FengWu
Shanghai AI Lab's deep learning-based global weather forecasting model pushing skillful forecasts beyond 10 days lead, with open-source inference code and pretrained ONNX model weights (arXiv 2023)
README
FengWu: Pushing Skillful Global Weather Forecasts beyond 10 Days Lead This repository presents the inference code and pre-trained model of FengWu, a deep learning-based weather forecasting model that pushes the skillful global weather forecasts beyond 10 days lead. The original version of FengWu has 37 vertical levels. To make it easier for real-time evaluation with operational analysis data, the pre-trained model released here accepts 13 vertical levels. If you are interested in the technique…
- Repository
- github.com/openearthlab/fengwu
Source attribution
- GitHub — github.com/openearthlab/fengwu
- Awesome AI for Science — github.com/openearthlab/fengwu
Related resources
ECMWF's unified framework and command-line tool to run AI-based weather forecasting models (GraphCast, Aurora, Pangu, NeuralGCM, FourCastNet) with operational ECMWF data infrastructure, enabling standardized inference and benchmarking across state-of-the-art meteorological AI systems (ECMWF, 576+ stars)
Microsoft's AI-powered geospatial Earth science application for natural-language exploration, visualization, and analysis of 130+ satellite collections, with STAC integration, multi-agent backend, MCP server, and deployable React/FastAPI stack (MIT, 2025)
First foundation model for weather and climate by Microsoft, Vision Transformer-based architecture trained on heterogeneous datasets (ICML 2023)
Google Research's hybrid ML/physics atmospheric model combining learned dynamics with physical constraints, outperforming traditional models on 2-15 day forecasts and 40-year climate simulation, developed with ECMWF (Nature 2024)
World's first fully open, accelerated weather AI software stack with Medium Range forecasting and Nowcasting models using generative AI (January 2026)
Microsoft's foundation model for the Earth system supporting weather, air pollution, and ocean wave forecasting at multiple resolutions, trained on 1M+ hours of diverse atmospheric data (Nature 2025)