MambaRain: Multi-Scale Mamba-Attention Framework for 0-3 Hour Precipitation Nowcasting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916012528500736 |
|---|---|
| author | Shi, Chunlei Wu, Cui Xu, Xiang Li, Hao Fan, Ni Han, Xue Feng, Yongchao Zhu, Yufeng Liu, Boyu Zang, Zengliang Wang, Hongbin Yang, Yanlan Niu, Dan |
| author_facet | Shi, Chunlei Wu, Cui Xu, Xiang Li, Hao Fan, Ni Han, Xue Feng, Yongchao Zhu, Yufeng Liu, Boyu Zang, Zengliang Wang, Hongbin Yang, Yanlan Niu, Dan |
| contents | Accurate precipitation nowcasting over extended horizons (0-3 hours) is essential for disaster mitigation and operational decision-making, yet remains a critical challenge in the field. Existing deterministic approaches are predominantly constrained to shorter prediction windows (0-2 hours), exhibiting severe performance degradation beyond 90 minutes owing to their inherent difficulty in capturing long-range spatiotemporal dependencies from radar-derived observations. To address these fundamental limitations, we propose MambaRain, a novel multi-scale encoder-decoder architecture that synergistically integrates Mamba's linear-complexity long-range temporal modeling with self-attention mechanisms for explicit spatial correlation capture. The core innovation lies in a hybrid design paradigm wherein Mamba blocks leverage selective state space mechanisms to model global temporal dynamics across extended sequences with computational efficiency, while self-attention modules explicitly characterize spatial correlations within precipitation fields - a capability inherently absent in Mamba's sequential processing paradigm. This complementary synergy enables comprehensive spatiotemporal representation learning, effectively extending the viable forecasting horizon to 2-3 hours with substantial accuracy improvements. Furthermore, we introduce a spectral loss formulation to mitigate blurring artifacts characteristic of chaotic precipitation systems, thereby preserving fine-scale motion details critical for nowcasting accuracy. Experimental validation demonstrates that MambaRain substantially outperforms existing deterministic methodologies in 0-3 hour nowcasting tasks, with particularly pronounced performance gains in the challenging 2-3 hour prediction range. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_14606 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MambaRain: Multi-Scale Mamba-Attention Framework for 0-3 Hour Precipitation Nowcasting Shi, Chunlei Wu, Cui Xu, Xiang Li, Hao Fan, Ni Han, Xue Feng, Yongchao Zhu, Yufeng Liu, Boyu Zang, Zengliang Wang, Hongbin Yang, Yanlan Niu, Dan Computer Vision and Pattern Recognition Accurate precipitation nowcasting over extended horizons (0-3 hours) is essential for disaster mitigation and operational decision-making, yet remains a critical challenge in the field. Existing deterministic approaches are predominantly constrained to shorter prediction windows (0-2 hours), exhibiting severe performance degradation beyond 90 minutes owing to their inherent difficulty in capturing long-range spatiotemporal dependencies from radar-derived observations. To address these fundamental limitations, we propose MambaRain, a novel multi-scale encoder-decoder architecture that synergistically integrates Mamba's linear-complexity long-range temporal modeling with self-attention mechanisms for explicit spatial correlation capture. The core innovation lies in a hybrid design paradigm wherein Mamba blocks leverage selective state space mechanisms to model global temporal dynamics across extended sequences with computational efficiency, while self-attention modules explicitly characterize spatial correlations within precipitation fields - a capability inherently absent in Mamba's sequential processing paradigm. This complementary synergy enables comprehensive spatiotemporal representation learning, effectively extending the viable forecasting horizon to 2-3 hours with substantial accuracy improvements. Furthermore, we introduce a spectral loss formulation to mitigate blurring artifacts characteristic of chaotic precipitation systems, thereby preserving fine-scale motion details critical for nowcasting accuracy. Experimental validation demonstrates that MambaRain substantially outperforms existing deterministic methodologies in 0-3 hour nowcasting tasks, with particularly pronounced performance gains in the challenging 2-3 hour prediction range. |
| title | MambaRain: Multi-Scale Mamba-Attention Framework for 0-3 Hour Precipitation Nowcasting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.14606 |