Reconstructing 3-D Thermohaline Structures for Mesoscale Eddies Using Satellite Observations and Deep Learning

Mesoscale eddies are circular water currents found widely in the ocean and significantly impact the ocean’s circulation, water distribution, and biology. However, our comprehension of eddies’ 3-D structures remains constrained due to the scarcity of in situ data. Therefore, we introduce a novel deep learning (DL) model, 3D-EddyNet, designed for reconstructing the 3-D thermohaline structure of mesoscale eddies. Utilizing multisource satellite data and Argo profiles collected from eddies in the North Pacific Ocean between 2000 and 2015, we optimized the 3D-EddyNet model by adjusting image sizes, introducing a convolutional block attention module (CBAM), and incorporating eddy physical parameters. The results demonstrate remarkable accuracy, with an average root mean square error (RMSE) of 0.32 °C (0.03 psu) for temperature (salinity) within anticyclonic eddies and 0.41 °C (0.04 psu) within cyclonic eddies in the upper 1000 m. We applied 3D-EddyNet to reconstruct 3-D eddy structures in the Kuroshio extension (KE) and the Oyashio current (OC) regions, demonstrating its capability to accurately represent the 3-D thermohaline eddy structures both vertically and horizontally. The consistency in the averaged 3-D eddy structures between our 3D-EddyNet and the ARMOR3D dataset in the KE and OC regions underscores the robust generalizability of our model, indicating the model’s ability to infer 3-D eddy structures when Argo profiles are unavailable. The distinctive advantage offered by 3D-EddyNet enhances our ability to understand mesoscale eddy dynamics, overcoming challenges posed by the limited availability of in situ data.