Regional data-driven weather modeling with a global stretched-grid
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914936598298624 |
|---|---|
| author | Nipen, Thomas Nils Haugen, Håvard Homleid Ingstad, Magnus Sikora Nordhagen, Even Marius Salihi, Aram Farhad Shafiq Tedesco, Paulina Seierstad, Ivar Ambjørn Kristiansen, Jørn Lang, Simon Alexe, Mihai Dramsch, Jesper Raoult, Baudouin Mertes, Gert Chantry, Matthew |
| author_facet | Nipen, Thomas Nils Haugen, Håvard Homleid Ingstad, Magnus Sikora Nordhagen, Even Marius Salihi, Aram Farhad Shafiq Tedesco, Paulina Seierstad, Ivar Ambjørn Kristiansen, Jørn Lang, Simon Alexe, Mihai Dramsch, Jesper Raoult, Baudouin Mertes, Gert Chantry, Matthew |
| contents | A data-driven model (DDM) suitable for regional weather forecasting applications is presented. The model extends the Artificial Intelligence Forecasting System by introducing a stretched-grid architecture that dedicates higher resolution over a regional area of interest and maintains a lower resolution elsewhere on the globe. The model is based on graph neural networks, which naturally affords arbitrary multi-resolution grid configurations.
The model is applied to short-range weather prediction for the Nordics, producing forecasts at 2.5 km spatial and 6 h temporal resolution. The model is pre-trained on 43 years of global ERA5 data at 31 km resolution and is further refined using 3.3 years of 2.5 km resolution operational analyses from the MetCoOp Ensemble Prediction System (MEPS). The performance of the model is evaluated using surface observations from measurement stations across Norway and is compared to short-range weather forecasts from MEPS. The DDM outperforms both the control run and the ensemble mean of MEPS for 2 m temperature. The model also produces competitive precipitation and wind speed forecasts, but is shown to underestimate extreme events. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_02891 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Regional data-driven weather modeling with a global stretched-grid Nipen, Thomas Nils Haugen, Håvard Homleid Ingstad, Magnus Sikora Nordhagen, Even Marius Salihi, Aram Farhad Shafiq Tedesco, Paulina Seierstad, Ivar Ambjørn Kristiansen, Jørn Lang, Simon Alexe, Mihai Dramsch, Jesper Raoult, Baudouin Mertes, Gert Chantry, Matthew Atmospheric and Oceanic Physics Machine Learning A data-driven model (DDM) suitable for regional weather forecasting applications is presented. The model extends the Artificial Intelligence Forecasting System by introducing a stretched-grid architecture that dedicates higher resolution over a regional area of interest and maintains a lower resolution elsewhere on the globe. The model is based on graph neural networks, which naturally affords arbitrary multi-resolution grid configurations. The model is applied to short-range weather prediction for the Nordics, producing forecasts at 2.5 km spatial and 6 h temporal resolution. The model is pre-trained on 43 years of global ERA5 data at 31 km resolution and is further refined using 3.3 years of 2.5 km resolution operational analyses from the MetCoOp Ensemble Prediction System (MEPS). The performance of the model is evaluated using surface observations from measurement stations across Norway and is compared to short-range weather forecasts from MEPS. The DDM outperforms both the control run and the ensemble mean of MEPS for 2 m temperature. The model also produces competitive precipitation and wind speed forecasts, but is shown to underestimate extreme events. |
| title | Regional data-driven weather modeling with a global stretched-grid |
| topic | Atmospheric and Oceanic Physics Machine Learning |
| url | https://arxiv.org/abs/2409.02891 |