CNCast: Leveraging 3D Swin Transformer and DiT for Enhanced Regional Weather Forecasting
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_ | 1866912279646175232 |
|---|---|
| author | Liang, Hongli Zhang, Yuanting Meng, Qingye He, Shuangshuang Yuan, Xingyuan |
| author_facet | Liang, Hongli Zhang, Yuanting Meng, Qingye He, Shuangshuang Yuan, Xingyuan |
| contents | This study introduces a cutting-edge regional weather forecasting model based on the SwinTransformer 3D architecture. This model is specifically designed to deliver precise hourly weather predictions ranging from 1 hour to 5 days, significantly improving the reliability and practicality of short-term weather forecasts. Our model has demonstrated generally superior performance when compared to Pangu, a well-established global model. The evaluation indicates that our model excels in predicting most weather variables, highlighting its potential as a more effective alternative in the field of limited area modeling. A noteworthy feature of this model is the integration of enhanced boundary conditions, inspired by traditional numerical weather prediction (NWP) techniques. This integration has substantially improved the model's predictive accuracy. Additionally, the model includes an innovative approach for diagnosing hourly total precipitation at a high spatial resolution of approximately 5 kilometers. This is achieved through a latent diffusion model, offering an alternative method for generating high-resolution precipitation data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13546 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CNCast: Leveraging 3D Swin Transformer and DiT for Enhanced Regional Weather Forecasting Liang, Hongli Zhang, Yuanting Meng, Qingye He, Shuangshuang Yuan, Xingyuan Machine Learning Artificial Intelligence This study introduces a cutting-edge regional weather forecasting model based on the SwinTransformer 3D architecture. This model is specifically designed to deliver precise hourly weather predictions ranging from 1 hour to 5 days, significantly improving the reliability and practicality of short-term weather forecasts. Our model has demonstrated generally superior performance when compared to Pangu, a well-established global model. The evaluation indicates that our model excels in predicting most weather variables, highlighting its potential as a more effective alternative in the field of limited area modeling. A noteworthy feature of this model is the integration of enhanced boundary conditions, inspired by traditional numerical weather prediction (NWP) techniques. This integration has substantially improved the model's predictive accuracy. Additionally, the model includes an innovative approach for diagnosing hourly total precipitation at a high spatial resolution of approximately 5 kilometers. This is achieved through a latent diffusion model, offering an alternative method for generating high-resolution precipitation data. |
| title | CNCast: Leveraging 3D Swin Transformer and DiT for Enhanced Regional Weather Forecasting |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2503.13546 |