To accelerate efforts to combat the $140 billion in economic losses due to extreme weather brought on by climate change, NVIDIA today announced its Earth-2 climate digital twin cloud platform for simulating and visualizing weather and climate at unprecedented scale.
Part of the NVIDIA CUDA-X™ microservices, announced separately today, Earth-2’s new cloud APIs on NVIDIA DGX Cloud™ allow virtually any user to create AI-powered emulations to speed delivery of interactive, high-resolution simulations ranging from the global atmosphere and local cloud cover to typhoons and turbulence.
When combined with proprietary data owned by companies in the $20 billion climate tech industry, the Earth-2 application programming interfaces help users deliver warnings and updated forecasts in seconds compared to the minutes or hours in traditional CPU-driven modeling.
Earth-2’s APIs offer AI models and employ a new NVIDIA generative AI model called CorrDiff, using state-of-the-art diffusion modeling, that generates 12.5x higher resolution images than current numerical models 1,000x faster and 3,000x more energy efficiently. It corrects inaccuracies of coarse-resolution forecasts and synthesizes metrics critical to decision-making. CorrDiff is a first-of-its-kind generative AI model to deliver super-resolution, synthesize new metrics of interest to stakeholders, and learn the physics of fine-scale local weather from high-resolution datasets.
The Central Weather Administration of Taiwan plans to use these diffusion models to forecast more precise locations of typhoon landfall. When a typhoon warning is launched, the priority is to minimize casualties by carrying out early evacuations based on quality information generated by relevant agencies, including Taiwan’s National Science and Technology Center for Disaster Reduction (NCDR). In the last decade, the death toll due to typhoons has fallen.
Another key component of Earth-2 cloud APIs is NVIDIA Omniverse™, a computing platform that enables individuals and teams to develop Universal Scene Description (OpenUSD)-based 3D workflows and applications.
