Identifying Oceanic Eddy With an Edge-Enhanced Multiscale Convolutional Network
Identifying oceanic eddy from remotely sensed sea surface height (SSH) data is challenging, mainly because of its large-size variations. This article proposes an automatic identification model upon convolutional neural networks for dealing with this issue. The proposed network is comprised of two br...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9924559/ |
| _version_ | 1818470605424427008 |
|---|---|
| author | Renlong Hang Gang Li Mei Xue Changming Dong Jianfen Wei |
| author_facet | Renlong Hang Gang Li Mei Xue Changming Dong Jianfen Wei |
| author_sort | Renlong Hang |
| collection | DOAJ |
| description | Identifying oceanic eddy from remotely sensed sea surface height (SSH) data is challenging, mainly because of its large-size variations. This article proposes an automatic identification model upon convolutional neural networks for dealing with this issue. The proposed network is comprised of two branches: an eddy identification branch and an edge extraction branch. Both of them adopt encoder–decoder frameworks, and the encoder is shared with each other. The eddy identification branch simultaneously uses multiscale convolution modules in the encoder and skip-layer connections between the encoder and the decoder to learn multiscale features, thus effectively identifying eddies with different sizes. Differently, the edge extraction branch is designed to learn the edge information of eddies, which is not fully captured by the eddy identification branch. To sufficiently evaluate the identification performance of our proposed model, several experiments are conducted on a public eddy identification dataset named SCSE-Eddy, and the results indicate that the proposed model is capable of achieving higher performance than those of the existing identification models. |
| first_indexed | 2024-04-13T21:39:13Z |
| format | Article |
| id | doaj.art-c1ba85b8a0494d6b8fdc100b862b6b5a |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-13T21:39:13Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-c1ba85b8a0494d6b8fdc100b862b6b5a2022-12-22T02:28:49ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01159198920710.1109/JSTARS.2022.32156969924559Identifying Oceanic Eddy With an Edge-Enhanced Multiscale Convolutional NetworkRenlong Hang0https://orcid.org/0000-0001-6046-3689Gang Li1Mei Xue2Changming Dong3Jianfen Wei4https://orcid.org/0000-0001-8655-2970Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, School of Computer, Nanjing University of Information Science and Technology, Nanjing, ChinaJiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, School of Computer, Nanjing University of Information Science and Technology, Nanjing, ChinaJiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, School of Computer, Nanjing University of Information Science and Technology, Nanjing, ChinaSouthern Marine Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai, ChinaSchool of Atmospheric Science and Remote Sensing, Wuxi University, Wuxi, ChinaIdentifying oceanic eddy from remotely sensed sea surface height (SSH) data is challenging, mainly because of its large-size variations. This article proposes an automatic identification model upon convolutional neural networks for dealing with this issue. The proposed network is comprised of two branches: an eddy identification branch and an edge extraction branch. Both of them adopt encoder–decoder frameworks, and the encoder is shared with each other. The eddy identification branch simultaneously uses multiscale convolution modules in the encoder and skip-layer connections between the encoder and the decoder to learn multiscale features, thus effectively identifying eddies with different sizes. Differently, the edge extraction branch is designed to learn the edge information of eddies, which is not fully captured by the eddy identification branch. To sufficiently evaluate the identification performance of our proposed model, several experiments are conducted on a public eddy identification dataset named SCSE-Eddy, and the results indicate that the proposed model is capable of achieving higher performance than those of the existing identification models.https://ieeexplore.ieee.org/document/9924559/Convolutional neural networkeddy identificationedge extractionmultiscale features |
| spellingShingle | Renlong Hang Gang Li Mei Xue Changming Dong Jianfen Wei Identifying Oceanic Eddy With an Edge-Enhanced Multiscale Convolutional Network IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Convolutional neural network eddy identification edge extraction multiscale features |
| title | Identifying Oceanic Eddy With an Edge-Enhanced Multiscale Convolutional Network |
| title_full | Identifying Oceanic Eddy With an Edge-Enhanced Multiscale Convolutional Network |
| title_fullStr | Identifying Oceanic Eddy With an Edge-Enhanced Multiscale Convolutional Network |
| title_full_unstemmed | Identifying Oceanic Eddy With an Edge-Enhanced Multiscale Convolutional Network |
| title_short | Identifying Oceanic Eddy With an Edge-Enhanced Multiscale Convolutional Network |
| title_sort | identifying oceanic eddy with an edge enhanced multiscale convolutional network |
| topic | Convolutional neural network eddy identification edge extraction multiscale features |
| url | https://ieeexplore.ieee.org/document/9924559/ |
| work_keys_str_mv | AT renlonghang identifyingoceaniceddywithanedgeenhancedmultiscaleconvolutionalnetwork AT gangli identifyingoceaniceddywithanedgeenhancedmultiscaleconvolutionalnetwork AT meixue identifyingoceaniceddywithanedgeenhancedmultiscaleconvolutionalnetwork AT changmingdong identifyingoceaniceddywithanedgeenhancedmultiscaleconvolutionalnetwork AT jianfenwei identifyingoceaniceddywithanedgeenhancedmultiscaleconvolutionalnetwork |