Searth Transformer: A Transformer Architecture Incorporating Earth's Geospheric Physical Priors for Global Mid-Range Weather Forecasting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917203797868544 |
|---|---|
| author | Li, Tianye Liu, Qi Li, Hao Chen, Lei Cheng, Wencong Zheng, Fei Xia, Xiangao Wang, Ya Huang, Gang Wang, Weiwei Tong, Xuan Zu, Ziqing Fang, Yi Fu, Shenming Jiang, Jiang Li, Haochen Li, Mingxing Xia, Jiangjiang |
| author_facet | Li, Tianye Liu, Qi Li, Hao Chen, Lei Cheng, Wencong Zheng, Fei Xia, Xiangao Wang, Ya Huang, Gang Wang, Weiwei Tong, Xuan Zu, Ziqing Fang, Yi Fu, Shenming Jiang, Jiang Li, Haochen Li, Mingxing Xia, Jiangjiang |
| contents | Accurate global medium-range weather forecasting is fundamental to Earth system science. Most existing Transformer-based forecasting models adopt vision-centric architectures that neglect the Earth's spherical geometry and zonal periodicity. In addition, conventional autoregressive training is computationally expensive and limits forecast horizons due to error accumulation. To address these challenges, we propose the Shifted Earth Transformer (Searth Transformer), a physics-informed architecture that incorporates zonal periodicity and meridional boundaries into window-based self-attention for physically consistent global information exchange. We further introduce a Relay Autoregressive (RAR) fine-tuning strategy that enables learning long-range atmospheric evolution under constrained memory and computational budgets. Based on these methods, we develop YanTian, a global medium-range weather forecasting model. YanTian achieves higher accuracy than the high-resolution forecast of the European Centre for Medium-Range Weather Forecasts and performs competitively with state-of-the-art AI models at one-degree resolution, while requiring roughly 200 times lower computational cost than standard autoregressive fine-tuning. Furthermore, YanTian attains a longer skillful forecast lead time for Z500 (10.3 days) than HRES (9 days). Beyond weather forecasting, this work establishes a robust algorithmic foundation for predictive modeling of complex global-scale geophysical circulation systems, offering new pathways for Earth system science. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_09467 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Searth Transformer: A Transformer Architecture Incorporating Earth's Geospheric Physical Priors for Global Mid-Range Weather Forecasting Li, Tianye Liu, Qi Li, Hao Chen, Lei Cheng, Wencong Zheng, Fei Xia, Xiangao Wang, Ya Huang, Gang Wang, Weiwei Tong, Xuan Zu, Ziqing Fang, Yi Fu, Shenming Jiang, Jiang Li, Haochen Li, Mingxing Xia, Jiangjiang Machine Learning Artificial Intelligence Atmospheric and Oceanic Physics Accurate global medium-range weather forecasting is fundamental to Earth system science. Most existing Transformer-based forecasting models adopt vision-centric architectures that neglect the Earth's spherical geometry and zonal periodicity. In addition, conventional autoregressive training is computationally expensive and limits forecast horizons due to error accumulation. To address these challenges, we propose the Shifted Earth Transformer (Searth Transformer), a physics-informed architecture that incorporates zonal periodicity and meridional boundaries into window-based self-attention for physically consistent global information exchange. We further introduce a Relay Autoregressive (RAR) fine-tuning strategy that enables learning long-range atmospheric evolution under constrained memory and computational budgets. Based on these methods, we develop YanTian, a global medium-range weather forecasting model. YanTian achieves higher accuracy than the high-resolution forecast of the European Centre for Medium-Range Weather Forecasts and performs competitively with state-of-the-art AI models at one-degree resolution, while requiring roughly 200 times lower computational cost than standard autoregressive fine-tuning. Furthermore, YanTian attains a longer skillful forecast lead time for Z500 (10.3 days) than HRES (9 days). Beyond weather forecasting, this work establishes a robust algorithmic foundation for predictive modeling of complex global-scale geophysical circulation systems, offering new pathways for Earth system science. |
| title | Searth Transformer: A Transformer Architecture Incorporating Earth's Geospheric Physical Priors for Global Mid-Range Weather Forecasting |
| topic | Machine Learning Artificial Intelligence Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2601.09467 |