skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: A Deep Learning Model for Forecasting Velocity Structures of the Loop Current System in the Gulf of Mexico
Despite the large efforts made by the ocean modeling community, such as the GODAE (Global Ocean Data Assimilation Experiment), which started in 1997 and was renamed as OceanPredict in 2019, the prediction of ocean currents has remained a challenge until the present day—particularly in ocean regions that are characterized by rapid changes in their circulation due to changes in atmospheric forcing or due to the release of available potential energy through the development of instabilities. Ocean numerical models’ useful forecast window is no longer than two days over a given area with the best initialization possible. Predictions quickly diverge from the observational field throughout the water and become unreliable, despite the fact that they can simulate the observed dynamics through other variables such as temperature, salinity and sea surface height. Numerical methods such as harmonic analysis are used to predict both short- and long-term tidal currents with significant accuracy. However, they are limited to the areas where the tide was measured. In this study, a new approach to ocean current prediction based on deep learning is proposed. This method is evaluated on the measured energetic currents of the Gulf of Mexico circulation dominated by the Loop Current (LC) at multiple spatial and temporal scales. The approach taken herein consists of dividing the velocity tensor into planes perpendicular to each of the three Cartesian coordinate system directions. A Long Short-Term Memory Recurrent Neural Network, which is best suited to handling long-term dependencies in the data, was thus used to predict the evolution of the velocity field in each plane, along each of the three directions. The predicted tensors, made of the planes perpendicular to each Cartesian direction, revealed that the model’s prediction skills were best for the flow field in the planes perpendicular to the direction of prediction. Furthermore, the fusion of all three predicted tensors significantly increased the overall skills of the flow prediction over the individual model’s predictions. The useful forecast period of this new model was greater than 4 days with a root mean square error less than 0.05 cm·s−1 and a correlation coefficient of 0.6.  more » « less
Award ID(s):
1828181
PAR ID:
10312467
Author(s) / Creator(s):
; ; ; ;
Date Published:
Journal Name:
Forecasting
Volume:
3
Issue:
4
ISSN:
2571-9394
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; (, Journal of geophysical research)
    null (Ed.)
    The Ocean State Ocean Model OSOM is an application of the Regional Ocean Modeling System spanning the Rhode Island waterways, including Narragansett Bay, Mt. Hope Bay, larger rivers, and the Block Island Shelf circulation from Long Island to Nantucket. This paper discusses the physical aspects of the estuary (Narragansett and Mount Hope Bays and larger rivers) to evaluate physical circulation predictability. This estimate is intended to help decide if a forecast and prediction system is warranted, to prepare for coupling with biogeochemistry and fisheries models with widely disparate timescales, and to find the spin-up time needed to establish the climatological circulation of the region. Perturbed initial condition ensemble simulations are combined with metrics from information theory to quantify the predictability of the OSOM forecast system--i.e., how long anomalies from different initial conditions persist. The predictability timescale in this model agrees with readily estimable timescales such as the freshwater flushing timescale evaluated using the total exchange flow (TEF) framework, indicating that the estuarine dynamics rather than chaotic transport is the dominant model behavior limiting predictions. The predictability of the OSOM is ~ 7 to 40 days, varying with parameters, region, and season. 
    more » « less
  2. ; ; ; ; (, Journal of Geophysical Research: Oceans)
    Abstract The Ocean State Ocean Model (OSOM) is an application of the Regional Ocean Modeling System spanning the Rhode Island waterways, including Narragansett Bay, Mt. Hope Bay, larger rivers, and the Block Island Shelf circulation from Long Island to Nantucket. This study discusses the physical aspects of the estuary (Narragansett and Mount Hope Bays and larger rivers) to evaluate physical circulation predictability. This estimate is intended to help decide if a forecast and prediction system is warranted, to prepare for coupling with biogeochemistry and fisheries models with widely disparate timescales, and to find the spin‐up time needed to establish the climatological circulation of the region. Perturbed initial condition ensemble simulations are combined with metrics from information theory to quantify the predictability of the OSOM forecast system–i.e., how long anomalies from different initial conditions persist. The predictability timescale in this model agrees with readily estimable timescales such as the freshwater flushing timescale evaluated using the total exchange flow (TEF) framework, indicating that the estuarine dynamics rather than chaotic transport is the dominant model behavior limiting predictions. The predictability of the OSOM is ∼7–40 days, varying with parameters, region, and season. 
    more » « less
  3. ; ; ; (, Frontiers in Earth Science)
    Analysis of the time-dependent behavior of the buoyant plume rising above Grotto Vent (Main Endeavour Field, Juan de Fuca Ridge) as imaged by the Cabled Observatory Vent Imaging Sonar (COVIS) between September 2010 and October of 2015 captures long term time-dependent changes in the direction of background bottom currents independent of broader oceanographic processes, indicating a systematic evolution in vent output along the Endeavour Segment of the Juan de Fuca Ridge. The behavior of buoyant plumes can be quantified by describing the volume, velocity, and orientation of the effluent relative to the seafloor, which are a convolved expression of hydrothermal flux from the seafloor and ocean bottom currents in the vicinity of the hydrothermal vent. We looked at the azimuth and inclination of the Grotto plume, which was captured in three-dimensional acoustic images by the COVIS system, at 3-h intervals during October 2010 and between October 2011 and December 2014. The distribution of plume azimuths shifts from bimodal NW and SW to SE in 2010, 2011, and 2012 to single mode NW in 2013 and 2014. Modeling of the distribution of azimuths for each year with a bimodal Gaussian indicates that the prominence of southward bottom currents decreased systematically between 2010 and 2014. Spectral analysis of the azimuthal data showed a strong semi-diurnal peak, a weak or missing diurnal peak, and some energy in the sub-inertial and weather bands. This suggests the dominant current generating processes are either not periodic (such as the entrainment fields generated by the hydrothermal plumes themselves) or are related to tidal processes. This prompted an investigation into the broader oceanographic current patterns. The surface wind patterns in buoy data at two sites in the Northeast Pacific and the incidence of sea-surface height changes related to mesoscale eddies show little systematic change over this time-period. The limited bottom current data for the Main Endeavour Field and other parts of the Endeavour Segment neither confirm nor refute our observation of a change in the bottom currents. We hypothesize that changes in venting either within the Main Endeavour Field or along the Endeavour Segment have resulted in the changes in background currents. Previous numerical simulations (Thomson et al., J. Geophys. Res., 2009, 114 (C9), C09020) showed that background bottom currents were more likely to be controlled by the local (segment-scale) venting than by outside ocean circulation or atmospheric patterns. 
    more » « less
  4. ; ; (, Scientific Reports)
    Abstract The surface-intensified, poleward-flowing Gulf Stream (GS) encounters the equatorward-flowing Deep Western Boundary Current (DWBC) at 36° N off Cape Hatteras. In this study, daily output from a data-assimilative, high-resolution (800 m), regional ocean reanalysis was examined to quantify variability in the velocity structure of the GS and DWBC during 2017–2018. The validity of this reanalysis was confirmed with independent observations of ocean velocity and density that demonstrate a high level of realism in the model’s representation of the regional circulation. The model’s daily velocity time series across a transect off Cape Hatteras was examined using rotated Empirical Orthogonal Function analysis, and analysis suggests three leading modes that characterize the variability of the western boundary currents throughout the water column. The first mode, related to meandering of the GS current, accounts for 55.3% of the variance, followed by a “wind-forced mode”, which accounts for 12.5% of the variance. The third mode, influenced by the DWBC and upper-ocean eddies, accounts for 7.1% of the variance. 
    more » « less
  5. ; ; ; ; (, Artificial Intelligence for the Earth Systems)
    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
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email