发表机构
William & Mary; Virginia Institute of Marine Science, William & Mary; Florida Atlantic University（威廉与玛丽学院; 威廉与玛丽学院弗吉尼亚海洋科学研究所; 佛罗里达大西洋大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对开放边界水文图预测中的边界强迫缺失与误差累积问题，提出含幽灵节点代理和双物理精化器的计算框架，提升长时域预测精度与稳定性。
AI 中文摘要
水文图上的时空预测在开放边界系统中尤其容易出现不稳定性，在该类系统中，预测域与未观测的外部环境交换通量。在此类系统中，边界节点接收外部强迫，例如河流中的上游流入或沿海地区的潮汐信号，而这些信息在预测时通常不可用。该信息的缺失会在自回归方式展开预测时加剧误差，导致长时域预测性能不佳。本文通过探讨两个问题来剖析这一不稳定问题。1）当边界之外的信息缺失时，何种边界强迫进入预测域？2）在自回归滚动预测下，该强迫应如何在域内传播而不引起误差放大？为同时解决这两个问题，我们提出了一种新的计算框架，包含两个关键组件。首先，为补偿边界强迫，我们的框架从边界节点和内部节点学习幽灵节点代理，力求逼近未观测的外部输入。其次，为控制这些学习到的代理所产生的误差累积，我们利用两个物理精化器。特别地，一个精化器通过将幽灵代理与其两跳邻居（即边界节点及其紧邻的内部节点）对齐来强制局部一致性。另一个精化器通过物理引导的图神经算子校正模型预测来增强全局稳定性，减少长时域数值漂移。我们采用两个真实世界的水文图进行实证评估。比较结果表明，与基于学习的和物理信息的模型竞争者相比，我们的方案在预测精度和长时域稳定性方面均表现更优。
英文摘要
Spatiotemporal forecasting on hydrologic graphs is especially prone to instability in open-boundary systems, where the forecast domain exchanges fluxes with an unobserved exterior. In such systems, boundary nodes receive external forcing, e.g., upstream inflows in rivers or tidal signals in coastal regions, that is typically unavailable at prediction time. The absence of this information can compound errors as forecasts unfold in an autoregressive fashion, leading to inferior long-horizon performance. This paper dissects this instability issue by exploring two questions. 1) What boundary forcing enters the forecast domain when information beyond the boundary is missing? 2) How should this forcing propagate through the domain without incurring error amplification under autoregressive rollout? To address both, we propose a new computing framework comprising two key components. First, to compensate for the boundary forcing, our framework learns ghost node proxies from the boundary and interior nodes, striving to approximate unobserved external inputs. Second, to control error accumulation from these learned proxies, we leverage two physics refiners. In particular, one refiner enforces local consistency by aligning ghost proxies with their two-hop neighbors (i.e., boundary nodes and their immediate interiors). The other refiner enhances global stability by correcting the model forecasts through a physics-guided graph neural operator, reducing long-horizon numerical drift. Two real-world hydrologic graphs are employed for empirical evaluation. Comparative results show that our proposal enjoys higher prediction accuracy and long-horizon stability over both learning-based and physics-informed model competitors.
CommentsAccepted at the 2026 IEEE International Conference on Data Mining (ICDM)
