A deep learning global ocean forecasting model with sub-daily and eddy-resolving resolution
10 affiliations
- 1School of Marine Science and Technology, Tianjin University, Tianjin, China
- 2Shanghai Academy of Artificial Intelligence for Science, Shanghai, China
- 3Artificial Intelligence Innovation and Incubation Institute , Fudan University, Shanghai, China
- 4Shanghai Innovation Institute, Shanghai, China
- 5FuXi Intelligent Computing Technology Co. Ltd, Shanghai, China
- 6Department of Atmospheric and Oceanic Sciences and Institute of Atmospheric Sciences, Fudan University, Shanghai, China
- 7Institute for Big Data, Fudan University, Shanghai, China
- 8MOE Laboratory for National Development and Intelligent Governance, Fudan University, Shanghai, China
- 9School of Data Science, Fudan University, Shanghai, China
- 10Yazhou Bay Innovation Institute, College of Marine Science and Technology, Hainan Tropical Ocean University, Sanya, China
Abstract
Accurate and physically realistic ocean forecasting at high spatial and temporal resolution is essential for resolving fine-scale dynamical features, with profound implications for hazard prediction, maritime navigation, and sustainable ocean management. Conventional numerical models can produce sub-daily, eddy-resolving forecasts but require substantial computational resources and often struggle to maintain predictive skill at such fine scales. Deep learning offers a promising alternative with significantly higher computational efficiency. However, most existing models operate at daily resolution, averaging out sub-daily variability and thus struggling to learn the complex and diverse diurnal cycle characteristics across different variables and depth layers. This limits their ability to capture rapidly evolving ocean processes, and they remain heavily dependent on atmospheric forcing from numerical weather prediction (NWP) models. Here, we introduce FuXi-Ocean, a global deep learning-based ocean forecasting model that generates 6-hourly predictions at 1/12 ∘ mesoscale-eddy-resolving resolution, extending to 1500 m depth. Unlike previous approaches, FuXi-Ocean operates independently of NWP forecasts, using near-surface atmospheric variables only for initialization, thereby establishing a fully independent, coupled ocean-atmosphere prediction framework. The model adaptively integrates forecasts across multiple temporal windows, capturing variable-specific evolution rates in ocean dynamics, while effectively addressing the technical challenge of cumulative error amplification in autoregressive forecasting. Through its innovative architectural design, FuXi-Ocean maintains stable predictive performance despite requiring four times more autoregressive steps than daily-resolution models. Based on our evaluation for 2022, FuXi-Ocean demonstrates improved performance over the latest deep learning-based GOFS (WenHai) in 10-day forecasts of temperature, salinity, zonal and meridional currents, sea surface temperature, and sea level anomaly. By advancing global ocean forecasts from daily to sub-daily resolution through independent deep learning-based ocean-atmospheric coupling, FuXi-Ocean represents a significant step forward in high-resolution ocean prediction.
Related
- OceanForecastBench: A Benchmark Data Set for Data‐Driven Global Ocean Forecasting
- LangYa: a large AI model for global ocean forecasting
- Learning native eddy-resolving ocean dynamics outperforms coarse emulation and downscaling
- Towards high-resolution forecasting of tropical deforestation with deep learning
- From objective discovery to prediction of global ocean eco-provinces: A pathway for trustworthy learning
BibTeX
@article{niu2026deep,
title = {{A deep learning global ocean forecasting model with sub-daily and eddy-resolving resolution}},
author = {Yuan Niu and Qiusheng Huang and Xiaohui Zhong and Anboyu Guo and Lei Chen and Dianjun Zhang and Z Zhou and Xiaoyan Jia and Libo Wu and Renhe Zhang and Jiawei Qi and Xuefeng Zhang and Hui Li},
journal = {npj Climate and Atmospheric Science},
year = {2026},
month = may,
doi = {10.1038/s41612-026-01444-2},
url = {https://doi.org/10.1038/s41612-026-01444-2},
note = {CC BY},
}
RIS
TY - JOUR
TI - A deep learning global ocean forecasting model with sub-daily and eddy-resolving resolution
AU - Yuan Niu
AU - Qiusheng Huang
AU - Xiaohui Zhong
AU - Anboyu Guo
AU - Lei Chen
AU - Dianjun Zhang
AU - Z Zhou
AU - Xiaoyan Jia
AU - Libo Wu
AU - Renhe Zhang
AU - Jiawei Qi
AU - Xuefeng Zhang
AU - Hui Li
PY - 2026
DA - 2026/05/30
JO - npj Climate and Atmospheric Science
DO - 10.1038/s41612-026-01444-2
UR - https://doi.org/10.1038/s41612-026-01444-2
AB - Accurate and physically realistic ocean forecasting at high spatial and temporal resolution is essential for resolving fine-scale dynamical features, with profound implications for hazard prediction, maritime navigation, and sustainable ocean management. Conventional numerical models can produce sub-daily, eddy-resolving forecasts but require substantial computational resources and often struggle to maintain predictive skill at such fine scales. Deep learning offers a promising alternative with significantly higher computational efficiency. However, most existing models operate at daily resolution, averaging out sub-daily variability and thus struggling to learn the complex and diverse diurnal cycle characteristics across different variables and depth layers. This limits their ability to capture rapidly evolving ocean processes, and they remain heavily dependent on atmospheric forcing from numerical weather prediction (NWP) models. Here, we introduce FuXi-Ocean, a global deep learning-based ocean forecasting model that generates 6-hourly predictions at 1/12 ∘ mesoscale-eddy-resolving resolution, extending to 1500 m depth. Unlike previous approaches, FuXi-Ocean operates independently of NWP forecasts, using near-surface atmospheric variables only for initialization, thereby establishing a fully independent, coupled ocean-atmosphere prediction framework. The model adaptively integrates forecasts across multiple temporal windows, capturing variable-specific evolution rates in ocean dynamics, while effectively addressing the technical challenge of cumulative error amplification in autoregressive forecasting. Through its innovative architectural design, FuXi-Ocean maintains stable predictive performance despite requiring four times more autoregressive steps than daily-resolution models. Based on our evaluation for 2022, FuXi-Ocean demonstrates improved performance over the latest deep learning-based GOFS (WenHai) in 10-day forecasts of temperature, salinity, zonal and meridional currents, sea surface temperature, and sea level anomaly. By advancing global ocean forecasts from daily to sub-daily resolution through independent deep learning-based ocean-atmospheric coupling, FuXi-Ocean represents a significant step forward in high-resolution ocean prediction.
SN - 2397-3722
ER -