NVIDIA/earth2studio

Open-source deep-learning framework for exploring, building and deploying AI weather/climate workflows.

What it solves

Earth2Studio simplifies the process of using AI-driven weather and climate models. It provides a unified interface to access a wide variety of third-party models, datasets, and AI frameworks, removing the need to write custom code for every different model or data source.

How it works

It acts as an AI inference pipeline toolkit. By providing a unified API, it allows users to compose pipelines that chain together different data sources (like GFS or IFS), AI models (such as FourCastNet3, AIFS, and GraphCast), and output stores (like Zarr), making it easy to swap components for alternatives.

Who it’s for

Researchers and scientists in weather and climate science who want to build, research, and explore AI-driven forecasting and climate emulation.

Highlights

  • A large "model zoo" of weather and climate AI models.
  • Support for multiple data sources and optimized cloud data access.
  • Composable pipelines for complex workflows.
  • Agent-assisted setup via NVIDIA Skills to automate environment configuration and forecast runs.

Related

  • Project
    ecmwf-lab/ai-models

    A command-line tool for running AI-based weather forecasting models, providing a unified interface for data retrieval and model execution.

  • Project
    opengeos/geoai

    A Python package that integrates AI frameworks with geospatial data analysis, providing tools for satellite imagery processing, model training, and inference.

  • Project
    facebookresearch/projectaria_tools

    A suite of C++/Python utilities for processing and analyzing sensor and machine perception data from Project Aria AR glasses to support AI and machine perception research.

  • Project
    Avaiga/taipy

    A Python framework for data scientists and ML engineers to build and deploy production-ready AI and data-driven web applications without needing frontend expertise.

  • Project
    microsoft/ResearchStudio

    An AI co-author toolkit that automates the research lifecycle, from generating reviewer-defensible research ideas to creating posters, videos, and blogs from finished papers.