Diffusion-Based, Data-Assimilation-Enabled Super-Resolution of Hub-height Winds
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_ | 1866915532586876928 |
|---|---|
| author | Ma, Xiaolong Dong, Xu Tarrant, Ashley Yang, Lei Kotamarthi, Rao Wang, Jiali Yan, Feng Kettimuthu, Rajkumar |
| author_facet | Ma, Xiaolong Dong, Xu Tarrant, Ashley Yang, Lei Kotamarthi, Rao Wang, Jiali Yan, Feng Kettimuthu, Rajkumar |
| contents | High-quality observations of hub-height winds are valuable but sparse in space and time. Simulations are widely available on regular grids but are generally biased and too coarse to inform wind-farm siting or to assess extreme-weather-related risks (e.g., gusts) at infrastructure scales. To fully utilize both data types for generating high-quality, high-resolution hub-height wind speeds (tens to ~100m above ground), this study introduces WindSR, a diffusion model with data assimilation for super-resolution downscaling of hub-height winds. WindSR integrates sparse observational data with simulation fields during downscaling using state-of-the-art diffusion models. A dynamic-radius blending method is introduced to merge observations with simulations, providing conditioning for the diffusion process. Terrain information is incorporated during both training and inference to account for its role as a key driver of winds. Evaluated against convolutional-neural-network and generative-adversarial-network baselines, WindSR outperforms them in both downscaling efficiency and accuracy. Our data assimilation reduces WindSR's model bias by approximately 20% relative to independent observations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_03364 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Diffusion-Based, Data-Assimilation-Enabled Super-Resolution of Hub-height Winds Ma, Xiaolong Dong, Xu Tarrant, Ashley Yang, Lei Kotamarthi, Rao Wang, Jiali Yan, Feng Kettimuthu, Rajkumar Machine Learning Artificial Intelligence High-quality observations of hub-height winds are valuable but sparse in space and time. Simulations are widely available on regular grids but are generally biased and too coarse to inform wind-farm siting or to assess extreme-weather-related risks (e.g., gusts) at infrastructure scales. To fully utilize both data types for generating high-quality, high-resolution hub-height wind speeds (tens to ~100m above ground), this study introduces WindSR, a diffusion model with data assimilation for super-resolution downscaling of hub-height winds. WindSR integrates sparse observational data with simulation fields during downscaling using state-of-the-art diffusion models. A dynamic-radius blending method is introduced to merge observations with simulations, providing conditioning for the diffusion process. Terrain information is incorporated during both training and inference to account for its role as a key driver of winds. Evaluated against convolutional-neural-network and generative-adversarial-network baselines, WindSR outperforms them in both downscaling efficiency and accuracy. Our data assimilation reduces WindSR's model bias by approximately 20% relative to independent observations. |
| title | Diffusion-Based, Data-Assimilation-Enabled Super-Resolution of Hub-height Winds |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.03364 |