A Dataset and Model for Imputing Water Surface Elevation on a Large and Extremely Sparse Spatiotemporal Graph
作者: Ruben Cartuyvels, Karim Douch, Gabriele Bertoli, Mounia El Baz, Artemis Vrettou, Sébastien Lefèvre, Diego Fernandez Prieto
分类: cs.LG
发布日期: 2026-09-10
💡 一句话要点
提出AmazonSWE数据集与模型以解决水面高度估计问题
🎯 匹配领域: 支柱二：RL算法与架构 (RL & Architecture) 支柱八：物理动画 (Physics-based Animation)
关键词: 水面高度估计 数据插补 卫星测高 时空图 机器学习模型 环境监测 洪水预警
📋 核心要点
- 现有水面高度估计方法面临数据稀疏和时间覆盖不足的挑战，限制了模型的可靠性。
- 本文提出了一种双向选择性状态空间模型，通过采样连接子图并展平空间和时间来解决稀疏性问题。
- 实验结果表明，所提模型在RMSE上相较于现场测量降低了18-39%，并能为每条河段提供预测。
📝 摘要（中文）
水面高度的连续监测对于洪水预报、水资源管理和全球水循环理解至关重要。然而，全球范围内现场测量仪器的稀缺限制了可靠建模框架的发展。卫星测高技术有潜力缓解这一问题，但其稀疏的时间覆盖限制了应用。为此，本文引入了AmazonSWE数据集，整合了来自多种来源的卫星测高数据，覆盖亚马逊流域超过19,000条河段和10年的数据。该数据集的稀疏性和独特的有向无环图结构对现有插补方法提出了挑战。我们提出了一种双向选择性状态空间模型，能够在连接子图上进行采样，并将空间和时间展平为单一的令牌序列，从而在准确性上超越了现有方法。
🔬 方法详解
问题定义：本文旨在解决水面高度估计中的数据稀疏性问题，现有方法在处理稀疏和不规则的时空图时表现不佳，导致预测准确性不足。
核心思路：提出的双向选择性状态空间模型通过采样连接子图，展平空间和时间为单一令牌序列，能够更好地适应稀疏数据和复杂的河流拓扑结构。
技术框架：模型的整体架构包括数据预处理、连接子图的采样、空间时间展平以及拓扑感知的位置编码，确保信息的有效传递和利用。
关键创新：最重要的创新在于提出了一种新的模型架构，能够处理比现有基准更稀疏的图结构，且在拓扑上考虑了河流的有向无环特性。
关键设计：模型采用了特定的损失函数以优化预测精度，并在网络结构中引入了拓扑感知的位置编码，以增强模型对空间关系的理解。
🖼️ 关键图片
📊 实验亮点
实验结果显示，所提模型在与现场测量数据的对比中，RMSE降低了18-39%。此外，该模型能够为每条河段提供预测，而不仅仅是那些有足够卫星覆盖的区域，显著提升了预测的全面性和准确性。
🎯 应用场景
该研究的潜在应用领域包括洪水预警系统、水资源管理和环境监测等。通过提供更准确的水面高度预测，能够帮助决策者制定更有效的管理策略，减少自然灾害带来的损失，提升社会福祉。未来，该模型还可以扩展到其他流域或不同类型的水体监测中，具有广泛的应用前景。
📄 摘要（原文）
Continuous monitoring of water surface elevation across river networks is critical for flood forecasting, water resource management, and understanding the global water cycle. Yet, the scarcity of in situ gauges across much of the globe constrains the development of reliable modeling frameworks. Satellite altimetry has the potential to alleviate this problem but its use is currently hindered by sparse temporal coverage. To this end, we introduce AmazonSWE, a dataset for training and evaluating large-scale spatiotemporal graph imputation methods that integrates processed satellite altimetry measurements from a range of sources, including the recent wide-swath SWOT sensor. The dataset covers over 19K river sections and 10 years (2016-2026) in the Amazon river basin, with in situ gauges held out for evaluation. Besides contributing a novel real-world use case with the potential for societal impact, AmazonSWE introduces significant technical challenges: with fewer than 1% of sections observed per day, the dataset is far sparser than existing imputation benchmarks, and its directed acyclic river topology is both structurally different from and larger than graphs in existing datasets. We show that prior spatiotemporal graph imputation methods are not adapted to this topology, scale and sparsity, and propose a simple bidirectional selective state space model that outperforms them by sampling connected subgraphs and flattening space and time into a single token sequence with topology-aware positional encodings. Compared to the state-of-the-art published method for SWOT-based WSE densification, which integrates statistics with physical modeling, our model reduces RMSE against in situ gauges by 18-39%, while producing predictions for every river section rather than only those with sufficient nearby satellite coverage.