Toward Enhanced Water Detection in SWOT Pixel Clouds using Dynamic Graph Neural Networks
Abstract
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.
Related
- Convolutional neural networks for enhanced classification of VLF rock rupture precursors
- Explaining patterns learned by neural networks for detection of atmospheric surface fronts in gridded atmospheric data
- Automatic detection of laminated clouds in lidar data
- The Nonlinear Physics and Statistical Field Theory of Twilight Clouds: Hovering Dynamics and Dynamic Inertia Emergence
- Detection and characterization of deep convective clouds over the Tibetan plateau and Asian Monsoon regions using hyperspectral infrared sounders
BibTeX
@misc{baumann2026toward,
title = {{Toward Enhanced Water Detection in SWOT Pixel Clouds using Dynamic Graph Neural Networks}},
author = {Christoph Baumann and Junyang Gou and Christian Schwatke and Mohammad J. Tourian and Florian Seitz and Benedikt Soja},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.34954},
eprint = {2609.34954},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.34954},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Toward Enhanced Water Detection in SWOT Pixel Clouds using Dynamic Graph Neural Networks
AU - Christoph Baumann
AU - Junyang Gou
AU - Christian Schwatke
AU - Mohammad J. Tourian
AU - Florian Seitz
AU - Benedikt Soja
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2609.34954
UR - https://arxiv.org/abs/2609.34954
AB - 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.
ER -