Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.12328 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918517109948416 |
|---|---|
| author | Chobtham, Kiattikun Sarinnapakorn, Kanoksri Torsri, Kritanai Deeprasertkul, Prattana Kamma, Jirawan |
| author_facet | Chobtham, Kiattikun Sarinnapakorn, Kanoksri Torsri, Kritanai Deeprasertkul, Prattana Kamma, Jirawan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12328 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Teleconnections with Physics-Informed Graph Attention Networks for Long-Range Extreme Rainfall Forecasting in Thailand Chobtham, Kiattikun Sarinnapakorn, Kanoksri Torsri, Kritanai Deeprasertkul, Prattana Kamma, Jirawan Machine Learning 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. |
| title | Leveraging Teleconnections with Physics-Informed Graph Attention Networks for Long-Range Extreme Rainfall Forecasting in Thailand |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.12328 |