解析哨兵-2水深反演模型的决策依据与可靠性边界
From Bands to Depth: Understanding Bathymetry Decisions on Sentinel-2
- 用Swin-BathyUNet分析光谱带重要性，符合浅水光学规律
- 仅保留关键像素时误差单调上升，验证解释聚焦真实依据
- 跨区域推理显示深度越深误差越大，需针对性优化
在不同地点稳健部署哨兵-2卫星水深反演（SDB）仍具挑战。本文分析基于Swin-Transformer的U-Net模型（Swin-BathyUNet），探究其深度推断机制及预测可信度。通过留一谱段分析，验证各波段重要性与浅水光学一致。提出基于归因的CAM用于回归（A-CAM-R），并通过性能保持测试验证：仅保留前p%显著像素而屏蔽其余，导致均方根误差（RMSE）持续增大，表明解释聚焦于模型依赖的真实证据。注意力模块消融显示，解码器条件化跨跳连接注意力是有效改进，提升对耀斑/泡沫干扰的鲁棒性。跨区域推理（在一处训练，另一处测试）揭示深度依赖性退化：平均绝对误差（MAE）随深度近似线性上升，双峰分布加剧中深层错误。实用建议包括：保持大感受野、保留绿/蓝波段辐射保真度、预滤除近岸高亮高方差区域，并结合轻量目标区域微调与深度感知校准以实现跨区迁移。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。