This work presents EddyNet, a deep learning based architecture for automated eddy detection and classification from Sea Surface Height (SSH) maps provided by the Copernicus Marine and Environment Monitoring Service (CMEMS). EddyNet consists of a convolutional encoder-decoder followed by a pixelwise classification layer. The output is a map with the same size of the input where pixels have the following labels {'0': Non eddy, '1': anticyclonic eddy, '2': cyclonic eddy}. Keras Python code, the training datasets and EddyNet weights files are open-source and freely available on https://github.com/redouanelg/EddyNet.
This paper proposes a new algorithm for parallel identification of mesoscale eddies from global satellite altimetry data. By simplifying the recognition process and the sea level anomaly (SLA) contours’ search range, the method improves identification efficiency compared with the previous SSH-based method even in the single-threaded process. The global SLA map is divided into several regions. These regions are identified simultaneously with a new SSH-based method. All the eddy identification results of these regions are merged seamlessly into a global eddy map. A β-plane approximation is used to calculate the geostrophic speed in the equatorial band. Compared with the computation complexity of the previous SSH-based method, which is , the computation complexity of the new method is , where K is the number of threads and L is the number of regional SLA maps. When applying the new method to the global SLA map, the computation is ~100 times faster than the previous SSH-based method on an average computer. The new method characterizes an eddy structure by radius, amplitude, eddy core, closed SLA contour, and closed SLA contour with maximum average geostrophic speed. In situ data and another global eddy dataset are applied to validate the reliability of eddies detected by the new algorithm. Global eddy mean properties, variability, and the geographical distribution of both datasets are analyzed to demonstrate the performance of this new method and to help understand eddy activities on a global scale.
From the recent developments of data-driven methods as a means to better exploit large-scale observation, simulation and reanalysis datasets for solving inverse problems, this study addresses the improvement of the reconstruction of higher-resolution Sea Level Anomaly (SLA) fields using analog strategies. This reconstruction is stated as an analog data assimilation issue, where the analog models rely on patch-based and Empirical Orthogonal Functions (EOF)-based representations to circumvent the curse of dimensionality. We implement an Observation System Simulation Experiment (OSSE) in the South China Sea. The reported results show the relevance of the proposed framework with a significant gain in terms of Root Mean Square Error (RMSE) for scales below 100 km. We further discuss the usefulness of the proposed analog model as a means to exploit high-resolution model simulations for the processing and analysis of current and future satellite-derived altimetric data with regard to conventional interpolation schemes, especially optimal interpolation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.