利用动态图神经网络增强SWOT像素云中的水体检测
Toward Enhanced Water Detection in SWOT Pixel Clouds using Dynamic Graph Neural Networks
- Institute of Geodesy and Photogrammetry, ETH Zurich（苏黎世联邦理工学院大地测量与摄影测量研究所）
- Deutsches Geodätisches Forschungsinstitut, Technische Universität München (DGFI-TUM)（德国大地测量学研究所，慕尼黑工业大学）
- Institute of Geodesy, University of Stuttgart（斯图加特大学大地测量研究所）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对SWOT PIXC产品在城市环境中的水体误分类问题，提出基于动态图卷积神经网络的方法，利用空间邻近性和特征相似性提升分类精度，显著提高F1分数。
AI中文摘要：
地表水与海洋地形（SWOT）任务通过其创新的宽幅测量系统提供了前所未有的淡水监测能力，该系统生成多种数据产品，包括高分辨率像素云（PIXC）产品。然而，原生PIXC水体分类在城市环境中仍容易出现系统性误分类，其中来自非水体表面的强雷达回波是主要误差来源。我们提出了一种深度学习方法，基于动态图卷积神经网络直接在SWOT PIXC数据上增强陆地-水体分类，该网络同时利用空间邻近性和特征相似性来推导二值陆地-水体类别标签。模型使用达拉斯-沃斯堡都会区一整年的PIXC数据进行训练，训练所用的像素级地面真值类别标签来源于DSWx-HLS产品，该产品基于Landsat和Sentinel-2数据提供30米空间分辨率的水体类别标签。与DSWx派生的参考相比，所提方法在时间独立测试集上将平均场景级F1分数从0.52提升至0.86，在时空测试集上从0.43提升至0.74，相对于原生PIXC分类。这些结果表明，动态图神经网络非常适合PIXC数据的不规则、点云状结构，并为在SWOT PIXC产品提供的高空间分辨率下实现更可靠的城市洪水监测和淡水制图提供了一条可扩展的路径。
英文摘要：
The Surface Water and Ocean Topography (SWOT) mission offers unprecedented freshwater monitoring capabilities through its innovative wide-swath measurement system, which generates several data products, including the high-resolution pixel cloud (PIXC) product. However, the native PIXC water classification remains prone to systematic misclassification in urban environments, where strong radar returns from non-water surfaces are the predominant error sources. We present a deep learning approach that enhances land-water classification directly on SWOT PIXC data based on a dynamic graph convolutional neural network that simultaneously exploits spatial proximity and feature similarity to derive binary land-water class labels. The model is trained on a full year of PIXC data for the Dallas-Fort Worth metropolitan area using pixel-level ground-truth class labels derived from the DSWx-HLS product, which provides water-class labels based on Landsat and Sentinel-2 at a 30\,m spatial resolution. Against the DSWx-derived reference, the proposed method increases the mean scene-level F1 score against the DSWx-derived reference from 0.52 to 0.86 on the temporally independent test set and from 0.43 to 0.74 on the spatiotemporal test set, relative to the native PIXC classification. These results demonstrate that dynamic graph neural networks are well-suited to the irregular, point-cloud-like structure of PIXC data and offer a scalable path toward more reliable urban flood monitoring and freshwater mapping at the high spatial resolution provided by the SWOT PIXC product.
