Observation-only learning of neural mapping schemes for gappy satellite-derived ocean colour parameters
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911287871537152 |
|---|---|
| author | Dorffer, Clément Jourdin, Frédéric Nguyen, Thi Thuy Nga Devillers, Rodolphe Mouillot, David Fablet, Ronan |
| author_facet | Dorffer, Clément Jourdin, Frédéric Nguyen, Thi Thuy Nga Devillers, Rodolphe Mouillot, David Fablet, Ronan |
| contents | Monitoring optical properties of coastal and open ocean waters is crucial to assessing the health of marine ecosystems. Deep learning offers a promising approach to address these ecosystem dynamics, especially in scenarios where gap-free ground-truth data is lacking, which poses a challenge for designing effective training frameworks. Using an advanced neural variational data assimilation scheme (called 4DVarNet), we introduce a comprehensive training framework designed to effectively train directly on gappy data sets. Using the Mediterranean Sea as a case study, our experiments not only highlight the high performance of the chosen neural network in reconstructing gap-free images from gappy datasets but also demonstrate its superior performance over state-of-the-art algorithms such as DInEOF and Direct Inversion, whether using CNN or UNet architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_11532 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Observation-only learning of neural mapping schemes for gappy satellite-derived ocean colour parameters Dorffer, Clément Jourdin, Frédéric Nguyen, Thi Thuy Nga Devillers, Rodolphe Mouillot, David Fablet, Ronan Image and Video Processing I.4.5; I.2.10 Monitoring optical properties of coastal and open ocean waters is crucial to assessing the health of marine ecosystems. Deep learning offers a promising approach to address these ecosystem dynamics, especially in scenarios where gap-free ground-truth data is lacking, which poses a challenge for designing effective training frameworks. Using an advanced neural variational data assimilation scheme (called 4DVarNet), we introduce a comprehensive training framework designed to effectively train directly on gappy data sets. Using the Mediterranean Sea as a case study, our experiments not only highlight the high performance of the chosen neural network in reconstructing gap-free images from gappy datasets but also demonstrate its superior performance over state-of-the-art algorithms such as DInEOF and Direct Inversion, whether using CNN or UNet architectures. |
| title | Observation-only learning of neural mapping schemes for gappy satellite-derived ocean colour parameters |
| topic | Image and Video Processing I.4.5; I.2.10 |
| url | https://arxiv.org/abs/2503.11532 |