FlowCast-ODE: Continuous Hourly Weather Forecasting with Dynamic Flow Matching and ODE Solver
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_ | 1866909816389107712 |
|---|---|
| author | He, Shuangshuang Zhang, Yuanting Liang, Hongli Meng, Qingye Yuan, Xingyuan Wang, Shuo |
| author_facet | He, Shuangshuang Zhang, Yuanting Liang, Hongli Meng, Qingye Yuan, Xingyuan Wang, Shuo |
| contents | Data-driven hourly weather forecasting models often face the challenge of error accumulation in long-term predictions. The problem is exacerbated by non-physical temporal discontinuities present in widely-used training datasets such as ECMWF Reanalysis v5 (ERA5), which stem from its 12-hour assimilation cycle. Such artifacts lead hourly autoregressive models to learn spurious dynamics and rapidly accumulate errors. To address this, we introduce FlowCast-ODE, a novel framework that treats atmospheric evolution as a continuous flow to ensure temporal coherence. Our method employs dynamic flow matching to learn the instantaneous velocity field from data and an ordinary differential equation (ODE) solver to generate smooth and temporally continuous hourly predictions. By pre-training on 6-hour intervals to sidestep data discontinuities and fine-tuning on hourly data, FlowCast-ODE produces seamless forecasts for up to 120 hours with a single lightweight model. It achieves competitive or superior skill on key meteorological variables compared to baseline models, preserves fine-grained spatial details, and demonstrates strong performance in forecasting extreme events, such as tropical cyclone tracks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14775 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FlowCast-ODE: Continuous Hourly Weather Forecasting with Dynamic Flow Matching and ODE Solver He, Shuangshuang Zhang, Yuanting Liang, Hongli Meng, Qingye Yuan, Xingyuan Wang, Shuo Machine Learning Data-driven hourly weather forecasting models often face the challenge of error accumulation in long-term predictions. The problem is exacerbated by non-physical temporal discontinuities present in widely-used training datasets such as ECMWF Reanalysis v5 (ERA5), which stem from its 12-hour assimilation cycle. Such artifacts lead hourly autoregressive models to learn spurious dynamics and rapidly accumulate errors. To address this, we introduce FlowCast-ODE, a novel framework that treats atmospheric evolution as a continuous flow to ensure temporal coherence. Our method employs dynamic flow matching to learn the instantaneous velocity field from data and an ordinary differential equation (ODE) solver to generate smooth and temporally continuous hourly predictions. By pre-training on 6-hour intervals to sidestep data discontinuities and fine-tuning on hourly data, FlowCast-ODE produces seamless forecasts for up to 120 hours with a single lightweight model. It achieves competitive or superior skill on key meteorological variables compared to baseline models, preserves fine-grained spatial details, and demonstrates strong performance in forecasting extreme events, such as tropical cyclone tracks. |
| title | FlowCast-ODE: Continuous Hourly Weather Forecasting with Dynamic Flow Matching and ODE Solver |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.14775 |