Abstract:

This dataset is the outcome of an ocean current prediction model based on deep learning method. This method was 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 four days, with a root mean square error less than 0.05 cm·s^−1 and a correlation coefficient of 0.6. This dataset supports this publication: Muhamed Ali, Ali, Hanqi Zhuang, James VanZwieten, Ali K. Ibrahim, and Laurent Chérubin. 2021. A Deep Learning Model for Forecasting Velocity Structures of the Loop Current System in the Gulf of Mexico. Forecasting 3, no. 4: 934-953. https://doi.org/10.3390/forecast3040056

Suggested Citation:

Muhamed Ali, Ali. 2024. Forecasting 3D velocity structures of the Loop Current system in the Gulf of Mexico using a deep learning model. Distributed by: GRIIDC, Harte Research Institute, Texas A&M University–Corpus Christi. doi:10.7266/KX3MBKQR

Publications:

Muhamed Ali, A., Zhuang, H., VanZwieten, J., Ibrahim, A. K., & Chérubin, L. (2021). A Deep Learning Model for Forecasting Velocity Structures of the Loop Current System in the Gulf of Mexico. Forecasting, 3(4), 934–953. https://doi.org/10.3390/forecast3040056

Purpose:

Develop a deep learning method to forecast the 3D velocity structure of the Loop Current the Gulf of Mexico.

Data Parameters and Units:

u [cm/s], v [cm/s], depth [m], time [12 hour time steps beginning 2009-03-02], longitude [decimal degrees], latitude [decimal degrees]. Note: The velocity matrices have dimensions [SW=20 (20-day sliding window), FCST (fourteen time steps, or 7 days), depth (0 – 500m in 20m intervals), latitude, and longitude].

Methods:

A comprehensive observational study of the Loop Current (LC) in the eastern Gulf of Mexico (GOM), including nine tall moorings and seven short moorings, an array of 25 Pressure-equipped Inverted Echo Sounders (PIES), and remote sensing, measured the water column velocity for 2.5 years, beginning in April 2009 (Hamilton et al. 2016). This array was located to cover both the east and west sides of the LC between the West Florida Slope and the Mississippi Fan and was also centered over the zone where Loop Current Eddies (LCEs) typically separate from the LC. The horizontal separation between moorings was around 50–80 km and between the PIES sensors was around 40–50 km. These recorded data were used to construct the measurement-based water velocity matrix used in this study. The subsurface velocity data measured these in-situ sensors were used to train and test a deep learning prediction method. To implement the deep learning model, we reduced the dimensionality of the tensors of each component of the velocity field to one dimension by applying EOF analysis. The obtained principal component (PC) vectors were used as input variables to a Long Short-Term Memory (LSTM) model. The prediction model was applied separately to each layer of the tensor. We defined one tensor for each direction of the Cartesian coordinate system, which led to three prediction models associated with each direction, respectively. Each model was composed of one individual LSTM model per layer in each tensor, and the final prediction consisted of the final tensor made of all the layered predictions for each velocity component. The results of this approach revealed that the prediction models associated with each of the three directions were the best at predicting the flow field in their respective directions. The errors across layers significantly altered the cross-layer structure of the flow. However, the fusion of all three models’ solutions with a Gaussian filter delivered an improved prediction field over each individual prediction.

Provenance and Historical References:

Hamilton, Peter, Alexis Lugo-Fernández, and Julio Sheinbaum. 2016. A Loop Current experiment: Field and remote measurements. Dynamics of Atmospheres and Oceans, 76, 156-173. https://doi.org/10.1016/j.dynatmoce.2016.01.005 Muhamed Ali, Ali, Hanqi Zhuang, James VanZwieten, Ali K. Ibrahim, and Laurent Chérubin. 2021. A Deep Learning Model for Forecasting Velocity Structures of the Loop Current System in the Gulf of Mexico. Forecasting 3, no. 4: 934-953. https://doi.org/10.3390/forecast3040056

Individual Files: