Ocean Eddy Identification and Tracking Using Neural Networks

  title={Ocean Eddy Identification and Tracking Using Neural Networks},
  author={Katharina Franz and Ribana Roscher and Andres Milioto and Susanne Wenzel and J{\"u}rgen Kusche},
  journal={IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium},
  • K. Franz, R. Roscher, J. Kusche
  • Published 20 March 2018
  • Environmental Science, Computer Science
  • IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium
Global climate change plays an essential role in our daily life. Mesoscale ocean eddies have a significant impact on global warming, since they affect the ocean dynamics, the energy as well as the mass transports of ocean circulation. From satellite altimetry we can derive high-resolution, global maps containing ocean signals with dominating coherent eddy structures. The aim of this study is the development and evaluation of a deep-learning based approach for the analysis of eddies. In detail… 

Figures and Tables from this paper

Mesoscale Ocean Eddy Detection Using High-Resolution Network
This work applies the improved and reliable high-resolution representation network to eddy detection and classification from Sea Surface Height (SSH) maps based on semantic segmentation and effectively combines the segmentation result with a CascadePSP module to obtain more accurate results than those produced by existing approaches.
ET-SORT: A deep learning-based method for mesoscale eddies tracking in two-dimensional time-varying flow field.
This paper improves the detector and tracker of Deep SORT to propose a model called ET-SORT, which is capable of tracking the motion trajectory and scale variation of eddies, and employs bilinear interpolation and streamline visualization methods to process the flow field data to obtain the dataset required for eddy tracking.
A Streampath-Based RCNN Approach to Ocean Eddy Detection
This paper presents a new eddy detection approach via deep neural networks to improve eddy Detection accuracy and solves the problem that eddies are difficult to detect in the sparse streampath region.
Application of Three Deep Learning Schemes Into Oceanic Eddy Detection
Recent years have witnessed the increase in applications of artificial intelligence (AI) into the detection of oceanic features. Oceanic eddies, ubiquitous in the global ocean, are important in the
Deep-SST-Eddies: A Deep Learning Framework to Detect Oceanic Eddies in Sea Surface Temperature Images
This work introduces a novel method that employs Deep Learning to detect eddy signatures on Sea Surface Temperature (SST) satellite images, and provides the first available dataset for this task, retaining SST images through altimetric-based region proposal.
Oceanic Eddy Identification Using an AI Scheme
The present study demonstrates that the AI algorithm is applicable of oceanic eddy detection, one of the first few of efforts to bridge AI techniques and oceanography research.
A Deep Learning Model for Oceanic Mesoscale Eddy Detection Based on Multi-source Remote Sensing Imagery
A multi-modal U-Net model, a deep neural network-based framework for eddy detection from multi-source remote sensing images is proposed, which improves the accuracy and efficiency of eddy Detection by using fusion data of SSH and SST.
DEDNet: Offshore Eddy Detection and Location with HF Radar by Deep Learning
Experimental results show that DEDNet performs better than the FCN-based eddy detection network and is competitive with the classical statistics-based methods.
SymmetricNet: A mesoscale eddy detection method based on multivariate fusion data
A mesoscale eddy detection method based on multivariate fusion data to solve the problem of inaccurate performance of existing detection methods, which uses Sea Surface Height (SSH) as a variable to detect.


Eddy dynamics from satellite altimetry
Most of the kinetic energy of ocean circulation is contained in ubiquitous mesoscale eddies. Their prominent signatures in sea surface height have rendered satellite altimetry highly effective in
Identification of Marine Eddies from Altimetric Maps
A procedure is presented to detect eddy cores from sea level anomaly (SLA) maps obtained from altimetric measurements. The method is based on finding the sign of Q, which is an invariant of the
Tracking coherent structures in a regional ocean model with wavelet analysis: Application to Cape Basin eddies - art. no. C05043
[1] This study is mainly aimed at proposing objective tools for the identification and tracking of three-dimensional eddy structures. It is conducted with a high-resolution numerical model of the
Global high-resolution mapping of ocean circulation from TOPEX/Poseidon and ERS-1 and -2
This study focuses on the improved estimation of mesoscale surface ocean circulation obtained by merging TOPEX/Poseidon (T/P) and ERS-1 and -2 altimeter measurements between October 1992 and May
EddyNet: A Deep Neural Network For Pixel-Wise Classification of Oceanic Eddies
EddyNet consists of a convolutional encoder-decoder followed by a pixel-wise classification layer for automated eddy detection and classification from Sea Surface Height maps provided by the Copernicus Marine and Environment Monitoring Service (CMEMS).
Oceanic eddy detection and lifetime forecast using machine learning methods
A novel altimetry-based machine learning approach for eddy identification and characterization using daily maps of geostrophic velocity anomalies and trained according to the phase angle between the zonal and meridional components at each grid point is reported.
An eddy resolving tidal-driven model of the South China Sea assimilating along-track SLA data using the EnOI
Abstract. The upper ocean circulation in the South China Sea (SCS) is driven by the Asian monsoon, the Kuroshio intrusion through the Luzon Strait, strong tidal currents, and a complex topography.
Global observations of nonlinear mesoscale eddies
Eddy activity in the four major upwelling systems from satellite altimetry (1992-2007)