arXiv：cs.LG（机器学习，全量分类）· Haoyang Jiang, Zhengui Wang, Shenghan Gao, Y. Joseph Zhang, Xingquan Zhu, Yi He·· 14 小时前AI 评分29
面向开放边界水文图的物理精炼时空预测框架
Physics-Refined Spatiotemporal Forecasting on Open-Boundary Hydrologic Graphs
AI 导读
针对开放边界水文图中外部通量缺失导致自回归预测误差累积的问题，研究者提出一种新计算框架，通过从边界与内部节点学习"幽灵节点"代理来近似未观测的外部输入，并用两个物理精炼器分别约束局部一致性与全局稳定性。该框架在两张真实水文图上取得比学习型和物理信息模型更高的预测精度与长时程稳定性，已被 ICDM 2026 接收。
正文
Abstract: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.
| Comments: | Accepted at the 2026 IEEE International Conference on Data Mining (ICDM) |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.01765 [cs.LG] |
| (or arXiv:2610.01765v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.01765 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haoyang Jiang [view email]
[v1]
Thu, 1 Oct 2026 14:24:15 UTC (1,218 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org