The Flow has not summarised this story yet — read it at arXiv Machine Learning.
arXiv:2504. 20238v2 Announce Type: replace-cross Abstract: Atmospheric predictability research has long held that rapid error growth at small spatial scales imposes an intrinsic limit of roughly two weeks on deterministic weather forecast skill.
arXiv:2510. 09484v3 Announce Type: replace Abstract: Limited-Area Models (LAMs) enable weather forecasting over regional domains at higher resolutions than what is computationally feasible for global models.
The paper introduces Nested‑EAGLE, a 0.25° global weather model with a 6 km refinement over the contiguous United States, designed to merge short‑ and medium‑range forecasts into a single system. It shows lower mean‑squared error for near‑surface and low‑level variables over the U.S. compared to NOAA’s GFS and HRRR, while remaining competitive globally. Although precipitation forecasts are less skillful than HRRR’s deterministic training, Nested‑EAGLE delivers the most accurate storm‑location predictions at longer lead times, with blurred extrema.
The paper presents a graph-transformer AI weather model that is fine‑tuned with high‑resolution IMERG precipitation observations, moving beyond the traditional reliance on the ERA5 reanalysis dataset. This approach yields up to a 19% improvement in medium‑range continuous ranked probability scores and a 57% better Brier skill score for extreme rainfall compared to leading operational models, while also excelling in tropical storm and drizzle prediction. The study demonstrates that directly incorporating observation‑based precipitation data into AI training can markedly enhance forecast accuracy, though physics‑based models still outperform for the heaviest events.
The study evaluates three machine‑learning weather‑prediction models—FourCastNet3, GraphCast, and the ECMWF High‑Resolution Forecast—for wind‑speed forecasting in Northern Norway using multi‑year station data. Results show the ECMWF model slightly outperforms the ML models (RMSE 2.89 m s⁻¹ vs. 2.96 m s⁻¹ for FourCastNet3 and 2.94 m s⁻¹ for GraphCast), yet all models maintain comparable performance beyond their training periods and underestimate strong winds. FourCastNet3 performs best under high‑wind conditions, indicating ML models are competitive with traditional numerical weather prediction but still need improvement for complex terrain.
arXiv:2508. 18486v2 Announce Type: replace-cross Abstract: Over the past few years, machine learning-based data-driven weather prediction has been transforming operational weather forecasting by providing more accurate forecasts while using a mere fraction of computing power compared to traditional numerical weather prediction (NWP).