Towards submesoscale eddy detection in SDGSAT-1 data through deep learning
| Title: | Towards submesoscale eddy detection in SDGSAT-1 data through deep learning |
|---|---|
| Authors: | Ruijiao Li, Linghui Xia, Jie Yang, Baoxiang Huang, Ge Chen |
| Source: | International Journal of Digital Earth, Vol 17, Iss 1 (2024) |
| Publisher Information: | Taylor & Francis Group, 2024. |
| Publication Year: | 2024 |
| Collection: | LCC:Mathematical geography. Cartography |
| Subject Terms: | Submesoscale eddy, SDGSAT-1, deep learning, object detection, Mathematical geography. Cartography, GA1-1776 |
| More Details: | In coastal regions, the formation of submesoscale eddies is frequently influenced by factors including topography, tidal forces, and ocean currents. These eddies are often challenging to detect owing to the limited spatial resolution of altimeters and restricted observation areas. Equipped with a multispectral imager (MSI) specialized in coastal and offshore environments, SDGSAT-1 supports the sustainable development goals. It generates extensive data concerning nearshore resources. However, the multispectral data from SDGSAT-1 exhibit image blurring and indistinct eddy boundaries due to the imaging conditions of remote sensing satellites. This challenge impedes conventional deep learning models from directly identifying these features. Consequently, we developed a multispectral eddy detection network (MEDNet). Given the characteristics of remote sensing images, we employ a linear stretching technique to enhance eddy information in SDGSAT-1 images. Additionally, we propose a multispectral eddy horizontal flip technique (MEHFT) to address the imbalance between cyclonic and anticyclonic eddies in remote sensing imagery. To direct the network’s focus towards critical areas, we incorporate a multi-branch stacking construct and an SPPCSPC module to enhance eddy feature extraction. Experimental results demonstrate that our method achieves high accuracy (mAP of 90.42%) in the dataset, surpassing competing object detection models. |
| Document Type: | article |
| File Description: | electronic resource |
| Language: | English |
| ISSN: | 17538947 1753-8955 1753-8947 |
| Relation: | https://doaj.org/toc/1753-8947; https://doaj.org/toc/1753-8955 |
| DOI: | 10.1080/17538947.2024.2369625 |
| Access URL: | https://doaj.org/article/d039a4024a014eb68a48ff1632e911ca |
| Accession Number: | edsdoj.039a4024a014eb68a48ff1632e911ca |
| Database: | Directory of Open Access Journals |
| ISSN: | 17538947 17538955 |
|---|---|
| DOI: | 10.1080/17538947.2024.2369625 |
| Published in: | International Journal of Digital Earth |
| Language: | English |