Nvidia is moving into the weather game with artificial intelligence (AI). The chipmaker on Monday released three open-source artificial intelligence models aimed at helping create better weather forecasts, faster.
The announcement was made at the American Meteorological Society’s annual meeting in Houston and is part of Nvidia’s broader effort to expand the use of AI across scientific and industrial fields.
This comes just in time a powerful winter storm hit parts of the East Coast on Tuesday, bringing heavy snow, icy conditions and strong winds that disrupted travel and prompted emergency declarations in several states. The winter storm has brought cold temperatures not seen since 2021, according to AccuWeather.
READ: Amazon to use Nvidia tech in AI chips, roll out new servers (
The models are part of Nvidia’s Earth-2 family, a suite of AI-based weather forecasting tools that run on graphics processing units rather than traditional supercomputers, One model, Earth-2 Medium Range, uses Nvidia’s Atlas architecture to generate 15-day forecasts across more than 70 atmospheric variables, such as temperature, wind and humidity.
Another model, Earth-2 Nowcasting, focuses on short-term forecasts, aiming to deliver high-resolution storm predictions within a six-hour window. A third model, Earth-2 Global Data Assimilation, is designed to speed up the process of preparing initial atmospheric conditions for forecasts.
As the models are open source and available on platforms such as GitHub and Hugging Face, they could be widely adopted by researchers, governments and private companies. Nvidia says this approach may help democratize access to advanced forecasting tools, though their real-world accuracy and long-term impact will depend on further testing and adoption.
In the case of weather forecasting, Nvidia is aiming to replace expensive and time-consuming conventional weather simulations with AI-driven versions that the company said can rival or exceed the accuracy of older methods, the AI models, once trained, are also faster and cost less to run.
READ: Nvidia takes $2 billion stake in chip designer Synopsys (
By positioning its technology at the foundation of climate and meteorological research, Nvidia could strengthen its relevance in sectors where long-term public investment, government partnerships, and global collaboration are essential. This approach may deepen Nvidia’s influence across research institutions and public agencies, potentially embedding its platforms into workflows that shape policy decisions, disaster preparedness, agriculture, and energy management.
For weather forecasting more generally, the growing use of AI represents a shift in how forecasts are produced and evaluated. Instead of relying solely on physics-based simulations that demand massive computing resources, meteorology may increasingly adopt hybrid or AI-first approaches that emphasize speed, scalability, and accessibility.
Faster forecasts could translate into earlier warnings for extreme weather events, improved risk planning, and more responsive decision-making at local and regional levels. At the same time, this transition raises questions about transparency, validation, and trust, particularly when AI systems influence public safety outcomes.