微软 Aurora
Microsoft's "Earth system"-scale AI foundation model for Earth forecasting
Microsoft's "Earth system"-scale AI foundation model for weather, air-quality, and wave forecasting.
Image generation and computer vision — detection, editing, 3D.
Key features
- Foundation model for the Earth system forecasting (Nature 2025 paper)
- Predicts atmospheric variables like temperature; pre-trained on large datasets then
- Four specialized versions: medium-res weather, high-res weather, air pollution, ocean
- Adapts to specialized atmospheric forecasting tasks with relatively little data
- Intended for research use, not direct operational decision-making
Good for
- Researchers doing weather, air pollution, or ocean wave forecasting
- Foundation-model research for atmospheric and environmental modeling
Stack & tags
PythonPyTorchweather-forecastingfoundation-modelearth-systemair-pollutionocean-wavesmicrosoftresearch
Quick start
pip install microsoft-auroraFrom the project README on GitHub.
Similar open-source projects
FLUX.2 klein
★ 25,996Black Forest Labs' sub-second image generation — generate and edit in <0.5s
DiffSynth-Studio
★ 13,200The framework behind Qwen-Image-i2L — the first "Image→LoRA" visual generation system