Abstract:Accurate rainfall forecasting, particularly for extreme events, remains a significant challenge in climatology and the Earth system. This paper presents novel physics-informed Graph Neural Networks (GNNs) combined with extreme-value analysis techniques to improve gauge-station rainfall predictions across Thailand. The model leverages a graph-structured representation of gauge stations to capture complex spatiotemporal patterns, and it offers explainability through teleconnections. We preprocess relevant climate indices that potentially influence regional rainfall. The proposed Graph Attention Network with Long Short-Term Memory (Attention-LSTM) applies the attention mechanism using initial edge features derived from simple orographic-precipitation physics formulation. The embeddings are subsequently processed by LSTM layers. To address extremes, we perform Peak-Over-Threshold (POT) mapping using the novel Spatial Season-aware Generalized Pareto Distribution (GPD) method, which overcomes limitations of traditional machine-learning models. Experiments demonstrate that our method outperforms well-established baselines across most regions, including areas prone to extremes, and remains strongly competitive with the state of the art. Compared with the operational forecasting system SEAS5, our real-world application improves extreme-event prediction and offers a practical enhancement to produce high-resolution maps that support decision-making in long-term water management.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2510.12328 [cs.LG] |
| (or arXiv:2510.12328v5 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2510.12328 arXiv-issued DOI via DataCite |
From: Kiattikun Chobtham [view email]
[v1]
Tue, 14 Oct 2025 09:34:14 UTC (2,580 KB)
[v2]
Wed, 15 Oct 2025 08:26:05 UTC (2,283 KB)
[v3]
Fri, 17 Oct 2025 07:57:57 UTC (2,260 KB)
[v4]
Sat, 25 Oct 2025 02:01:04 UTC (4,293 KB)
[v5]
Fri, 24 Apr 2026 10:06:12 UTC (3,074 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。