FuXiWeather2 Analysis Dataset

This repository hosts the FuXiWeather2 Analysis Dataset, a fully machine-learning-based, 0.25-degree global atmospheric analysis dataset covering a full year from July 1, 2023, to June 30, 2024. The dataset encompasses a comprehensive suite of meteorological variables: Upper-Air Variables (5 variables across 13 pressure levels): Temperature (T), Relative Humidity (R), Geopotential (Z), U-component of wind (U), and V-component of wind (V). The 13 pressure levels range from 1000 hPa to 50 hPa (specifically: 50, 100, 150, 200, 250, 300, 400, 500, 600, 700, 850, 925, and 1000 hPa) Surface Variables (4 variables): 10-meter U-wind component (U10), 10-meter V-wind component (V10), 2-meter Temperature (T2M), and Mean Sea-Level Pressure (MSL) For a more detailed introduction and technical specifications, please refer to the README.md file. If you use this dataset in your research, please cite our works: Sun, X., Zhong, X., Xu, X. et al. A data-to-forecast machine learning system for global weather. Nat Commun 16, 6658 (2025). https://doi.org/10.1038/s41467-025-62024-1 Xu, X., Sun, X., Zhu, S. et al. FuXiWeather2: Learning accurate atmospheric state estimation for operational global weather forecasting. arXiv:2603.15358, (2026). https://doi.org/10.48550/arXiv.2603.15358