Dual generative adversarial networks for merging ocean transparency from satellite observations
Satellite ocean transparency data have low spatial coverage due to cloud shading, sun glint, swath width, and temporal revisit. Merging multiple satellite ocean transparency data can improve spatial coverage and create a high-accuracy data set. This study proposed a new satellite ocean transparency...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-12-01
|
| Series: | GIScience & Remote Sensing |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/15481603.2024.2356357 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850135403257921536 |
|---|---|
| author | Xuan Zhou Xiaofeng Yang Xiaomin Ye Bing Li |
| author_facet | Xuan Zhou Xiaofeng Yang Xiaomin Ye Bing Li |
| author_sort | Xuan Zhou |
| collection | DOAJ |
| description | Satellite ocean transparency data have low spatial coverage due to cloud shading, sun glint, swath width, and temporal revisit. Merging multiple satellite ocean transparency data can improve spatial coverage and create a high-accuracy data set. This study proposed a new satellite ocean transparency merging model based on dual generative adversarial networks (ZSD-merging GAN), and the products of full-coverage and high-accuracy ocean transparency were produced. The ZSD-merging GAN comprises the guess GAN and the merging GAN. The guess GAN is used to generate the guess of the ocean transparency merged product, while the merging GAN combines the guess and satellite ocean transparency data to produce the merged product. The experiments show that the spatial coverage of the ZSD-merging GAN product is 100%. The root-mean-square error (RMSE) and average relative error (ARE) between the ZSD-merging GAN product and unmerged ocean transparency data from the Visible Infrared Imaging Radiometer Suite (VIIRS) on JPSS1 are 4.31 m and 11%, respectively, which are better than 5.59 m and 17% for historical average, 5.55 m and 19% for guess product, 5.08 m and 17% for Poisson blending product, and 5.12 m and 21% for Kriging interpolation product. |
| format | Article |
| id | doaj-art-a2b2a514c30047e18541a9dcfad12429 |
| institution | OA Journals |
| issn | 1548-1603 1943-7226 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | GIScience & Remote Sensing |
| spelling | doaj-art-a2b2a514c30047e18541a9dcfad124292025-08-20T02:31:26ZengTaylor & Francis GroupGIScience & Remote Sensing1548-16031943-72262024-12-0161110.1080/15481603.2024.2356357Dual generative adversarial networks for merging ocean transparency from satellite observationsXuan Zhou0Xiaofeng Yang1Xiaomin Ye2Bing Li3Key Laboratory of Smart Planet, Beijing, ChinaState Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaNational Satellite Ocean Application Service, Beijing, ChinaKey Laboratory of Smart Planet, Beijing, ChinaSatellite ocean transparency data have low spatial coverage due to cloud shading, sun glint, swath width, and temporal revisit. Merging multiple satellite ocean transparency data can improve spatial coverage and create a high-accuracy data set. This study proposed a new satellite ocean transparency merging model based on dual generative adversarial networks (ZSD-merging GAN), and the products of full-coverage and high-accuracy ocean transparency were produced. The ZSD-merging GAN comprises the guess GAN and the merging GAN. The guess GAN is used to generate the guess of the ocean transparency merged product, while the merging GAN combines the guess and satellite ocean transparency data to produce the merged product. The experiments show that the spatial coverage of the ZSD-merging GAN product is 100%. The root-mean-square error (RMSE) and average relative error (ARE) between the ZSD-merging GAN product and unmerged ocean transparency data from the Visible Infrared Imaging Radiometer Suite (VIIRS) on JPSS1 are 4.31 m and 11%, respectively, which are better than 5.59 m and 17% for historical average, 5.55 m and 19% for guess product, 5.08 m and 17% for Poisson blending product, and 5.12 m and 21% for Kriging interpolation product.https://www.tandfonline.com/doi/10.1080/15481603.2024.2356357Ocean transparencymerginggenerative adversarial network (GAN)satellite |
| spellingShingle | Xuan Zhou Xiaofeng Yang Xiaomin Ye Bing Li Dual generative adversarial networks for merging ocean transparency from satellite observations GIScience & Remote Sensing Ocean transparency merging generative adversarial network (GAN) satellite |
| title | Dual generative adversarial networks for merging ocean transparency from satellite observations |
| title_full | Dual generative adversarial networks for merging ocean transparency from satellite observations |
| title_fullStr | Dual generative adversarial networks for merging ocean transparency from satellite observations |
| title_full_unstemmed | Dual generative adversarial networks for merging ocean transparency from satellite observations |
| title_short | Dual generative adversarial networks for merging ocean transparency from satellite observations |
| title_sort | dual generative adversarial networks for merging ocean transparency from satellite observations |
| topic | Ocean transparency merging generative adversarial network (GAN) satellite |
| url | https://www.tandfonline.com/doi/10.1080/15481603.2024.2356357 |
| work_keys_str_mv | AT xuanzhou dualgenerativeadversarialnetworksformergingoceantransparencyfromsatelliteobservations AT xiaofengyang dualgenerativeadversarialnetworksformergingoceantransparencyfromsatelliteobservations AT xiaominye dualgenerativeadversarialnetworksformergingoceantransparencyfromsatelliteobservations AT bingli dualgenerativeadversarialnetworksformergingoceantransparencyfromsatelliteobservations |