TY - JOUR
T1 - Semantic Segmentation of Mesoscale Eddies in the Arabian Sea: A Deep Learning Approach
AU - Hammoud, Mohamad Abed ElRahman
AU - Zhan, Peng
AU - Hakla, Omar
AU - Knio, Omar
AU - Hoteit, Ibrahim
N1 - KAUST Repository Item: Exported on 2023-03-16
Acknowledged KAUST grant number(s): REP/1/3268-01-01
Acknowledgements: The research reported in this publication was supported by the Virtual Red Sea Initiative Award #REP/1/3268-01-01. We thank Issam Lakkis for his helpful discussions. We also thank Jad Bhamdouni, Louis Youssef, Nour Qaraqira, and Omar AlLahham for their help with acquiring the annotation.
PY - 2023/3/10
Y1 - 2023/3/10
N2 - 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.
AB - 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.
UR - http://hdl.handle.net/10754/690351
UR - https://www.mdpi.com/2072-4292/15/6/1525
U2 - 10.3390/rs15061525
DO - 10.3390/rs15061525
M3 - Article
SN - 2072-4292
VL - 15
SP - 1525
JO - Remote Sensing
JF - Remote Sensing
IS - 6
ER -