Three-Dimensional Spatio-Temporal Slim Weighted Generative Adversarial Imputation Network: Spatio-Temporal Silm Weighted Generative Adversarial Imputation Net to Repair Missing Ocean Current Data
Three-dimensional ocean observation is the foundation for accurately predicting ocean information. Although ocean observation sensor arrays can obtain internal data, their deployment is difficult, costly, and prone to component failures and environmental noise, resulting in discontinuous data. To ad...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/13/5/911 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849711824186900480 |
|---|---|
| author | Yiwan Yue Juan Li Yu Zhang Meiqi Ji Jingyao Zhang Rui Ma |
| author_facet | Yiwan Yue Juan Li Yu Zhang Meiqi Ji Jingyao Zhang Rui Ma |
| author_sort | Yiwan Yue |
| collection | DOAJ |
| description | Three-dimensional ocean observation is the foundation for accurately predicting ocean information. Although ocean observation sensor arrays can obtain internal data, their deployment is difficult, costly, and prone to component failures and environmental noise, resulting in discontinuous data. To address the severe missing data problem in three-dimensional ocean flow fields, this paper proposes an unsupervised model: Three-dimensional Spatio-Temporal Slim Weighted Generative Adversarial Imputation Network (3D-STA-SWGAIN). This method integrates spatio-temporal attention mechanisms and Wasserstein constraints. The generator captures the three-dimensional spatial distribution and vertical profile dynamic patterns through the spatio-temporal attention module, while the discriminator introduces gradient penalty constraints to prevent gradient vanishing. The generator strives to generate data that conforms to the real ocean flow field, and the discriminator attempts to identify pseudo-ocean current data samples. Through the adversarial training of the generator and the discriminator, high-quality completed data are generated. Additionally, a spatio-temporal continuity loss function is designed to ensure the physical rationality of the data. Experiments show that on the three-dimensional flow field dataset of the South China Sea, compared with methods such as GAIN, under a 50% random missing rate, this method reduces the error by 37.2%. It effectively solves the problem that traditional interpolation methods have difficulty handling non-uniform missing and spatio-temporal correlations and maintains the spatio-temporal continuity of the current field’s three-dimensional structure. |
| format | Article |
| id | doaj-art-512539bfc8f3407e9f80b1ddc722cb98 |
| institution | DOAJ |
| issn | 2077-1312 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj-art-512539bfc8f3407e9f80b1ddc722cb982025-08-20T03:14:31ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-05-0113591110.3390/jmse13050911Three-Dimensional Spatio-Temporal Slim Weighted Generative Adversarial Imputation Network: Spatio-Temporal Silm Weighted Generative Adversarial Imputation Net to Repair Missing Ocean Current DataYiwan Yue0Juan Li1Yu Zhang2Meiqi Ji3Jingyao Zhang4Rui Ma5Qingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266580, ChinaQingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266580, ChinaThe College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, ChinaThe College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, ChinaThe College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, ChinaThe College of Oceanography and Space Informatics, China University of Petroleum (East China), Qingdao 266580, ChinaThree-dimensional ocean observation is the foundation for accurately predicting ocean information. Although ocean observation sensor arrays can obtain internal data, their deployment is difficult, costly, and prone to component failures and environmental noise, resulting in discontinuous data. To address the severe missing data problem in three-dimensional ocean flow fields, this paper proposes an unsupervised model: Three-dimensional Spatio-Temporal Slim Weighted Generative Adversarial Imputation Network (3D-STA-SWGAIN). This method integrates spatio-temporal attention mechanisms and Wasserstein constraints. The generator captures the three-dimensional spatial distribution and vertical profile dynamic patterns through the spatio-temporal attention module, while the discriminator introduces gradient penalty constraints to prevent gradient vanishing. The generator strives to generate data that conforms to the real ocean flow field, and the discriminator attempts to identify pseudo-ocean current data samples. Through the adversarial training of the generator and the discriminator, high-quality completed data are generated. Additionally, a spatio-temporal continuity loss function is designed to ensure the physical rationality of the data. Experiments show that on the three-dimensional flow field dataset of the South China Sea, compared with methods such as GAIN, under a 50% random missing rate, this method reduces the error by 37.2%. It effectively solves the problem that traditional interpolation methods have difficulty handling non-uniform missing and spatio-temporal correlations and maintains the spatio-temporal continuity of the current field’s three-dimensional structure.https://www.mdpi.com/2077-1312/13/5/911ocean current field datagenerative adversarial imputation network (GAIN)spatio-temporal attention mechanismdata imputation |
| spellingShingle | Yiwan Yue Juan Li Yu Zhang Meiqi Ji Jingyao Zhang Rui Ma Three-Dimensional Spatio-Temporal Slim Weighted Generative Adversarial Imputation Network: Spatio-Temporal Silm Weighted Generative Adversarial Imputation Net to Repair Missing Ocean Current Data Journal of Marine Science and Engineering ocean current field data generative adversarial imputation network (GAIN) spatio-temporal attention mechanism data imputation |
| title | Three-Dimensional Spatio-Temporal Slim Weighted Generative Adversarial Imputation Network: Spatio-Temporal Silm Weighted Generative Adversarial Imputation Net to Repair Missing Ocean Current Data |
| title_full | Three-Dimensional Spatio-Temporal Slim Weighted Generative Adversarial Imputation Network: Spatio-Temporal Silm Weighted Generative Adversarial Imputation Net to Repair Missing Ocean Current Data |
| title_fullStr | Three-Dimensional Spatio-Temporal Slim Weighted Generative Adversarial Imputation Network: Spatio-Temporal Silm Weighted Generative Adversarial Imputation Net to Repair Missing Ocean Current Data |
| title_full_unstemmed | Three-Dimensional Spatio-Temporal Slim Weighted Generative Adversarial Imputation Network: Spatio-Temporal Silm Weighted Generative Adversarial Imputation Net to Repair Missing Ocean Current Data |
| title_short | Three-Dimensional Spatio-Temporal Slim Weighted Generative Adversarial Imputation Network: Spatio-Temporal Silm Weighted Generative Adversarial Imputation Net to Repair Missing Ocean Current Data |
| title_sort | three dimensional spatio temporal slim weighted generative adversarial imputation network spatio temporal silm weighted generative adversarial imputation net to repair missing ocean current data |
| topic | ocean current field data generative adversarial imputation network (GAIN) spatio-temporal attention mechanism data imputation |
| url | https://www.mdpi.com/2077-1312/13/5/911 |
| work_keys_str_mv | AT yiwanyue threedimensionalspatiotemporalslimweightedgenerativeadversarialimputationnetworkspatiotemporalsilmweightedgenerativeadversarialimputationnettorepairmissingoceancurrentdata AT juanli threedimensionalspatiotemporalslimweightedgenerativeadversarialimputationnetworkspatiotemporalsilmweightedgenerativeadversarialimputationnettorepairmissingoceancurrentdata AT yuzhang threedimensionalspatiotemporalslimweightedgenerativeadversarialimputationnetworkspatiotemporalsilmweightedgenerativeadversarialimputationnettorepairmissingoceancurrentdata AT meiqiji threedimensionalspatiotemporalslimweightedgenerativeadversarialimputationnetworkspatiotemporalsilmweightedgenerativeadversarialimputationnettorepairmissingoceancurrentdata AT jingyaozhang threedimensionalspatiotemporalslimweightedgenerativeadversarialimputationnetworkspatiotemporalsilmweightedgenerativeadversarialimputationnettorepairmissingoceancurrentdata AT ruima threedimensionalspatiotemporalslimweightedgenerativeadversarialimputationnetworkspatiotemporalsilmweightedgenerativeadversarialimputationnettorepairmissingoceancurrentdata |