Exascale Hybrid Numerical-AI Ensembles for Operational Flood-Season Forecasting in East Asia: 15-km Decadal Hindcasts and 1-km High-Resolution Capability
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916042836541440 |
|---|---|
| author | Chen, Mengxuan Xu, Yunpu Sun, Qiuyan Zhang, Han Lai, Jiayi Zhou, Zheng Zheng, Juepeng Meng, Hongsong Wei, Nan Zhang, Jinxiao Tan, Xiongchuan Bian, Haodong Cai, Yinan Yang, Ge Wang, Fang Liu, Yunyun He, Conghui Dong, Runmin Wang, Lanning Lu, Yutong Dai, Yongjiu Fu, Haohuan |
| author_facet | Chen, Mengxuan Xu, Yunpu Sun, Qiuyan Zhang, Han Lai, Jiayi Zhou, Zheng Zheng, Juepeng Meng, Hongsong Wei, Nan Zhang, Jinxiao Tan, Xiongchuan Bian, Haodong Cai, Yinan Yang, Ge Wang, Fang Liu, Yunyun He, Conghui Dong, Runmin Wang, Lanning Lu, Yutong Dai, Yongjiu Fu, Haohuan |
| contents | Seasonal forecasting of summer rainfall in East Asia remains a grand challenge, as predictability at 3 to 6 month lead times is constrained by the spring predictability barrier, weak large-scale signals, and localized nonlinear convective extremes. We address this challenge with CAPES, which integrates a kilometer-resolution coupled regional model with atmosphere, land, and ocean components and a data-driven AI seasonal forecasting system. At 15 km resolution, the fused workflow combines 174 numerical members from varying start times, physics schemes, and parameter perturbations with 1,600 AI members generated from initial and physical perturbations. Using the full LineShine system, CAPES completes ten annual 1,774-member hindcasts for 2016 to 2025 within 14.6 hours, improving the mean prediction score from ECMWF's 71.8 to 75.9 and delivering a major gain in operational forecasting capability. The 1-km configuration further enables fine-scale typhoon simulation and establishes the feasibility of kilometer-scale fused ensemble forecasting on a one-week timescale. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_24896 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Exascale Hybrid Numerical-AI Ensembles for Operational Flood-Season Forecasting in East Asia: 15-km Decadal Hindcasts and 1-km High-Resolution Capability Chen, Mengxuan Xu, Yunpu Sun, Qiuyan Zhang, Han Lai, Jiayi Zhou, Zheng Zheng, Juepeng Meng, Hongsong Wei, Nan Zhang, Jinxiao Tan, Xiongchuan Bian, Haodong Cai, Yinan Yang, Ge Wang, Fang Liu, Yunyun He, Conghui Dong, Runmin Wang, Lanning Lu, Yutong Dai, Yongjiu Fu, Haohuan Computational Engineering, Finance, and Science Atmospheric and Oceanic Physics Seasonal forecasting of summer rainfall in East Asia remains a grand challenge, as predictability at 3 to 6 month lead times is constrained by the spring predictability barrier, weak large-scale signals, and localized nonlinear convective extremes. We address this challenge with CAPES, which integrates a kilometer-resolution coupled regional model with atmosphere, land, and ocean components and a data-driven AI seasonal forecasting system. At 15 km resolution, the fused workflow combines 174 numerical members from varying start times, physics schemes, and parameter perturbations with 1,600 AI members generated from initial and physical perturbations. Using the full LineShine system, CAPES completes ten annual 1,774-member hindcasts for 2016 to 2025 within 14.6 hours, improving the mean prediction score from ECMWF's 71.8 to 75.9 and delivering a major gain in operational forecasting capability. The 1-km configuration further enables fine-scale typhoon simulation and establishes the feasibility of kilometer-scale fused ensemble forecasting on a one-week timescale. |
| title | Exascale Hybrid Numerical-AI Ensembles for Operational Flood-Season Forecasting in East Asia: 15-km Decadal Hindcasts and 1-km High-Resolution Capability |
| topic | Computational Engineering, Finance, and Science Atmospheric and Oceanic Physics |
| url | https://arxiv.org/abs/2605.24896 |