NVIDIA Earth 2 Platform

5 min read Original article ↗

Open, production-ready AI models and tools for global forecasting and planetary resilience.

Overview

Making Weather AI Accessible Worldwide

NVIDIA Earth-2 is a comprehensive family of open models, libraries, and frameworks that democratize global access to professional-grade weather and climate AI. By integrating state-of-the-art architectures, the platform provides a fully open software stack that accelerates every stage of forecasting, from data processing to high-resolution visualization. This shift from resource-intensive physics models to an end-to-end AI pipeline lets researchers, startups, and government agencies run, fine-tune, and deploy sophisticated forecasting systems on their own infrastructure with unprecedented speed and cost-efficiency.

Announcing the NVIDIA Earth-2 Family of Open Models

NVIDIA launched a new family of Earth-2 models that brings weather AI—from data processing to high-resolution visualization of local and global forecasts—to the world.

A New Paradigm in Global Forecasting

From initial data to high-resolution forecasting, NVIDIA Earth-2 provides an open, end-to-end set of tools for building sovereign AI weather systems with unprecedented speed and skill.

Earth-2 Overview Video

The Earth-2 Model Family

NVIDIA Earth-2 makes weather AI accessible worldwide at every stage, from processing observation data for initial states to generating local storm predictions and 15-day global forecasts.

Earth-2 Medium Range

The Atlas architecture delivers high-accuracy predictions for over 70 weather variables up to 15 days in advance, outperforming leading open models like GenCast on key industry benchmarks.

Earth-2 Nowcasting

Using generative AI to predict satellite and radar imagery, Earth-2 Nowcasting delivers high-fidelity, zero- to six-hour hazardous weather forecasts in minutes. It’s the first AI model to outperform traditional physics-based systems in simulating storm dynamics.

Earth-2 Global Data Assimilation (Coming Soon)

The Earth-2 Global Data Assimilations model generates precise initial atmospheric conditions in seconds on GPUs rather than hours on supercomputers. When coupled with Earth-2 Medium Range, it delivers the most skillful forecasting predictions produced by an open, entirely AI pipeline.

Earth-2 CorrDiff

CorrDiff enables generative AI downscaling 500x faster with a 10,000x improvement in energy efficiency. This augments current applications and workflows, allowing enterprises to generate more datasets for better probabilistic distributions of weather events​.​

Earth-2 FourCastNet 3

FourCastNet 3 accelerates AI-based global weather forecasting. With it, enterprises can develop solutions using datasets that are up to 20x larger, capture extreme weather events while maintaining or boosting energy efficiency.

Build Your Own AI Weather Forecasts Rapidly With Earth2Studio

Experience the next generation of weather AI. Download Earth2Studio to start building, fine-tuning, and deploying Earth-2 open models on your own infrastructure today.

Leading Adopters Across Industries

From energy and finance to global weather agencies, the Earth-2 model family is powering a new era of weather intelligence. Organizations are leveraging these open models and tools to transform raw data into actionable insights.

From Global Insights to Local Action

Explore interactive workflows to see how Earth-2 models and tools transform planetary data into actionable intelligence for energy, safety, and infrastructure.

Earth-2 Goes Down to Street Level

City-scale simulation data is now incorporated  into the Earth-2 planetary digital twin. In this video, we demonstrate the combination of high-resolution simulation data from ICON, WRF, and PALM with Google Photoreal Tiles served by Cesium using the Earth-2 visualization service to help address questions in the urban environment.

Visualize AI-Augmented Weather Simulations

Researchers are using interactive visualization of AI weather forecasts, simulation data, and archived data to analyze extreme weather.

Accelerating Carbon Capture and Storage with Fourier Neural Operator and NVIDIA PhysicsNeMo

Accelerating Carbon Capture and Storage with Fourier Neural Operator and NVIDIA PhysicsNeMo

By accelerating analysis 700,000X, NVIDIA Omniverse and PhysicsNeMo can help engineers with planning and operating carbon capture and storage, ensuring safe operation and long-term storage and reducing the amount of carbon dioxide released into our atmosphere.

Predicting Extreme Weather Events Three Weeks in Advance With FourCastNet

Predicting Extreme Weather Events Three Weeks in Advance With FourCastNet

By running FourCastNet in NVIDIA PhysicsNeMo, we were able to generate 21-day weather trajectories of 1,000 ensemble members in a tenth of the time it previously took to do a single ensemble—and with 1,000X less energy consumption.

Interactive Visualization of High-Resolution, Global-Scale Climate Data in the Cloud

Interactive Visualization of High-Resolution, Global-Scale Climate Data in the Cloud

Built on NVIDIA Omniverse and the OpenUSD 3D framework, the Earth-2 platform enables aggregation and visualization of diverse, global-scale climate simulation and geospatial datasets. Made possible with cloud-native technology, visualizations can be explored by anyone around the globe.