4.7 Article

Semantic Segmentation of Mesoscale Eddies in the Arabian Sea: A Deep Learning Approach

期刊

REMOTE SENSING
卷 15, 期 6, 页码 -

出版社

MDPI
DOI: 10.3390/rs15061525

关键词

eddy detection; deep neural network; semantic segmentation; Arabian Sea

向作者/读者索取更多资源

Detecting and understanding mesoscale ocean eddies is crucial for studying the transport of salt, heat, and carbon in the ocean. Existing eddy detection techniques have limitations in accurately predicting non-circular or non-elliptical eddies. This study applies deep learning techniques to semantic segmentation of eddies, using human-annotated datasets that include complex geometries commonly found in the real ocean. The results show that incorporating additional surface variables as inputs to the network improves the accuracy of eddy segmentation by approximately 5%. Fine-tuning a pre-trained neural network also reduces training time and improves accuracy compared to training from scratch.
Detecting mesoscale ocean eddies provides a better understanding of the oceanic processes that govern the transport of salt, heat, and carbon. Established eddy detection techniques rely on physical or geometric criteria, and they notoriously fail to predict eddies that are neither circular nor elliptical in shape. Recently, deep learning techniques have been applied for semantic segmentation of mesoscale eddies, relying on the outputs of traditional eddy detection algorithms to supervise the training of the neural network. However, this approach limits the network's predictions because the available annotations are either circular or elliptical. Moreover, current approaches depend on the sea-surface height, temperature, or currents as inputs to the network, and these data may not provide all the information necessary to accurately segment eddies. In the present work, we have trained a neural network for the semantic segmentation of eddies using human-based-and expert-validated-annotations of eddies in the Arabian Sea. Training with human-annotated datasets enables the network predictions to include more complex geometries, which occur commonly in the real ocean. We then examine the impact of different combinations of input surface variables on the segmentation performance of the network. The results indicate that providing additional surface variables as inputs to the network improves the accuracy of the predictions by approximately 5%. We have further fine-tuned another pre-trained neural network to segment eddies and achieved a reduced overall training time and higher accuracy compared to the results from a network trained from scratch.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据