NVIDIA introduces Earth-2, a digital twin of the Earth for weather modeling and forecasting

NVIDIA introduced Earth-2 digital cloud platform for weather and climate modeling and visualization.

The new Earth-2 cloud APIs powered by NVIDIA DGX Cloud allow virtually any user to create AI-powered emulations to accelerate interactive, high-resolution simulations ranging from global atmosphere and local cloud cover to typhoons and turbulence.

Combined with proprietary data from companies in the climate industry, Earth-2’s capabilities will help forecast weather in seconds compared to minutes or hours in traditional CPU-based modeling.

“Climate disasters are now normal — historic droughts, catastrophic hurricanes and generational floods appear in the news with alarming frequency,” said Jensen Huang, founder and CEO of NVIDIA. “Earth-2 cloud APIs strive to help us better prepare for — and inspire us to act to moderate — extreme weather.”

Earth-2 uses NVIDIA’s new generative AI model called CorrDiff, which generates images with 12.5 times higher resolution, 1000 times faster, and 3000 times more energy efficient than numerical models.

Taiwan’s Central Meteorological Administration plans to use Earth-2 to predict more accurate typhoon locations.

Another key component of Earth-2’s cloud APIs is NVIDIA Omniverse, a computing platform that enables individuals and teams to develop 3D workflows and applications based on Universal Scene Description (OpenUSD).

The Weather Company, a global leader in weather forecasting and analysis, plans to integrate its Weatherverse meteorological data and tools with Omniverse, enabling customers creating digital twins to better understand and visualize the impact of actual weather conditions for the first time.

The Weather Company also plans to explore the use of NVIDIA’s score-based generative AI for its Weatherverse services.

Other early adopters of the Earth-2 API include weather analysis platform companies such as Spire and Meteomatics, which can use their own data sources and assimilate information to create accurate forecasts, as well as startups such as Tomorrow.io, north.io, and ClimaSens, which are exploring new solutions for climate technology.