach for flow-dependent integration of radar extrapolation nowcasts and NWP precipitation ensembles. Mon Weather Rev, 2019, 14739871006.

[16] Shalabi LA, Shaaban Z, Kasasbeh B. Data mining: a preprocessing engine. J Comput Sci, 2006, 29735739.

[17] Shi BY, Hao YJ, Feng L, Ge CH, Peng Y, He HL. An attention-based context fusion network for spatiotemporal prediction of sea surface temperature. IEEE Geosci Remote Sens Lett, 2024, 21: 1504405.

[18] Simmons HL, Chang MH, Chang YT, Chao SY, Fringer O, Jackson CR, et al. Modeling and prediction of internal waves in the South China Sea. Oceanography, 2011, 24498107.

[19] Spiridonov V, Ćurić M. Weather forecast and NWP. Fundamentals of meteorology, 2021, Cham: Springer, 349-376.

[20] Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (2015) Learning spatiotemporal features with 3D convolutional networks. In: 2015 IEEE International Conference on Computer Vision (ICCV). IEEE, pp 4489–4497. https://doi.org/10.1109/ICCV.2015.510

[21] Trouw K, Zimmermann N, Mathys M, Delgado R, Roelvink D (2012) Numerical modelling of hydrodynamics and sediment transport in the surf zone: a sensitivity study with different types of numerical models. In: International Conference on Coastal Engineering (ICCE 2012). Coastal Engineering Research Council, pp 1–11. https://doi.org/10.9753/icce.v33.sediment.23

[22] Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN et al (2017) Attention is all you need. Preprint at arXiv:1706.03762

[23] Wang Z, Bovik AC. Mean squared error: love it or leave it?. IEEE Signal Process Mag, 2009, 26198117.

[24] Yang XH, Sun SW, Liu MZ. Adaptive multi-scale spatio-temporal convolutional network with reinforcement learning for dynamic lane-level traffic flow prediction. Array, 2025, 28. 100513

[25] Yang YT, Dong JY, Sun X, Lima E, Mu QQ, Wang XH. A CFCC-LSTM model for sea surface temperature prediction. IEEE Geosci Remote Sens Lett, 2018, 152207211.

Rights & permissions

The Author(s)