Eddy Detection in the Marginal Ice Zone with Sentinel-1 Data Using YOLOv5
The automatic detection and analysis of ocean eddies in the marginal ice zone via remote sensing is a very challenging task but of critical importance for scientific applications and anthropogenic activities. Therefore, as one of the first steps toward the automation of the eddy detection process, w...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/9/2244 |
| _version_ | 1797601865552101376 |
|---|---|
| author | Eduard Khachatrian Nikita Sandalyuk Pigi Lozou |
| author_facet | Eduard Khachatrian Nikita Sandalyuk Pigi Lozou |
| author_sort | Eduard Khachatrian |
| collection | DOAJ |
| description | The automatic detection and analysis of ocean eddies in the marginal ice zone via remote sensing is a very challenging task but of critical importance for scientific applications and anthropogenic activities. Therefore, as one of the first steps toward the automation of the eddy detection process, we investigated the potential of applying YOLOv5, a deep convolutional neural network architecture, to specifically collected and labeled high-resolution synthetic aperture radar data for a very dynamic area over the Fram Strait. Our approach involved fine-tuning pre-trained YOLOv5 models on a sparse dataset and achieved accurate results with minimal training data. The performances of the models were evaluated using several metrics, and the best model was selected by visual examination. The experimental results obtained from the validation and test datasets consistently demonstrated the robustness and effectiveness of the chosen model to identify submesoscale and mesoscale eddies with different structures. Moreover, our work provides a foundation for automated eddy detection in the marginal ice zone using synthetic aperture radar imagery and contributes to advancing oceanography research. |
| first_indexed | 2024-03-11T04:08:34Z |
| format | Article |
| id | doaj.art-f0779ec5aa86474da4aaa136e3bcd2bc |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T04:08:34Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-f0779ec5aa86474da4aaa136e3bcd2bc2023-11-17T23:37:29ZengMDPI AGRemote Sensing2072-42922023-04-01159224410.3390/rs15092244Eddy Detection in the Marginal Ice Zone with Sentinel-1 Data Using YOLOv5Eduard Khachatrian0Nikita Sandalyuk1Pigi Lozou2Department of Physics and Technology, UiT The Arctic University of Norway, NO-9037 Tromsø, NorwayDepartment of Oceanology, Saint Petersburg State University, 199034 Saint Petersburg, RussiaSchool of Electrical and Computer Engineering, National Technical University of Athens, 15780 Athens, GreeceThe automatic detection and analysis of ocean eddies in the marginal ice zone via remote sensing is a very challenging task but of critical importance for scientific applications and anthropogenic activities. Therefore, as one of the first steps toward the automation of the eddy detection process, we investigated the potential of applying YOLOv5, a deep convolutional neural network architecture, to specifically collected and labeled high-resolution synthetic aperture radar data for a very dynamic area over the Fram Strait. Our approach involved fine-tuning pre-trained YOLOv5 models on a sparse dataset and achieved accurate results with minimal training data. The performances of the models were evaluated using several metrics, and the best model was selected by visual examination. The experimental results obtained from the validation and test datasets consistently demonstrated the robustness and effectiveness of the chosen model to identify submesoscale and mesoscale eddies with different structures. Moreover, our work provides a foundation for automated eddy detection in the marginal ice zone using synthetic aperture radar imagery and contributes to advancing oceanography research.https://www.mdpi.com/2072-4292/15/9/2244mesoscale eddiessubmesoscale eddieseddy detectionmarginal ice zonedeep learningYOLOv5 |
| spellingShingle | Eduard Khachatrian Nikita Sandalyuk Pigi Lozou Eddy Detection in the Marginal Ice Zone with Sentinel-1 Data Using YOLOv5 Remote Sensing mesoscale eddies submesoscale eddies eddy detection marginal ice zone deep learning YOLOv5 |
| title | Eddy Detection in the Marginal Ice Zone with Sentinel-1 Data Using YOLOv5 |
| title_full | Eddy Detection in the Marginal Ice Zone with Sentinel-1 Data Using YOLOv5 |
| title_fullStr | Eddy Detection in the Marginal Ice Zone with Sentinel-1 Data Using YOLOv5 |
| title_full_unstemmed | Eddy Detection in the Marginal Ice Zone with Sentinel-1 Data Using YOLOv5 |
| title_short | Eddy Detection in the Marginal Ice Zone with Sentinel-1 Data Using YOLOv5 |
| title_sort | eddy detection in the marginal ice zone with sentinel 1 data using yolov5 |
| topic | mesoscale eddies submesoscale eddies eddy detection marginal ice zone deep learning YOLOv5 |
| url | https://www.mdpi.com/2072-4292/15/9/2244 |
| work_keys_str_mv | AT eduardkhachatrian eddydetectioninthemarginalicezonewithsentinel1datausingyolov5 AT nikitasandalyuk eddydetectioninthemarginalicezonewithsentinel1datausingyolov5 AT pigilozou eddydetectioninthemarginalicezonewithsentinel1datausingyolov5 |