Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2601.12636 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908774276530176 |
|---|---|
| author | Chowdhury, Satyaki Roy Radhakrishnan, Aswathnarayan Hsu, Hsiao Jou Subramoni, Hari Moortgat, Joachim |
| author_facet | Chowdhury, Satyaki Roy Radhakrishnan, Aswathnarayan Hsu, Hsiao Jou Subramoni, Hari Moortgat, Joachim |
| contents | Deploying Sentinel-2 satellite derived bathymetry (SDB) robustly across sites remains challenging. We analyze a Swin-Transformer based U-Net model (Swin-BathyUNet) to understand how it infers depth and when its predictions are trustworthy. A leave-one-band out study ranks spectral importance to the different bands consistent with shallow water optics. We adapt ablation-based CAM to regression (A-CAM-R) and validate the reliability via a performance retention test: keeping only the top-p% salient pixels while neutralizing the rest causes large, monotonic RMSE increase, indicating explanations localize on evidence the model relies on. Attention ablations show decoder conditioned cross attention on skips is an effective upgrade, improving robustness to glint/foam. Cross-region inference (train on one site, test on another) reveals depth-dependent degradation: MAE rises nearly linearly with depth, and bimodal depth distributions exacerbate mid/deep errors. Practical guidance follows: maintain wide receptive fields, preserve radiometric fidelity in green/blue channels, pre-filter bright high variance near shore, and pair light target site fine tuning with depth aware calibration to transfer across regions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12636 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Bands to Depth: Understanding Bathymetry Decisions on Sentinel-2 Chowdhury, Satyaki Roy Radhakrishnan, Aswathnarayan Hsu, Hsiao Jou Subramoni, Hari Moortgat, Joachim Computer Vision and Pattern Recognition Deploying Sentinel-2 satellite derived bathymetry (SDB) robustly across sites remains challenging. We analyze a Swin-Transformer based U-Net model (Swin-BathyUNet) to understand how it infers depth and when its predictions are trustworthy. A leave-one-band out study ranks spectral importance to the different bands consistent with shallow water optics. We adapt ablation-based CAM to regression (A-CAM-R) and validate the reliability via a performance retention test: keeping only the top-p% salient pixels while neutralizing the rest causes large, monotonic RMSE increase, indicating explanations localize on evidence the model relies on. Attention ablations show decoder conditioned cross attention on skips is an effective upgrade, improving robustness to glint/foam. Cross-region inference (train on one site, test on another) reveals depth-dependent degradation: MAE rises nearly linearly with depth, and bimodal depth distributions exacerbate mid/deep errors. Practical guidance follows: maintain wide receptive fields, preserve radiometric fidelity in green/blue channels, pre-filter bright high variance near shore, and pair light target site fine tuning with depth aware calibration to transfer across regions. |
| title | From Bands to Depth: Understanding Bathymetry Decisions on Sentinel-2 |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.12636 |