.png){kind=icon}
.png){kind=icon}
Return
Regional Data-Driven Weather Modeling with a Global Stretched Grid
.png){kind=icon}
PRE
AI
DOI：10.1175/AIES-D-25-0001.1.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We present Bris, a data-driven weather model suitable for regional forecasting applications. 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 multiresolution grid configurations. The model is applied to shortrange weather prediction for the Nordics, producing forecasts at 2.5-km spatial and 6-h temporal resolutions. Bris 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 Meteorological Cooperation (MetCoOp) Ensemble Prediction System (MEPS). The performance of the model is evaluated against surface observations from measurement stations across Norway and is compared to short-range weather forecasts from MEPS. In terms of root-mean-square error, Bris outperforms both the control run and the ensemble mean of MEPS for 2-m temperature. Bris also produces competitive precipitation and wind speed forecasts but is shown to underestimate extreme events.
Keywords:
Numerical weather prediction/forecasting
Machine learning
Neural networks
Journal
A
IF:
0
Papers:
63
Citations:
0
