WeatherMesh-3: Fast and accurate operational global weather forecasting

We present WeatherMesh-3 (WM-3), an operational transformer-based global weather forecasting system that improves the state of the art in both accuracy and computational efficiency. We introduce the following advances: 1) a latent rollout that enables arbitrary-length predictions in latent space without intermediate encoding or decoding; and 2) a modular architecture that flexibly utilizes mixed-horizon processors and encodes multiple real-time analyses to create blended initial conditions. WM-3 generates 14-day global forecasts at 0.25-degree resolution in 12 seconds on a single RTX 4090. This represents a >100,000-fold speedup over traditional NWP approaches while achieving superior accuracy with up to 37.7% improvement in RMSE over operational models, requiring only a single consumer-grade GPU for deployment. We aim for WM-3 to democratize weather forecasting by providing an accessible, lightweight model for operational use while pushing the performance boundaries of machine learning-based weather prediction.

@article{du2025_2503.22235,
  title={ WeatherMesh-3: Fast and accurate operational global weather forecasting },
  author={ Haoxing Du and Lyna Kim and Joan Creus-Costa and Jack Michaels and Anuj Shetty and Todd Hutchinson and Christopher Riedel and John Dean },
  journal={arXiv preprint arXiv:2503.22235},
  year={ 2025 }
}