- **DOI:**

https://doi.org/10.1038/s41586-023-06185-3

**Abstract:**

Weather forecasting is important for science and society. ... Here we introduce an artificial-intelligence-based method for accurate, medium-range global weather forecasting. We show that three-dimensional deep networks equipped with Earth-specific priors are effective at dealing with complex patterns in weather data, and that a hierarchical temporal aggregation strategy reduces accumulation errors in medium-range forecasting...

**Bullet points summary:**

Pangu-Weather, an AI-based weather forecasting system, uses 3D deep networks with Earth-specific priors to achieve accurate medium-range global weather forecasts.Pangu-Weather uses a hierarchical temporal aggregation strategy to reduce accumulation errors in medium-range forecasting.Pangu-Weather demonstrates stronger deterministic forecast results compared to the operational Integrated Forecasting System (IFS) of the European Centre for Medium-Range Weather Forecasts (ECMWF) on tested weather variables. It also shows improved accuracy in tracking tropical cyclones compared to ECMWF-HRES.The AI-based method of Pangu-Weather is more than 10,000 times faster than the operational IFS, offering opportunities for large-member ensemble forecasts with reduced computational costs.Pangu-Weather was trained and tested on reanalysis data and showed limitations, such as omitting certain weather variables and producing smoother forecast results. However, it shows the potential for combining AI-based and NWP methods for improved performance.

**Citation:**

Bi, K., Xie, L., Zhang, H. et al. Accurate medium-range global weather forecasting with 3D neural networks. Nature 619, 533–538 (2023). https://doi.org/10.1038/s41586-023-06185-3