Advanced Long-term Earth System Forecasting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917191111147520 |
|---|---|
| author | Wu, Hao Gao, Yuan Gou, Ruijian Wu, Xian Wu, Chuhan Yi, Huahui Brandstetter, Johannes Xu, Fan Wang, Kun Zhao, Penghao Jia, Hao Song, Qi Liu, Xinliang He, Juncai Cao, Shuhao Dong, Huanshuo Xiang, Yanfei Zhang, Fan Wang, Haixin Shi, Xingjian Wang, Qiufeng Li, Shuaipeng Xie, Ruobing Tao, Feng Lu, Yuxu Guo, Yu Chen, Yuntian Liang, Yuxuan Wen, Qingsong Ouyang, Wanli Chen, Deliang Boers, Niklas Huang, Xiaomeng |
| author_facet | Wu, Hao Gao, Yuan Gou, Ruijian Wu, Xian Wu, Chuhan Yi, Huahui Brandstetter, Johannes Xu, Fan Wang, Kun Zhao, Penghao Jia, Hao Song, Qi Liu, Xinliang He, Juncai Cao, Shuhao Dong, Huanshuo Xiang, Yanfei Zhang, Fan Wang, Haixin Shi, Xingjian Wang, Qiufeng Li, Shuaipeng Xie, Ruobing Tao, Feng Lu, Yuxu Guo, Yu Chen, Yuntian Liang, Yuxuan Wen, Qingsong Ouyang, Wanli Chen, Deliang Boers, Niklas Huang, Xiaomeng |
| contents | Reliable long-term forecasting of Earth system dynamics is fundamentally limited by instabilities in current artificial intelligence (AI) models during extended autoregressive simulations. These failures often originate from inherent spectral bias, leading to inadequate representation of critical high-frequency, small-scale processes and subsequent uncontrolled error amplification. Inspired by the nested grids in numerical models used to resolve small scales, we present TritonCast. At the core of its design is a dedicated latent dynamical core, which ensures the long-term stability of the macro-evolution at a coarse scale. An outer structure then fuses this stable trend with fine-grained local details. This design effectively mitigates the spectral bias caused by cross-scale interactions. In atmospheric science, it achieves state-of-the-art accuracy on the WeatherBench 2 benchmark while demonstrating exceptional long-term stability: executing year-long autoregressive global forecasts and completing multi-year climate simulations that span the entire available $2500$-day test period without drift. In oceanography, it extends skillful eddy forecast to $120$ days and exhibits unprecedented zero-shot cross-resolution generalization. Ablation studies reveal that this performance stems from the synergistic interplay of the architecture's core components. TritonCast thus offers a promising pathway towards a new generation of trustworthy, AI-driven simulations. This significant advance has the potential to accelerate discovery in climate and Earth system science, enabling more reliable long-term forecasting and deeper insights into complex geophysical dynamics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19432 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Advanced Long-term Earth System Forecasting Wu, Hao Gao, Yuan Gou, Ruijian Wu, Xian Wu, Chuhan Yi, Huahui Brandstetter, Johannes Xu, Fan Wang, Kun Zhao, Penghao Jia, Hao Song, Qi Liu, Xinliang He, Juncai Cao, Shuhao Dong, Huanshuo Xiang, Yanfei Zhang, Fan Wang, Haixin Shi, Xingjian Wang, Qiufeng Li, Shuaipeng Xie, Ruobing Tao, Feng Lu, Yuxu Guo, Yu Chen, Yuntian Liang, Yuxuan Wen, Qingsong Ouyang, Wanli Chen, Deliang Boers, Niklas Huang, Xiaomeng Machine Learning I.2.10; I.4.9 Reliable long-term forecasting of Earth system dynamics is fundamentally limited by instabilities in current artificial intelligence (AI) models during extended autoregressive simulations. These failures often originate from inherent spectral bias, leading to inadequate representation of critical high-frequency, small-scale processes and subsequent uncontrolled error amplification. Inspired by the nested grids in numerical models used to resolve small scales, we present TritonCast. At the core of its design is a dedicated latent dynamical core, which ensures the long-term stability of the macro-evolution at a coarse scale. An outer structure then fuses this stable trend with fine-grained local details. This design effectively mitigates the spectral bias caused by cross-scale interactions. In atmospheric science, it achieves state-of-the-art accuracy on the WeatherBench 2 benchmark while demonstrating exceptional long-term stability: executing year-long autoregressive global forecasts and completing multi-year climate simulations that span the entire available $2500$-day test period without drift. In oceanography, it extends skillful eddy forecast to $120$ days and exhibits unprecedented zero-shot cross-resolution generalization. Ablation studies reveal that this performance stems from the synergistic interplay of the architecture's core components. TritonCast thus offers a promising pathway towards a new generation of trustworthy, AI-driven simulations. This significant advance has the potential to accelerate discovery in climate and Earth system science, enabling more reliable long-term forecasting and deeper insights into complex geophysical dynamics. |
| title | Advanced Long-term Earth System Forecasting |
| topic | Machine Learning I.2.10; I.4.9 |
| url | https://arxiv.org/abs/2505.19432 |