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 January 1, 2026
Using Digital Twins of the Ocean to Build Capacity in the Wider Caribbean Region
An emerging technology for building capacity to make decisions in the ocean space is the development of Digital Twins of the Ocean (DTOs). A DTO is a virtual replication of the ocean environment, including its properties, behaviors, and processes (https://www.mercator-ocean.eu/en/digital-twin-ocean/). These digital replicas are created using a combination of real-time data collected from satellites and thousands of sensors deployed around the world, as well as outputs of advanced models and computer simulations.
more »
« less
- Award ID(s):
- 2318309
- PAR ID:
- 10599681
- Publisher / Repository:
- The Oceanography Society
- Date Published:
- Journal Name:
- Oceanography
- ISSN:
- 1042-8275
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Seismic ocean thermometry uses sound waves generated by repeating earthquakes to measure temperature change in the deep ocean. In this study, waves generated by earthquakes along the Japan Trench and received at Wake Island are used to constrain temperature variations in the Kuroshio Extension region. This region is characterized by energetic mesoscale eddies and large decadal variability, posing a challenging sampling problem for conventional ocean observations. The seismic measurements are obtained from a hydrophone station off and a seismic station on Wake Island, with the seismic station's digital record reaching back to 1997. These measurements are combined in an inversion for the time and azimuth dependence of the range‐averaged deep temperatures, revealing lateral and temporal variations due to Kuroshio Extension meanders, mesoscale eddies, and decadal water mass displacements. These results highlight the potential of seismic ocean thermometry for better constraining the variability and trends in deep‐ocean temperatures. By overcoming the aliasing problem of point measurements, these measurements complement existing ship‐ and float‐based hydrographic measurements.more » « less
-
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
-
Abstract A growing body of literature argues that digital models do not just help organizational leaders to predict the future. Models can inadvertently produce the very future they purport to describe. In this view,performativityis a side-effect of digital modeling. But digital twins turn such thinking on its head. Digital twins are digital models that are designed to be performative—changes in the model are supposed to produce corresponding changes in the world the model represents. This is what makes digital twins useful. But for decision-makers to act in ways that align the world outside the model with the predictions contained within, they must first believe that the model is a faithful representation. In other words, for a digital twin to become performative, it must first be taken-for-granted as “real”. In this paper, we explore the technological and organizational characteristics that are likely to shape the level of taken-for-grantedness of a digital twin.more » « less
-
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
