An official website of the United States government
Abstract. Many meteorological and oceanographic processes throughout the eastern United States and western Atlantic Ocean, such as storm tracks and shelf water transport, are influenced by the position and warm sea surface temperature of the Gulf Stream (GS)- the region's western boundary current. Due to highly nonlinear processes associated with the GS, predicting its meanders and frontal position have been long-standing challenges within the numerical modeling community. While the weather and climate modeling communities have begun to turn to data-driven machine learning frameworks to overcome analogous challenges, there has been less exploration of such models in oceanography. Using a new dataset from a high-resolution data-assimilative ocean reanalysis (1993–2022) for the Northwest Atlantic Ocean, OceanNet (a neural operator-based digital twin for regional oceans) was trained to identify and track the GS’s frontal position over subseasonal-to-seasonal timescales. Here we present the architecture of OceanNet and the advantages it holds over other machine learning frameworks explored during development while demonstrating predictions of the Gulf Stream Meander are physically reasonable over at least a 60-day period and remain stable for longer.
more »
« less
This content will become publicly available on January 1, 2026
Long-term prediction of the Gulf Stream meander using OceanNet: a principled neural-operator-based digital twin
Abstract. Many meteorological and oceanographic processes throughout the eastern US and western Atlantic Ocean, such as storm tracks and shelf water transport, are influenced by the position and warm sea surface temperature of the Gulf Stream (GS) – the region's western boundary current. Due to highly nonlinear processes associated with the GS, predicting its meanders and frontal position has been a long-standing challenge within the numerical modeling community. Although the weather and climate modeling communities have begun to turn to data-driven machine learning frameworks to overcome analogous challenges, there has been less exploration of such models in oceanography. Using a new dataset from a high-resolution data-assimilative ocean reanalysis (1993–2022) for the northwestern Atlantic Ocean, OceanNet (a neural-operator-based digital twin for regional oceans) was trained to predict the GS's frontal position over subseasonal to seasonal timescales. Here, we present the architecture of OceanNet and the advantages it holds over other machine learning frameworks explored during development. We also demonstrate that predictions of the GS meander are physically reasonable over at least a 60 d period and remain stable for longer. OceanNet can generate a 120 d forecast of the GS meander within seconds, offering significant computational efficiency.
more »
« less
- Award ID(s):
- 2331908
- PAR ID:
- 10633099
- Publisher / Repository:
- EGU
- Date Published:
- Journal Name:
- Ocean Science
- Volume:
- 21
- Issue:
- 3
- ISSN:
- 1812-0792
- Page Range / eLocation ID:
- 1065 to 1080
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
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
-
The Caribbean Through-Flow (CTF) is a critical chokepoint for North and South Atlantic waters that form the North Atlantic western boundary current system and the upper ocean limb of the Atlantic Meridional Overturning Circulation. While the circulation and energetics of the CTF have been well studied, its water mass transformations remain poorly constrained. Using over 7700 Argo float profiles from 2014 to 2024, we document a prominent westward modification in water mass structure across the Caribbean Sea. From the eastern to western Caribbean, we observe systematic increases in ocean heat content, a deepening of isopycnals, and a freshening and deepening of the subsurface salinity maximum. These changes result in a net mid-depth (~50–500 m) density reduction of 0.40 ± 0.27 kg m-3. We hypothesize that regional variations in mesoscale eddy activity, complex bathymetry, and meridional wind stress curl gradients drive this transformation. The resulting water mass structure has critical implications for regional climate, weather, ecosystems, and sea level rise, as it modifies the density and stratification of source waters entering the Gulf of Mexico and North Atlantic western boundary current system. Our findings highlight the importance of internal Caribbean processes in shaping upper-ocean heat and salt transport in the Atlantic and underscore the need for sustained in situ observations in the region and targeted modeling analyses of the underlying modification processes.more » « less
-
Abstract After leaving the U.S. East Coast, the northward flowing Gulf Stream (GS) becomes a zonal jet and carries along its frontal characteristics of strong flow and sea surface temperature gradients into the North Atlantic at midlatitudes. The separation location where it leaves the coast is also an anchor point for the wintertime synoptic storm track across North America to continue to develop and head across the ocean. We examine the meridionalvariabilityof the separated GS path on interannual to decadal time scales as an agent for similar changes in the storm track and blocking variability at midtroposphere from 1979 to 2012. We find that periods of northerly (southerly) GS path are associated with increased (suppressed) excursions of the synoptic storm track to the northeast over the Labrador Sea and reduced (enhanced) Greenland blocking. In both instances, GS shifts lead those in the midtroposphere by a few months.more » « less
-
Abstract Marine-terminating glaciers on the Antarctic Peninsula (AP) have retreated, accelerated and thinned in response to climate change in recent decades. Ocean warming has been implicated as a trigger for these changes in glacier dynamics, yet little data exist near glacier termini to assess the role of ocean warming here. We use remotely-sensed iceberg melt rates seaward of two glaciers on the eastern and six glaciers on the western AP from 2013 to 2019 to explore connections between variations in ocean conditions and glacier frontal ablation. We find iceberg melt rates follow regional ocean temperature variations, with the highest melt rates (mean ≈ 10 cm d −1 ) at Cadman and Widdowson glaciers in the west and the lowest melt rates (mean ≈ 0.5 cm d −1 ) at Crane Glacier in the east. Near-coincident glacier frontal ablation rates from 2014 to 2018 vary from ~450 m a −1 at Edgeworth and Blanchard glaciers to ~3000 m a −1 at Seller Glacier, former Wordie Ice Shelf tributary. Variations in iceberg melt rates and glacier frontal ablation rates are significantly positively correlated around the AP (Spearman's ρ = 0.71, p -value = 0.003). We interpret this correlation as support for previous research suggesting submarine melting of glacier termini exerts control on glacier frontal dynamics around the AP.more » « less
