From Bands to Depth: Understanding Bathymetry Decisions on Sentinel-2
This work addresses the problem of reliable bathymetry mapping for remote sensing applications, but it is incremental as it focuses on understanding and improving an existing model rather than introducing a new paradigm.
The study tackled the challenge of robustly deploying Sentinel-2 satellite-derived bathymetry across sites by analyzing a Swin-Transformer based U-Net model, finding that depth-dependent degradation leads to a nearly linear increase in MAE with depth and that bimodal depth distributions exacerbate errors.
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.