Huracan: A skillful end-to-end data-driven system for ensemble data assimilation and weather prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908503540498432 |
|---|---|
| author | Ni, Zekun Weyn, Jonathan Zhang, Hang Xiang, Yanfei Bian, Jiang Jin, Weixin Thambiratnam, Kit Zhang, Qi Dong, Haiyu Sun, Hongyu |
| author_facet | Ni, Zekun Weyn, Jonathan Zhang, Hang Xiang, Yanfei Bian, Jiang Jin, Weixin Thambiratnam, Kit Zhang, Qi Dong, Haiyu Sun, Hongyu |
| contents | Over the past few years, machine learning-based data-driven weather prediction has been transforming operational weather forecasting by providing more accurate forecasts while using a mere fraction of computing power compared to traditional numerical weather prediction (NWP). However, those models still rely on initial conditions from NWP, putting an upper limit on their forecast abilities. A few end-to-end systems have since been proposed, but they have yet to match the forecast skill of state-of-the-art NWP competitors. In this work, we propose Huracan, an observation-driven weather forecasting system which combines an ensemble data assimilation model with a forecast model to produce highly accurate forecasts relying only on observations as inputs. Huracan is not only the first to provide ensemble initial conditions and end-to-end ensemble weather forecasts, but also the first end-to-end system to achieve an accuracy comparable with that of ECMWF ENS, the state-of-the-art NWP competitor, despite using a smaller amount of available observation data. Notably, Huracan matches or exceeds the continuous ranked probability score of ECMWF ENS on 75.4% of the variable and lead time combinations. Our work is a major step forward in end-to-end data-driven weather prediction and opens up opportunities for further improving and revolutionizing operational weather forecasting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_18486 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Huracan: A skillful end-to-end data-driven system for ensemble data assimilation and weather prediction Ni, Zekun Weyn, Jonathan Zhang, Hang Xiang, Yanfei Bian, Jiang Jin, Weixin Thambiratnam, Kit Zhang, Qi Dong, Haiyu Sun, Hongyu Atmospheric and Oceanic Physics Machine Learning Over the past few years, machine learning-based data-driven weather prediction has been transforming operational weather forecasting by providing more accurate forecasts while using a mere fraction of computing power compared to traditional numerical weather prediction (NWP). However, those models still rely on initial conditions from NWP, putting an upper limit on their forecast abilities. A few end-to-end systems have since been proposed, but they have yet to match the forecast skill of state-of-the-art NWP competitors. In this work, we propose Huracan, an observation-driven weather forecasting system which combines an ensemble data assimilation model with a forecast model to produce highly accurate forecasts relying only on observations as inputs. Huracan is not only the first to provide ensemble initial conditions and end-to-end ensemble weather forecasts, but also the first end-to-end system to achieve an accuracy comparable with that of ECMWF ENS, the state-of-the-art NWP competitor, despite using a smaller amount of available observation data. Notably, Huracan matches or exceeds the continuous ranked probability score of ECMWF ENS on 75.4% of the variable and lead time combinations. Our work is a major step forward in end-to-end data-driven weather prediction and opens up opportunities for further improving and revolutionizing operational weather forecasting. |
| title | Huracan: A skillful end-to-end data-driven system for ensemble data assimilation and weather prediction |
| topic | Atmospheric and Oceanic Physics Machine Learning |
| url | https://arxiv.org/abs/2508.18486 |