Oceanic eddies play an important role in global energy and material transport, and contribute\ngreatly to nutrient and phytoplankton distribution. Deep learning is employed to identify oceanic\neddies from sea surface height anomalies data. In order to adapt to segmentation problems for\nmulti-scale oceanic eddies, the pyramid scene parsing network (PSPNet), which is able to satisfy\nthe fusion of semantics and details, is applied as the core algorithm in the eddy detection methods.\nThe results of eddies identified from this artificial intelligence (AI) method are well compared with\nthose from a traditional vector geometry-based (VG) method. More oceanic eddies are detected by\nthe AI algorithm than the VG method, especially for small-scale eddies. Therefore, the present study\ndemonstrates that the AI algorithm is applicable of oceanic eddy detection. It is one of the first few of\nefforts to bridge AI techniques and oceanography research.
Loading....