부산대학교 도서관

Accurate and efficient identification of submesoscale ocean eddies is crucial for understanding ocean circulation, tracer mixing, and energy transfer, especially in coastal regions. However, current methodologies face challenges due to their reliance on extremely large datasets typically requiring specialized domain expertise. To address these limitations, we propose a novel semi-supervised framework in this study. Leveraging self-supervised contrastive learning, we extract meaningful features from unlabeled SAR images and fine-tune them using a small set of labeled images. By employing SimCLR and MoCo algorithms, we achieve promising outcomes and superior performance in SAR-based submesoscale eddy detection, surpassing supervised techniques. The proposed approach yields a top F1-Macro of 0.85 and 0.80-0.83 for evaluating Mediterranean and California SAR patches, respectively.