An official website of the United States government
Abstract While data-driven approaches demonstrate great potential in atmospheric modeling and weather forecasting, ocean modeling poses distinct challenges due to complex bathymetry, land, vertical structure, and flow non-linearity. This study introduces OceanNet, a principled neural operator-based digital twin for regional sea-suface height emulation. OceanNet uses a Fourier neural operator and predictor-evaluate-corrector integration scheme to mitigate autoregressive error growth and enhance stability over extended time scales. A spectral regularizer counteracts spectral bias at smaller scales. OceanNet is applied to the northwest Atlantic Ocean western boundary current (the Gulf Stream), focusing on the task of seasonal prediction for Loop Current eddies and the Gulf Stream meander. Trained using historical sea surface height (SSH) data, OceanNet demonstrates competitive forecast skill compared to a state-of-the-art dynamical ocean model forecast, reducing computation by 500,000 times. These accomplishments demonstrate initial steps for physics-inspired deep neural operators as cost-effective alternatives to high-resolution numerical ocean models.
more »
« less
This content will become publicly available on July 1, 2026
Long-Term Predictions of Loop Current Eddy Evolutions Using OceanNet: A Fourier Neural Operator–Based Data-Driven Ocean Emulator
Abstract Circulation in the Gulf of Mexico is dominated by the Loop Current and associated mesoscale eddies. These mesoscale eddies pose a safety risk to offshore energy production and potential dispersal of large-scale pollutants like oil. We use a data-driven, physics-informed, and numerically consistent deep learning–based ocean emulator called OceanNet to generate a 120-day forecast of the sea surface height (SSH) in the eastern Gulf of Mexico. OceanNet uses a new dataset of high-resolution data assimilative ocean reanalysis (1993–2022) as input. This model is trained using years 1993–2018 and evaluated on four eddies during years 2019–21. For comparison, we use a state-of-the-art numerical ocean model to generate a dynamical model prediction initialized every 5 days from 27 April 2019 to 1 April 2020 (during eddies Sverdrup and Thor) using persistent forcing and boundary conditions. The dynamical model takes seven wall-clock days to run, whereas OceanNet runs in minutes. Edges of Loop Current eddies (LCEs) pose the most potent risk to offshore energy operations and pollutant dispersal due to strong water velocities. Therefore, most of the analysis focuses on edge accuracy, quantified by the modified Hausdorff distance. The edge of the LCEs is defined by the 17-cm sea surface height contour, which generally coincides with the strongest water velocity. The OceanNet prediction outperforms both persistence and the dynamical model prediction. Overall, this new ocean emulator provides a promising new approach to generate seasonal forecasts of LCEs and generates large model ensembles efficiently to quantify forecast uncertainty that is long needed by scientists and decision-makers for offshore operations. Significance StatementCirculation in the Gulf of Mexico (GoM) is dominated by the energetic Loop Current and associated mesoscale eddies (typically 150–400 km in diameter). As these eddies propagate westward through the Gulf, they pose a safety risk to offshore energy production and potential large-scale pollutant dispersal. We used ocean model output (1993–2022) to train a data-driven ocean emulator called OceanNet that generates a seasonal (up to 120 day) prediction of sea surface height (SSH) in the eastern GoM. For comparison, a simple dynamical model prediction is also evaluated. OceanNet’s performance is assessed with a focus on edge accuracy, the most potent risk to offshore energy operations and pollutant dispersal. Overall, OceanNet performs well for a seasonal forecast and shows great potential for further development.
more »
« less
- Award ID(s):
- 2331908
- PAR ID:
- 10633100
- Publisher / Repository:
- AMS
- Date Published:
- Journal Name:
- Artificial Intelligence for the Earth Systems
- Volume:
- 4
- Issue:
- 3
- ISSN:
- 2769-7525
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Internal tides (ITs) play a critical role in ocean mixing, and have strong signatures in ocean observations. Here, global IT sea surface height (SSH) in nadir altimetry is compared with an ocean forecast model that assimilates de‐tided SSH from nadir altimetry. The forecast model removes IT SSH variance from nadir altimetry at skill levels comparable to those achieved with empirical analysis of nadir altimetry. Accurate removal of IT SSH is needed to fully reveal lower‐frequency mesoscale eddies and currents in altimeter data. Analysis windows of order 30–120 days, made possible by the frequent (hourly) outputs of the forecast model, remove more IT SSH variance than longer windows. Forecast models offer a promising new approach for global internal tide mapping and altimetry correction. Because they provide information on the full water column, forecast models can also help to improve understanding of the underlying dynamics of ITs.more » « less
-
According to the National Academies, a week long forecast of velocity, vertical structure, and duration of the Loop Current (LC) and its eddies at a given location is a critical step toward understanding their effects on the gulf ecosystems as well as toward anticipating and mitigating the outcomes of anthropogenic and natural disasters in the Gulf of Mexico (GoM). However, creating such a forecast has remained a challenging problem since LC behavior is dominated by dynamic processes across multiple time and spatial scales not resolved at once by conventional numerical models. In this paper, building on the foundation of spatiotemporal predictive learning in video prediction, we develop a physics informed deep learning based prediction model called—Physics-informed Tensor-train ConvLSTM (PITT-ConvLSTM)—for forecasting 3D geo-spatiotemporal sequences. Specifically, we propose (1) a novel 4D higher-order recurrent neural network with empirical orthogonal function analysis to capture the hidden uncorrelated patterns of each hierarchy, (2) a convolutional tensor-train decomposition to capture higher-order space-time correlations, and (3) a mechanism that incorporates prior physics from domain experts by informing the learning in latent space. The advantage of our proposed approach is clear: constrained by the law of physics, the prediction model simultaneously learns good representations for frame dependencies (both short-term and long-term high-level dependency) and inter-hierarchical relations within each time frame. Experiments on geo-spatiotemporal data collected from the GoM demonstrate that the PITT-ConvLSTM model can successfully forecast the volumetric velocity of the LC and its eddies for a period greater than 1 week.more » « less
-
A divide-and-conquer (DAC) machine learning approach was first proposed by Wang et al. to forecast the sea surface height (SSH) of the Loop Current System (LCS) in the Gulf of Mexico. In this DAC approach, the forecast domain was divided into non-overlapping partitions, each of which had their own prediction model. The full domain SSH prediction was recovered by interpolating the SSH across each partition boundaries. Although the original DAC model was able to predict the LCS evolution and eddy shedding more than two months and three months in advance, respectively, growing errors at the partition boundaries negatively affected the model forecasting skills. In the study herein, a new partitioning method, which consists of overlapping partitions is presented. The region of interest is divided into 50%-overlapping partitions. At each prediction step, the SSH value at each point is computed from overlapping partitions, which significantly reduces the occurrence of unrealistic SSH features at partition boundaries. This new approach led to a significant improvement of the overall model performance both in terms of features prediction such as the location of the LC eddy SSH contours but also in terms of event prediction, such as the LC ring separation. We observed an approximate 12% decrease in error over a 10-week prediction, and also show that this method can approximate the location and shedding of eddy Cameron better than the original DAC method.more » « less
-
Abstract Western Atlantic bluefin tuna (ABT) undertake long-distance migrations from rich feeding grounds in the North Atlantic to spawn in oligotrophic waters of the Gulf of Mexico (GoM). Stock recruitment is strongly affected by interannual variability in the physical features associated with ABT larvae, but the nutrient sources and food-web structure of preferred habitat, the edges of anticyclonic loop eddies, are unknown. Here, we describe the goals, physical context, design and major findings of an end-to-end process study conducted during peak ABT spawning in May 2017 and 2018. Mesoscale features in the oceanic GoM were surveyed for larvae, and five multi-day Lagrangian experiments measured hydrography and nutrients; plankton biomass and composition from bacteria to zooplankton and fish larvae; phytoplankton nutrient uptake, productivity and taxon-specific growth rates; micro- and mesozooplankton grazing; particle export; and ABT larval feeding and growth rates. We provide a general introduction to the BLOOFINZ-GoM project (Bluefin tuna Larvae in Oligotrophic Ocean Foodwebs, Investigation of Nitrogen to Zooplankton) and highlight the finding, based on backtracking of experimental waters to their positions weeks earlier, that lateral transport from the continental slope region may be more of a key determinant of available habitat utilized by larvae than eddy edges per se.more » « less
