Research
Improving precipitation forecasts in an AI weather model using observational data
arXiv:2609.03210v1 Announce Type: cross Abstract: Artificial intelligence weather prediction (AIWP) systems now surpass state-of-the-art physical models for medium-range weather forecasting. Current g
arXiv:2609.03210v1 Announce Type: cross Abstract: Artificial intelligence weather prediction (AIWP) systems now surpass state-of-the-art physical models for medium-range weather forecasting. Current global AIWP models are trained almost exclusively using one reanalysis dataset, ERA5, but it has known biases, particularly for precipitation. Here we fine-tune a graph-transformer architecture with IMERG precipitation data at 0.25{eg} resolution. The resulting model improves medium-range continuous ranked probability scores by up to 19%, while also demonstrating superior skill for tropical storms and drizzle events. Our model exceeds the Brier skill score of state-of-the-art operational models on extreme rainfall prediction by 57% globally; however, a physics-based operational model remains more reliable for the heaviest precipitation events. Our results demonstrate that incorporating observations-based precipitation data directly into training can substantially improve precipitation forecasts.
Related
- Integrating GNSS-Derived Zenith Wet Delay into a Weather Foundation Model Improves Precipitation Forecasting
- Enforcing tail calibration when training probabilistic forecast models
- Uncertainty-Aware End-to-End AI Weather Forecasting: Disentangling Observation and Model Contributions
Source: arXiv cs.LG | 2026-09-04