Nvidia unveils Earth-2 open models for artificial intelligence weather and climate forecasting

Nvidia has introduced the Earth-2 family of open models, libraries and frameworks at the American Meteorological Society’s Annual Meeting, describing it as a fully open, production-ready artificial intelligence software stack for weather and climate applications.

At the American Meteorological Society’s Annual Meeting, Nvidia announced the Earth-2 family of open models, positioning it as a fully open, accelerated set of tools for artificial intelligence weather and climate applications. The company described Earth-2 as a production-ready weather artificial intelligence software stack that brings together open models, libraries and frameworks to support forecasting and climate research.

Nvidia said the Earth-2 offering is designed as an integrated family of open models, libraries and frameworks, indicating that it targets both weather prediction and broader climate artificial intelligence workloads. By emphasizing that the Earth-2 stack is fully open and production-ready, Nvidia is signaling that these tools are intended for real-world deployment by researchers, meteorological agencies and developers working on operational forecasting systems.

According to Nvidia, the Earth-2 family is the world’s first fully open, production-ready weather artificial intelligence software stack, suggesting a focus on openness and accessibility for the meteorology and climate science communities. The launch at a major professional gathering for meteorologists underscores Nvidia’s aim to embed these open models and tools into existing scientific and operational workflows, providing an accelerated software foundation for advanced weather and climate artificial intelligence.

58

Impact Score

AMD and Rackspace plan dedicated AI compute rollout

AMD and Rackspace have finalized a phased deployment for dedicated AMD-based compute across Rackspace data centers. The capacity is aimed at regulated enterprise workloads, including clinical AI and large-scale inference.

Lexar tests SSD offloading for local AI models

Lexar is developing an AI-focused SSD approach designed to cut DRAM demand when running large language models on consumer PCs. Internal tests show the company’s storage offloading can load models that traditional local frameworks struggle to run with limited memory.

NVIDIA Blackwell leads MLPerf Training 6.0

NVIDIA’s latest MLPerf Training 6.0 results put Blackwell across every benchmark in the suite, including new MoE workloads. Partner systems from Microsoft Azure and CoreWeave highlighted large-cluster runs on Llama 3.1 405B and DeepSeek-V3 671B.

HPE and NVIDIA expand AI Factory for agentic systems

HPE and NVIDIA are adding agent tooling, confidential computing and updated accelerated systems across the HPE AI Factory portfolio. The expansion targets production deployments that need governance, secure data handling and integrated networking.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.