Ocean Eddy Identification and Tracking using Neural Networks
Global climate change plays an essential role in our daily life and is nowadays one of the most important topics. Mesoscale ocean eddies have a significant impact on global warming, since they dominate the ocean dynamics, the energy as well as the mass transports of ocean circulation. In particular, 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 testing of a deep-learning based approach for the analysis of eddies in the future. In detail, we develop an eddy identification and tracking framework that is mainly based on feature learning with convolutional neural networks. Furthermore, state-of-the-art image processing tools and object tracking methods are used to support the eddy tracking. In contrast to previous methods, our framework is able to learn a representation of the data in which eddies can be detected and tracked in more objective and robust way. We show first experiments on SLA data from the area of Australia and the East Australia current. We compare our eddy detection and tracking framework to established approaches such as the Okubo-Weiss method. Our preliminary results indicate that we get a more precise and robust solution as state-of-the-art techniques.
READ FULL TEXT